CN120121135B - A pointer type oil level gauge for monitoring the oil level of a transformer oil storage cabinet - Google Patents
A pointer type oil level gauge for monitoring the oil level of a transformer oil storage cabinetInfo
- Publication number
- CN120121135B CN120121135B CN202510602188.5A CN202510602188A CN120121135B CN 120121135 B CN120121135 B CN 120121135B CN 202510602188 A CN202510602188 A CN 202510602188A CN 120121135 B CN120121135 B CN 120121135B
- Authority
- CN
- China
- Prior art keywords
- oil level
- value
- oil
- level gauge
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
- G01F23/30—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm by floats
Landscapes
- Physics & Mathematics (AREA)
- Fluid Mechanics (AREA)
- General Physics & Mathematics (AREA)
- Housings And Mounting Of Transformers (AREA)
Abstract
本发明涉及油位计技术领域，公开了一种用于变压器储油柜油位监测的指针式油位计，包括：油位计组件和控制模块，控制模块与油位计组件电连接，控制模块用以对油位计组件进行控制；油位计组件包括：表盘、固定法兰、限位杆、角度传感器、限位块、旋转杆和浮子，固定法兰的上端固定连接有表盘，表盘内电连接有角度传感器，固定法兰的下端固定连接有限位杆，限位杆远离固定法兰的一端固定连接有限位块，限位杆设置有两个，两限位杆之间设置有旋转杆，且旋转杆的两端分别转动连接表盘与限位块，旋转杆的表面轴向设置有螺纹，浮子套设在旋转杆上，且浮子的两侧滑动连接两限位杆。本申请减少因长期受力导致的变形或疲劳损伤。
The present invention relates to the technical field of oil level gauges, and discloses a pointer-type oil level gauge for monitoring the oil level of a transformer oil storage cabinet, comprising: an oil level gauge assembly and a control module, wherein the control module is electrically connected to the oil level gauge assembly and is used to control the oil level gauge assembly; the oil level gauge assembly comprises: a dial, a fixed flange, a limit rod, an angle sensor, a limit block, a rotating rod, and a float, wherein the upper end of the fixed flange is fixedly connected to the dial, the dial is electrically connected to the angle sensor, the lower end of the fixed flange is fixedly connected to the limit rod, the end of the limit rod away from the fixed flange is fixedly connected to the limit block, two limit rods are provided, a rotating rod is provided between the two limit rods, and the two ends of the rotating rod are respectively rotatably connected to the dial and the limit block, the surface of the rotating rod is axially provided with a thread, the float is sleeved on the rotating rod, and the two sides of the float are slidably connected to the two limit rods. The present application reduces deformation or fatigue damage caused by long-term stress.
Description
Technical Field
The invention relates to the technical field of oil level gauges, in particular to a pointer type oil level gauge for monitoring the oil level of an oil storage tank of a transformer.
Background
The transformer is core equipment of the power system, and the internal insulating oil of the transformer not only bears the functions of insulation and heat dissipation, but also can reflect the running state of the equipment through volume change. The oil conservator (also called a conservator) is used as an important component of a transformer, and maintains stable pressure in an oil tank by compensating expansion or contraction of insulating oil caused by temperature change, so that the oil level monitoring of the conservator is performed in real time, particularly the oil level monitoring is of great significance to preventing transformer faults and guaranteeing safe operation of an electric power system, air or moisture invasion can be caused if the oil level is too low, the insulation performance is reduced, partial discharge is even short circuit is caused, and leakage or burst can be caused if the oil level is too high.
However, after the conventional oil level indicator of the oil conservator is used for a long time, various reasons such as jamming of a floating ball, breakage of a telescopic rod and the like can occur, so that a phenomenon of 'false oil level' is caused, but the actual oil level is possibly lower than a safety threshold, but the oil level alarm cannot be triggered, so that an flashover accident is caused by insulation exposure, or the inside of a transformer is locally overheated, the degradation of insulating oil is accelerated, and the false oil level can mask the change trend of the actual oil level, so that an operation and maintenance person can miss the best oil supplementing time.
Therefore, there is a need to design a pointer type oil level gauge for monitoring the oil level of a transformer oil storage tank to solve the problems in the prior art.
Disclosure of Invention
In view of the above, the invention provides a pointer type oil level gauge for monitoring the oil level of an oil storage tank of a transformer, which aims to solve the problem of low detection accuracy of the current oil level gauge.
The invention provides a pointer type oil level gauge for monitoring the oil level of a transformer oil storage cabinet, which comprises the following components:
the oil level gauge comprises an oil level gauge assembly and a control module, wherein the control module is electrically connected with the oil level gauge assembly and is used for controlling the oil level gauge assembly, and the oil level gauge assembly comprises:
Dial plate, mounting flange, gag lever post, angle sensor, stopper, rotary rod and float, mounting flange's upper end fixedly connected with the dial plate, the electricity is connected with in the dial plate angle sensor, mounting flange's lower extreme fixedly connected with the gag lever post, the gag lever post is kept away from mounting flange's one end fixedly connected with the stopper, the gag lever post is provided with two, two be provided with between the gag lever post the rotary rod, just the both ends of rotary rod are swivelling joint respectively the dial plate with the stopper, the surface axial of rotary rod is provided with the screw thread, the float cover is established on the rotary rod, just the both sides sliding connection of float two the gag lever post.
Further, the control module includes:
The acquisition unit is configured to acquire sensor data, store the sensor data at fixed time intervals and denoise, and also configured to align time stamps of the sensor data and process missing values by adopting KNN interpolation;
a judging unit configured to extract the sensor data and input the sensor data into a pre-trained state model for comparison, the judging unit being further configured to determine a current operating state of the oil level gauge assembly based on a comparison result of the state model;
And an early warning unit configured to determine abnormal areas based on the abnormal state and transmit corresponding early warning information based on the respective abnormal areas when the current operation state of the oil level gauge assembly is abnormal.
Further, when the sensor data is input into a pre-trained state model for comparison, the method comprises the following steps:
Acquiring two groups of time sequences of the sensor data, wherein one time sequence comprises a time sequence waveform of an oil level value and a time sequence waveform of oil temperature data, and the other time sequence comprises a load current effective value, an external environment temperature and humidity and a vibration intensity of an oil storage cabinet;
In a bottom layer feature learning stage, splicing two groups of time sequence waveforms of the time sequence into an oil level-oil temperature combined feature and an auxiliary feature, and forming an enhanced time sequence feature based on the oil level-oil temperature combined feature and the auxiliary feature;
in a high-level feature learning stage, extracting high-level nonlinear features layer by layer based on the enhanced time sequence features by using a dense network with a two-layer structure to form the state model;
Inputting the sensor data into the state model, carrying out waveform reconstruction and obtaining an oil level predicted value;
and determining a reconstruction error value and a prediction deviation value of the state model based on the oil level predicted value.
Further, when determining the reconstruction error value and the prediction error value of the state model based on the oil level prediction value, the method includes:
Determining the reconstruction error value based on a time sequence waveform of the oil level value, and performing temperature coefficient compensation on the reconstruction error value when the external environment temperature fluctuates;
determining a reconstruction error threshold based on the historically normal oil level values;
Acquiring actual data of the oil level value, and determining the predicted deviation value based on the oil level predicted value;
and arranging the predicted deviation values in an ascending order, and taking 95% quantiles as a predicted deviation threshold.
Further, when determining the current operation state of the oil level gauge assembly based on the comparison result of the state model, the method includes:
determining an anomaly score based on the prediction bias threshold and the reconstruction error threshold:
;
Wherein, the For the purpose of scoring the anomaly,AndIs a weight coefficient, and+=1,The value of the error is reconstructed and,The threshold value for the reconstruction error is set,In order to predict the value of the deviation,Is a threshold for predicting the deviation value.
Further, when the current operation state of the oil level gauge assembly is abnormal, it includes:
When the abnormality score is 1 or less, determining that the oil level gauge assembly is normal;
When the anomaly score is greater than 1, determining that the oil level gauge assembly is anomalous and triggering fault signature analysis;
The fault characteristic analysis is divided into false oil level, oil leakage and sensor faults;
When (when) When the reconstruction error value is larger than 0.7 and is larger than twice the reconstruction error threshold value and the prediction deviation value is smaller than the prediction deviation threshold value, the false oil level fault is judged;
When (when) When the reconstruction error value is larger than 0.7 and smaller than twice the reconstruction error threshold value and the prediction deviation value is larger than twice the prediction deviation threshold value, judging that the sensor is faulty;
When (when) And when the reconstruction error value is larger than 0.7 and smaller than twice the reconstruction error threshold value and the prediction deviation value is larger than twice the prediction deviation threshold value, judging that the oil leakage fault exists.
Further, when the current operation state of the oil level gauge assembly is abnormal, it further includes:
When the fault characteristic analysis judges that the oil level value suddenly changes, the fault characteristic analysis judges that the oil level value is false, and the fault characteristic analysis preferentially judges that the oil level value is sensor fault;
and when the fault characteristic analysis judges that the oil level is false, but the effective value of the load current is suddenly increased and the vibration intensity of the oil storage cabinet is synchronously changed, preferentially judging that the oil storage cabinet is in vibration interference.
Further, when determining an abnormal region based on the abnormal state and transmitting corresponding early warning information based on each abnormal region, the method includes:
When the early warning unit judges the false oil level, generating first-level early warning information;
when the early warning unit judges that oil leaks, generating secondary early warning information;
and when the early warning unit judges that the sensor fails, three levels of early warning information are generated.
Further, when the early warning unit judges that the current running state is abnormal, the abnormal information is stored in the historical database, fault types are marked, the state model is trained at fixed time intervals, and the threshold value is updated.
The system further comprises a remote monitoring unit, wherein the remote monitoring unit is electrically connected with the early warning unit, and is configured to monitor the running state of the early warning unit and send running state monitoring information to an Internet and cloud data platform.
Compared with the prior art, the invention has the advantages that the mechanical strength of the integral structure is enhanced through the rigid connection of the fixed flange and the limiting rod, the impact of external vibration or pressure on key components can be dispersed, deformation or fatigue damage caused by long-term stress is reduced, the free floating mode of the traditional floating ball is replaced by sliding arrangement of the floating ball along the limiting rod, the motion track of the floating ball is restrained through physical guidance, the problem of jamming caused by mechanical loosening or deflection is avoided, the stability of the motion of the floating ball is further improved through the bilateral support of the limiting rod, the linear response of the floating ball can be still maintained when the oil density changes or the temperature fluctuates, the reliability of long-term operation is improved, in addition, the matching of the rotating rod and the limiting rod improves the force transmission path, the abrasion risk caused by local stress concentration is reduced, the direct linkage of the angle sensor and the rotating rod eliminates the clearance error in the traditional indirect transmission (such as a gear and a chain), the small change of the oil level can be real-time, the linear motion of the threaded rotating rod converts the vertical displacement of the floating ball into a rotating angle signal, the nonlinear error caused by gear meshing or lever swinging is avoided, the sensitivity of the oil level detection is improved, the oil level detection is shortened, the vibration resistance is reduced, the vibration resistance is caused by the vibration of the floating rod is increased, the vibration resistance is fast, the vibration is increased, the vibration resistance is caused by the vibration, and the vibration is fast, the vibration is reduced, and the vibration is caused by the vibration, and the vibration resistance is increased, the control module is electrically connected with the angle sensor, so that the oil level data can be acquired in real time and converted digitally, and a foundation is provided for remote monitoring and automatic analysis. Through integrated control module, can discern the trend characteristic that the oil level changes, early warning potential trouble (such as seepage, jam) in advance reduces the reliance of manual work inspection.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
fig. 1 is a schematic structural diagram of a pointer type oil level gauge for monitoring an oil level of an oil storage tank of a transformer according to an embodiment of the present invention.
Fig. 2 is a functional block diagram of a pointer type oil level gauge for monitoring an oil level of an oil storage tank of a transformer according to an embodiment of the present invention.
The oil level gauge comprises 1 of an oil level gauge assembly, 101 of a dial plate, 102 of a fixed flange, 103 of a limiting rod, 104 of an angle sensor, 105 of a rotating rod, 106 of a floater, 107 of a limiting block, 108 of a screw thread.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
In some embodiments of the present application, referring to fig. 1-2, a pointer oil level gauge for transformer tank oil level monitoring, comprising:
the oil level gauge comprises an oil level gauge assembly 1 and a control module, wherein the control module is electrically connected with the oil level gauge assembly and is used for controlling the oil level gauge assembly. The oil level gauge assembly includes:
Dial plate 101, mounting flange 102, gag lever post 103, angle sensor 104, stopper 107, rotary rod 105 and float 106, mounting flange 102's upper end fixedly connected with dial plate 101, the electricity is connected with angle sensor 104 in the dial plate 101, mounting flange 102's lower extreme fixedly connected with gag lever post 103, the one end fixedly connected with stopper 107 of mounting flange 102 is kept away from to gag lever post 103, gag lever post 103 is provided with two, be provided with rotary rod 105 between two gag lever posts 103, and rotary rod 105's both ends rotate respectively and connect dial plate 101 and stopper 107, rotary rod 105's surface axial is provided with screw 108, float 106 cover is established on rotary rod 105, and float 106's both sides sliding connection two gag lever posts 103.
Specifically, dial plate 101 sets up the top at mounting flange 102, the below of mounting flange 102 is provided with two gag lever posts 103, be provided with rotary rod 105 between two gag lever posts 103, and rotary rod 105 rotates and connects dial plate 101, and dial plate 101 electricity is connected with angle sensor 104, when oil level gauge assembly 1 operates, float 106 is located the upper surface of cooling oil, float through float 106, drive rotary rod 105 and rotate, and then dial plate 101 can show the oil level data of current moment, angle sensor 104 can more accurate acquire the data of oil level simultaneously, provide data basis for control module, and control module predicts future oil level variation trend in advance through acquiring the oil temperature of oil level gauge, data such as oil level, when the forecast changes and surpasses the threshold value, can generate early warning information, the staff of being convenient for confirms the unusual region or confirms the reason of unusual event, can more convenient reply unusual event.
It can be appreciated that the rigid connection between the fixing flange 102 and the limit rod 103 enhances the stability of the structure of the oil level gauge assembly 1, can disperse the stress generated by external mechanical vibration or oil fluctuation, and reduces the deformation or abrasion of the components caused by uneven long-term stress. The guiding arrangement of the floater 106 sliding along the limiting rod 103 replaces the traditional free floating structure, so that the problem of blocking caused by mechanical loosening or deflection of the floater 106 is avoided, and the reliability of long-term operation is improved. The cooperative cooperation of the rotary rod 105 and the limit rod 103 further optimizes the movement track of the floater 106, ensures that the linear response can be maintained when the oil density changes or the temperature fluctuates, and reduces the measurement deviation caused by environmental factors. The direct linkage of the angle sensor 104 and the rotary rod 105 eliminates clearance errors in traditional indirect transmission (such as gears and chains) and can capture small changes of the oil level in real time. The linear motion mechanism of the screw 108 rotating rod 105 converts the vertical displacement of the float 106 into an accurate rotation angle signal, and nonlinear errors caused by gear engagement or lever swinging are avoided. Not only improves the sensitivity of oil level detection, but also shortens the response time of signal transmission, so that the control module can quickly reflect the dynamic change of the oil level. In addition, the contact of the float 106 and the axial threads 108 of the rotary rod 105 increases the movement contact area, reduces the movement resistance caused by the viscosity of oil or the accumulation of impurities, and further improves the measurement consistency. The physical constraint of the stop lever 103 on the movement of the float 106 suppresses malfunction caused by severe fluctuation of the oil or mechanical vibration. In the case of frequent external vibrations, such a rigid guide structure is able to filter high-frequency disturbances, ensuring that the float 106 is displaced only when the oil level is actually changing. The dial 101 is a sealed dial, which can isolate external dust, oil dirt and moisture, reduce the pollution risk of the angle sensor 104, and prolong the service life of key components. The control module can dynamically analyze the trend characteristics of the oil level change by collecting the oil level data of the angle sensor 104 in real time and combining parameters such as the oil temperature. Based on the prediction model, potential anomalies (such as leakage and jamming) can be identified in advance, early warning information is generated, fault response time is shortened, dependence on manual inspection is reduced, and meanwhile, the working complexity of operation and maintenance personnel is reduced by locating anomaly reasons (such as distinguishing mechanical faults from sensor failures).
In some embodiments of the application, the control module comprises:
The control module comprises:
The acquisition unit is configured to acquire sensor data, store the sensor data at fixed time intervals and denoise, and is further configured to align a time stamp of the sensor data and process the missing value by KNN interpolation.
And the judging unit is configured to extract the sensor data and input the sensor data into a pre-trained state model for comparison, and is further configured to determine the current running state of the oil level gauge assembly based on the comparison result of the state model.
And an early warning unit configured to determine abnormal areas based on the abnormal state and transmit corresponding early warning information based on the respective abnormal areas when the current operation state of the oil level gauge assembly is abnormal.
Specifically, the acquisition unit acquires sensor data including, but not limited to, oil level value data, oil temperature data, effective value data of transformer load current, external environment temperature and humidity data, oil conservator (oil storage cabinet) vibration intensity and the like, and a state model is an LSTM-Autoencoder model, which can predict short-term change trend of oil level, is sensitive to hidden faults such as slow leakage and false oil level, can identify the hidden faults, can capture complex time sequence relation between the oil level and the oil temperature through state model prediction, adapts to nonlinear change, further improves detection reliability through double indexes of reconstruction error and prediction deviation, reduces false alarm rate, faces the situation of sudden change of the oil level in the actual use process, therefore, the missing value is processed by adopting KNN interpolation on the sensor signal, and meanwhile, the hidden faults are identified by adopting Kalman filtering and wavelet denoising, the filtering parameters can be adjusted to inhibit high-frequency noise and low-frequency drift, up-sample the low-frequency parameters (such as external environment temperature data), align with high-frequency oil level data, store sensor data in a history database, adjust the parameters of a model with new history data periodically to adapt to data distribution changes, a judging unit compares the reconstructed oil level data to identify abnormal conditions, and because all adopted data run under normal working conditions when training the state model, when abnormal conditions occur, the data cannot be matched with the state model, reconstruction errors can occur, future change trend can be predicted, abnormal conditions can be identified, and actual measured data such as actual oil level data, actual oil temperature data and the like are combined, the difference between the predicted condition and the actual condition can be seen, and the abnormal region or the occurrence reason of the abnormal condition can be more accurately determined by combining the output predicted value of the state model, so that the early warning unit sends early warning information, and a worker can conveniently and rapidly find the abnormal condition and solve the abnormal condition.
It can be appreciated that by fusing the multisource sensor data acquisition with an intelligent pretreatment mechanism, data integrity and reliability are improved. Aiming at the dynamic change characteristics of parameters such as oil level, oil temperature, load current and the like, a time sequence alignment and interpolation filling technology is adopted, so that the problem of data missing caused by sensor communication delay or short failure is solved. The self-adaptive filtering algorithm is combined, so that the interference of high-frequency noise and low-frequency drift on an original signal is inhibited, and the measurement distortion risk caused by environmental factors is reduced. In addition, through the up-sampling processing of the low-frequency parameters, the synchronous analysis of the multi-frequency data is realized, the accuracy of cross-parameter correlation analysis is enhanced, and a consistent input basis is provided for the follow-up model reasoning. Based on a depth time sequence modeling technology, the representation capability of the oil level dynamic change and multi-parameter coupling relation is constructed. By capturing complex nonlinear correlations between oil level and parameters such as oil temperature, load current, etc., the model can identify hidden failure modes (e.g., slow leak, float jam) that are difficult to detect with traditional threshold methods. The double criterion design of the reconstruction error and the prediction deviation reduces the misjudgment probability possibly caused by a single index and simultaneously enhances the distinguishing capability of sudden abnormality and progressive fault. And the normal working condition data is focused in the model training process, so that the mode deviation in an abnormal state is more easily captured, and the sensitivity to early faults is improved. The continuous updating mechanism of the historical database and the fine-tuning strategy of the model parameters ensure the adaptability of the system to the long-term drift such as equipment aging and environmental change. By regularly merging new data into the re-optimization model, the problem of performance attenuation caused by data distribution deviation is avoided. The threshold value adjusting function further balances the false alarm rate and the missing alarm rate, so that the system can keep stable detection efficiency in different seasons or operation stages, and the sustainable service capability in complex industrial scenes is improved. The combination of the abnormal detection result and multidimensional parameter association analysis provides support for fault root cause positioning. By comparing the deviation characteristics of the predicted trend and the actual measured value, different abnormal types such as mechanical faults, sensor failure or external interference can be distinguished, and targeted alarm information can be generated. The directional diagnosis capability shortens the fault checking path of operation and maintenance personnel and reduces secondary risk possibly caused by blind overhaul. Meanwhile, the structured storage of the historical data provides a data basis for fault mode backtracking and experience accumulation, and the assistance forms a preventive maintenance strategy. Aiming at the challenges of electromagnetic interference, mechanical vibration and the like common to industrial sites, a multi-stage filtering and redundancy checking mechanism is adopted in a signal processing link, so that the influence of instantaneous interference on a detection result is reduced. The time sequence dependency modeling introduced in the model design can distinguish the real oil level change from the short-term fluctuation caused by noise, and avoid the invalid alarm triggered by accidental abnormality.
In some embodiments of the application, the input of sensor data into the pre-trained state model for comparison comprises:
and acquiring two groups of time sequences of sensor data, wherein the time sequences comprise time sequence waveforms of oil level values and time sequence waveforms of oil temperature data, and the two time sequences comprise load current effective values, external environment temperature and humidity and vibration intensity of the oil storage cabinet.
And in the bottom layer feature learning stage, splicing the two groups of time sequence waveforms into an oil level-oil temperature combined feature and an auxiliary feature, and forming an enhanced time sequence feature based on the oil level-oil temperature combined feature and the auxiliary feature.
And in the high-level feature learning stage, extracting high-order nonlinear features layer by layer based on the enhanced time sequence features by using a dense network with a two-layer structure to form a state model.
And inputting the sensor data into a state model, carrying out waveform reconstruction and acquiring an oil level predicted value.
And determining a reconstruction error value and a prediction deviation value of the state model based on the oil level prediction value.
Specifically, by acquiring oil level data, as well as oil temperature data and auxiliary timing data, the auxiliary timing data includes, but is not limited to, load current effective values: reflecting the load condition, the environmental temperature is used for analyzing the running state and load change of equipment, the environmental temperature is used for monitoring the environmental temperature around an oil storage cabinet, the environmental humidity is used for evaluating the influence of the temperature on the running of the equipment, the environmental humidity is used for monitoring the environmental humidity around the oil storage cabinet, the influence of the humidity on the insulating performance of the equipment is evaluated, the power factor is used for reflecting the power utilization efficiency of the equipment, the operating efficiency and the energy consumption condition of the equipment are analyzed, the active power and the reactive power are used for evaluating the actual power output and the energy consumption of the equipment, the equipment temperature is used for monitoring the temperature of the oil temperature, the running state and the overheat risk of the equipment are evaluated, the vibration data is used for monitoring the vibration condition of the equipment, the mechanical state of the equipment and the potential fault and other information are judged, the state model is an LSTM-Autoencoder model, the time sequence data (such as oil level, oil temperature, load current and the like) in an input time window are used for extracting time sequence characteristics through an encoder, the potential space representation is compressed, the oil level value of a future time step is predicted through a decoder, and the reconstruction error is calculated, the original waveform is input in the bottom characteristic learning stage, low-dimensional time sequence characteristic is obtained, the auxiliary data is encoded through the input, the low dimensional time sequence characteristic is obtained, the auxiliary data is encoded through the input, the data is input into the complete sequence characteristic data, and the training characteristic data is not obtained through the training characteristic, and the training is obtained through the training and the final error, and the error is input, that is, the error value is reconstructed:
, wherein, The value of the error is reconstructed and,The actual oil level value (in%) for time t,For the oil level value (in%) reconstructed for the model, T is the time-series window length, and the predicted deviation value: , wherein, In order to predict the value of the deviation,In order to predict the number of time steps,For the actual oil level value at the kth time point in the future,A future kth point in time oil level value predicted for the model.
In some embodiments of the application, determining the reconstructed error value and the predicted deviation value of the state model based on the oil level predicted value comprises:
A reconstruction error value is determined based on the time-series waveform of the oil level value, and temperature coefficient compensation is performed on the reconstruction error value when the external ambient temperature fluctuates.
A reconstruction error threshold is determined based on the historical normal oil level values.
Actual data of the oil level value is acquired, and a predicted deviation value is determined based on the oil level predicted value.
The predicted deviation values are arranged in an ascending order, and 95% quantiles are taken as the predicted deviation threshold.
Specifically, temperature coefficient compensation: Wherein For an ambient temperature change, if the ambient temperature fluctuates (e.g., the temperature change is greater than 15 ℃ within 24 hours), the reconstruction error is multiplied by the temperature compensation coefficientThe reconstruction error threshold is determined by using data of the training state model: , wherein, The quantile of the data set used to train the state model,A reconstruction error set of the data set used for training the state model,Reconstructing the error threshold for all prediction errorsAccording to ascending order, 95% quantiles are taken as a prediction deviation threshold value.
In some embodiments of the application, determining the current operating state of the oil level gauge assembly based on the comparison of the state models includes:
determining an anomaly score based on the prediction bias threshold and the reconstruction error threshold:
。
Wherein, the For the purpose of scoring the anomaly,AndIs a weight coefficient, and+=1,The value of the error is reconstructed and,The threshold value for the reconstruction error is set,In order to predict the value of the deviation,Is a threshold for predicting the deviation value.
In some embodiments of the application, when the current operating state of the oil level gauge assembly is abnormal, it includes:
When the abnormality score is 1 or less, it is determined that the oil level gauge assembly is normal.
When the abnormality score is greater than 1, it is determined that the oil level gauge assembly is abnormal, and a fault signature analysis is triggered.
Fault signature analysis is divided into false oil level, oil leakage and sensor faults.
When (when)And when the reconstruction error value is larger than 0.7 and is larger than twice the reconstruction error threshold value and the prediction deviation value is smaller than the prediction deviation threshold value, the false oil level fault is judged.
When (when)And when the reconstruction error value is larger than 0.7 and smaller than twice the reconstruction error threshold value and the prediction deviation value is larger than twice the prediction deviation threshold value, judging that the sensor is faulty.
When (when)And when the reconstruction error value is larger than 0.7 and smaller than twice the reconstruction error threshold value and the prediction deviation value is larger than twice the prediction deviation threshold value, judging that the oil leakage fault exists.
It can be appreciated that by fusing the double criteria of the reconstruction error and the prediction deviation, the abnormal signal in the oil level monitoring can be more comprehensively captured. The reconstruction error focuses on the sensitivity to the deviation of the current data mode, and the prediction deviation strengthens the early warning capability of future trend abnormity. The weighted combination of the two reduces the risk of false positives that may be caused by a single indicator, e.g., relying on reconstruction errors alone may ignore early signs of slow leakage, while relying on prediction bias alone may produce an excessive response to transient noise. The cooperative action improves the coverage range and the reliability of anomaly detection, and ensures the accurate capture of complex fault modes (such as intermittent jamming or gradual oil leakage). Based on the judgment logic of the combination of the abnormal score component duty ratio and the threshold value, the diagnosis accuracy of the fault root cause is improved. By setting a differentiation threshold value of the weight coefficient (such as false oil level side reconstruction error leading and oil leakage side reconstruction deviation leading), mechanical faults, sensor failure and actual oil level abnormality can be distinguished. For example, the relative stability of overrun of reconstruction errors and predicted deviations in false oil level decisions may exclude disturbances of sensor noise or environmental disturbances. The continuous exceeding of the prediction deviation and the controllable range of the reconstruction error in the oil leakage judgment can reflect the real risk of continuous drop of the oil level, reduce the possibility of fault confusion through refined classification, and provide clear basis for targeted maintenance. By adopting multi-level threshold decision (such as double error threshold), fault scenes with different severity can be self-adapted. For significant overrun (e.g., exceeding a doubled threshold) of reconstruction errors or prediction bias, high risk faults (e.g., sensor failure or severe oil leakage) can be quickly identified, shortening the response time of critical faults. And under the condition of slight overrun, the comprehensive scoring mechanism is combined with other parameters to further verify, so that excessive response to accidental fluctuation is avoided, the detection sensitivity and specificity are balanced, and the stability under the complex working condition is improved. The direct mapping relation between the abnormal scores and the fault types simplifies the diagnosis flow of operation and maintenance personnel. By clearly distinguishing false oil level, oil leakage and sensor faults, directional alarm information can be generated to guide maintenance personnel to check high-probability fault points preferentially. For example, false oil level alarms may directly prompt inspection of the float mechanism or transmission, while sensor fault alarms preferably recommend verification of the sensor circuit or communication link. The directional guide reduces the time loss of blind investigation and reduces unnecessary equipment shutdown caused by misjudgment.
In some embodiments of the present application, when the current operation state of the oil level gauge assembly is abnormal, further comprising:
When the fault signature analysis determines a false oil level fault, but the oil level value is abrupt, it is preferentially determined as a sensor fault.
When the fault characteristic analysis judges that the false oil level is faulty, but the effective value of the load current is suddenly increased and the vibration intensity of the oil storage cabinet is synchronously changed, the fault characteristic analysis preferentially judges that the oil storage cabinet is in vibration interference.
In some embodiments of the present application, when determining an abnormal region based on an abnormal state and transmitting corresponding pre-warning information based on each abnormal region, the method includes:
And when the early warning unit judges that the oil level is false, generating first-level early warning information.
And when the early warning unit judges that oil leaks, generating secondary early warning information.
And when the early warning unit judges that the sensor fails, three-level early warning information is generated.
It can be appreciated that by introducing a dynamic priority determination mechanism, similar fault scenarios can be distinguished more accurately, and diagnostic deviations caused by single-feature erroneous determination are avoided. For example, when a false oil level fault and an abrupt oil level fault occur simultaneously, it is preferentially determined that the sensor fault combines the transient characteristic of the abrupt signal and the sustained characteristic of the mechanical jam, thereby eliminating the interference of the mechanical fault. The multi-parameter cross-validation mechanism enhances the reliability of fault location and reduces the dependence on a single data source, thereby reducing the risk of misjudgment caused by local abnormality. In the scene of synchronous change of load current sudden increase and vibration, mechanical vibration interference rather than false oil level is preferentially judged, and the resolution capability of composite type abnormality is improved. By correlating the cooperative change of the electrical parameter (load current) and the mechanical parameter (vibration intensity), the indirect influence of the external environment (such as overload of a transformer) on the oil level data can be identified, and the oil level fluctuation error caused by the mechanical vibration is prevented from being attributed to the floating ball jam or the sensor failure. Robustness in complex industrial environments is improved by multi-modal data analysis. Through a hierarchical early warning mechanism (from one level to three levels), warning information can be pushed in a differentiated mode according to the fault type and the emergency degree. For example, a first level early warning (false oil level) prompts mechanical part inspection, a second level early warning (oil leakage) triggers emergency shutdown protection, and a third level early warning (sensor failure) suggests circuit overhaul. And when the early warning unit judges that vibration is interfered, comparing the current data again, judging again based on the comparison result of the new state model, if judging that vibration is interfered, not alarming, if judging that other anomalies are detected, alarming based on other anomaly information, and the grading strategy helps operation and maintenance personnel to quickly identify the priority, shortens the response time of key faults (such as oil leakage) and simultaneously avoids excessive reaction to low-risk events, so that the manpower resource allocation and maintenance cost is optimized. The priority decision rule suppresses the limitations of the conventional static threshold method. For example, in the oil level abrupt change scene, the possibility of transient faults of the sensor is preferentially eliminated through dynamic switching of the judgment logic, instead of being directly bound into mechanical anomalies, the excessive dependence on a preset threshold value is reduced, the complex scene of abrupt interference or transient signal anomalies can be adapted, and false alarms caused by accidental events are reduced.
In some embodiments of the present application, when the pre-warning unit determines that the current operating state is abnormal, the abnormality information is stored in the history database and the fault type is noted, and the state model is trained at regular time intervals and the threshold is updated.
It can be appreciated that by storing anomaly information in a historical database and labeling fault types, multidimensional operational data and fault cases can be continuously accumulated. So that the historical data is no longer an isolated event record but is converted into a traceable, analyzable knowledge base. By marking the fault type, the data has definite semantic information, a structural basis is provided for subsequent root cause analysis and pattern mining, the multiplexing value of fault cases is improved, and the analysis fault risk caused by experience dependence or personnel flow is reduced. The state model is trained at regular intervals, ensuring that the model can be dynamically updated following changes in device state or the occurrence of new failure modes. By integrating the latest abnormal data, the model continuously learns new characteristic distribution and fault rules, and avoids performance degradation caused by equipment aging, environment transition or working condition adjustment. The generalization capability of the model to new scenes is improved, and the misjudgment probability of the traditional static model due to data distribution deviation is reduced. Meanwhile, the incremental training strategy reduces the overall dependence on historical data, and optimizes the utilization efficiency of computing resources. Based on the updated model and the historical abnormal data, the judgment threshold value of the reconstruction error and the prediction deviation can be dynamically adjusted, and the problems of insufficient sensitivity or overstress response possibly occurring in long-term operation of the traditional fixed threshold value are overcome. For example, after the device enters a stable aging phase, the threshold may be moderately relaxed to avoid excessive alarms. While in a high-precision monitoring scenario, the threshold may be tightened to capture early signs of abnormalities. This flexibility improves the adaptability to different lifecycle stages or external environmental changes, reduces the workload of manual frequent calibration, and updates the threshold according to new data: , wherein, Is a forgetting factor (typically 0.9),The threshold value calculated for the most recent data,Is the old threshold value of the value,Is an updated threshold.
In some embodiments of the application, the system further comprises a remote monitoring unit electrically connected with the early warning unit, wherein the remote monitoring unit is configured to monitor the operation state of the early warning unit and send the operation state monitoring information to the Internet and cloud data platform.
It can be understood that the oil level monitoring state is tracked in real time and synchronized in cloud by connecting the remote monitoring unit with the early warning unit. The operation and maintenance personnel can acquire the operation state of the equipment without being limited by geography, and timely grasp the occurrence of abnormal conditions. The real-time transmission of the monitoring information ensures timeliness of fault response, shortens a time window for processing intervention from abnormality occurrence, and reduces the risk of fault expansion caused by information delay. Meanwhile, the access of the cloud platform provides convenience for multi-terminal access, supports multi-channel monitoring of a mobile terminal, a PC terminal and the like, and enhances the flexibility of emergency treatment. And due to the introduction of the cloud data platform, the scattered monitoring data can be stored and managed in a centralized way. The space limitation of the traditional local storage is broken through by the centralized processing mode, and a foundation is provided for long-term storage and quick retrieval of massive historical data. Through the data aggregation of the cloud, cross-equipment and cross-region transverse comparison analysis can be realized, and potential regional risks or commonality fault modes are identified.
In summary, the invention has the advantages that the mechanical strength of the whole structure is enhanced through the rigid connection of the fixed flange and the limiting rod, the impact of external vibration or pressure on key components is dispersed, deformation or fatigue damage caused by long-term stress is reduced, the sliding arrangement of the floater along the limiting rod replaces the free floating mode of the traditional floater, the motion track of the floater is restrained through physical guidance, the problem of blocking caused by mechanical loosening or deflection is avoided, the stability of the motion of the floater is further improved through the bilateral support of the limiting rod, the linear response of the floater can be still maintained when the oil density changes or the temperature fluctuates, thereby improving the reliability of long-term operation, in addition, the cooperation of the rotating rod and the limiting rod improves the force transmission path, the abrasion risk caused by local stress concentration is reduced, the direct linkage of the angle sensor and the rotating rod is eliminated, the gap error in the traditional indirect transmission (such as a gear and a chain), the change of an oil level can be captured in real time, the vertical displacement of the floater is converted into a rotation angle signal through the linear motion of the threaded rotating rod, the nonlinear error caused by gear meshing or the swinging is avoided, the sensitivity of the oil level detection is improved, the oil level detection is shortened, the time is shortened, the oil level control module is controlled to change when the oil level is in response to the dynamic vibration, the vibration is fast, the vibration is increased, the vibration is caused by the vibration, the vibration is reduced, the vibration resistance is caused by the vibration of the floater is generated, the vibration is reduced, the vibration resistance is caused by the vibration, and the vibration is caused by the vibration fluctuation, and the vibration is directly fluctuation, and the vibration is generated, the control module is electrically connected with the angle sensor, so that the oil level data can be acquired in real time and converted digitally, and a foundation is provided for remote monitoring and automatic analysis. Through integrated control module, can discern the trend characteristic that the oil level changes, early warning potential trouble (such as seepage, jam) in advance reduces the reliance of manual work inspection.
It will be appreciated by those skilled in the art that embodiments of the application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flowchart and/or block of the flowchart illustrations and/or block diagrams, and combinations of flowcharts and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the specific embodiments of the present invention without departing from the spirit and scope of the present invention, and any modifications and equivalents are intended to be included in the scope of the claims of the present invention.
Claims (7)
1. A pointer type oil level gauge for monitoring the oil level of a transformer oil storage tank, comprising:
the oil level gauge comprises an oil level gauge assembly and a control module, wherein the control module is electrically connected with the oil level gauge assembly and is used for controlling the oil level gauge assembly, and the oil level gauge assembly comprises:
The dial plate, mounting flange, gag lever post, angle sensor, stopper, rotary rod and float, mounting flange's upper end fixedly connected with the dial plate, the electricity is connected with in the dial plate angle sensor, mounting flange's lower extreme fixedly connected with the gag lever post, the gag lever post is kept away from mounting flange's one end fixedly connected with the stopper, the gag lever post is provided with two, two be provided with between the gag lever post the rotary rod, just the both ends of rotary rod are rotated respectively and are connected the dial plate with the stopper, the surface axial of rotary rod is provided with the screw thread, the float cover is established on the rotary rod, just the both sides sliding connection of float two the gag lever post;
The control module includes:
The acquisition unit is configured to acquire sensor data, store the sensor data at fixed time intervals and denoise, and also configured to align time stamps of the sensor data and process missing values by adopting KNN interpolation;
a judging unit configured to extract the sensor data and input the sensor data into a pre-trained state model for comparison, the judging unit being further configured to determine a current operating state of the oil level gauge assembly based on a comparison result of the state model;
an early warning unit configured to determine abnormal areas based on the abnormal state and transmit corresponding early warning information based on the respective abnormal areas when the current operation state of the oil level gauge assembly is abnormal;
When the sensor data are input into a pre-trained state model for comparison, the method comprises the following steps:
Acquiring two groups of time sequences of the sensor data, wherein one time sequence comprises a time sequence waveform of an oil level value and a time sequence waveform of oil temperature data, and the other time sequence comprises a load current effective value, an external environment temperature and humidity and a vibration intensity of an oil storage cabinet;
In a bottom layer feature learning stage, splicing two groups of time sequence waveforms of the time sequence into an oil level-oil temperature combined feature and an auxiliary feature, and forming an enhanced time sequence feature based on the oil level-oil temperature combined feature and the auxiliary feature;
in a high-level feature learning stage, extracting high-level nonlinear features layer by layer based on the enhanced time sequence features by using a dense network with a two-layer structure to form the state model;
Inputting the sensor data into the state model, carrying out waveform reconstruction and obtaining an oil level predicted value;
Determining a reconstruction error value and a prediction bias value of the state model based on the oil level prediction value;
when determining the reconstruction error value and the prediction error value of the state model based on the oil level prediction value, the method comprises the following steps:
Determining the reconstruction error value based on a time sequence waveform of the oil level value, and performing temperature coefficient compensation on the reconstruction error value when the external environment temperature fluctuates;
determining a reconstruction error threshold based on the historically normal oil level values;
Acquiring actual data of the oil level value, and determining the predicted deviation value based on the oil level predicted value;
and arranging the predicted deviation values in an ascending order, and taking 95% quantiles as a predicted deviation threshold.
2. The pointer-type oil level gauge for monitoring the oil level of a transformer tank according to claim 1, wherein when determining the current operation state of the oil level gauge assembly based on the comparison result of the state model, comprising:
determining an anomaly score based on the prediction bias threshold and the reconstruction error threshold:
;
Wherein, the For the purpose of scoring the anomaly,AndIs a weight coefficient, and+=1,The value of the error is reconstructed and,The threshold value for the reconstruction error is set,In order to predict the value of the deviation,Is a threshold for predicting the deviation value.
3. The pointer-type oil level gauge for monitoring the oil level of a transformer tank according to claim 2, characterized by comprising, when the current operation state of the oil level gauge assembly is abnormal:
When the abnormality score is 1 or less, determining that the oil level gauge assembly is normal;
When the anomaly score is greater than 1, determining that the oil level gauge assembly is anomalous and triggering fault signature analysis;
The fault characteristic analysis is divided into false oil level, oil leakage and sensor faults;
When (when) When the reconstruction error value is larger than 0.7 and is larger than twice the reconstruction error threshold value and the prediction deviation value is smaller than the prediction deviation threshold value, the false oil level fault is judged;
When (when) When the reconstruction error value is larger than 0.7 and smaller than twice the reconstruction error threshold value and the prediction deviation value is larger than twice the prediction deviation threshold value, judging that the sensor is faulty;
When (when) And when the reconstruction error value is larger than 0.7 and smaller than twice the reconstruction error threshold value and the prediction deviation value is larger than twice the prediction deviation threshold value, judging that the oil leakage fault exists.
4. A pointer oil level gauge for transformer tank oil level monitoring as set forth in claim 3, further comprising, when the current operating state of said oil level gauge assembly is abnormal:
When the fault characteristic analysis judges that the oil level value suddenly changes, the fault characteristic analysis judges that the oil level value is false, and the fault characteristic analysis preferentially judges that the oil level value is sensor fault;
and when the fault characteristic analysis judges that the oil level is false, but the effective value of the load current is suddenly increased and the vibration intensity of the oil storage cabinet is synchronously changed, preferentially judging that the oil storage cabinet is in vibration interference.
5. The pointer type oil level gauge for monitoring oil level of a transformer tank according to claim 4, wherein when determining abnormal areas based on abnormal conditions and transmitting corresponding pre-warning information based on each abnormal area, comprising:
When the early warning unit judges the false oil level, generating first-level early warning information;
when the early warning unit judges that oil leaks, generating secondary early warning information;
and when the early warning unit judges that the sensor fails, three levels of early warning information are generated.
6. The pointer oil level gauge for monitoring oil level of transformer tank according to claim 5, wherein when the early warning unit determines that the current operation state is abnormal, the abnormality information is stored in a history database and the type of fault is noted, the state model is trained at regular time intervals, and the threshold value is updated.
7. The pointer oil level gauge for monitoring oil level of a transformer tank of claim 6, further comprising a remote monitoring unit electrically connected to the pre-warning unit, the remote monitoring unit configured to monitor an operational status of the pre-warning unit and send operational status monitoring information to an internet and cloud data platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510602188.5A CN120121135B (en) | 2025-05-12 | 2025-05-12 | A pointer type oil level gauge for monitoring the oil level of a transformer oil storage cabinet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510602188.5A CN120121135B (en) | 2025-05-12 | 2025-05-12 | A pointer type oil level gauge for monitoring the oil level of a transformer oil storage cabinet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120121135A CN120121135A (en) | 2025-06-10 |
| CN120121135B true CN120121135B (en) | 2025-08-26 |
Family
ID=95923500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510602188.5A Active CN120121135B (en) | 2025-05-12 | 2025-05-12 | A pointer type oil level gauge for monitoring the oil level of a transformer oil storage cabinet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120121135B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115752652A (en) * | 2022-12-21 | 2023-03-07 | 深圳供电局有限公司 | A measuring device and measuring system for casing oil level |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206132187U (en) * | 2016-10-26 | 2017-04-26 | 南京大全变压器有限公司 | Transformer stores up oil level gaugember for oil tank |
| CN108444566A (en) * | 2018-03-14 | 2018-08-24 | 国网天津市电力公司电力科学研究院 | Oil level gauge for transformer based on pressure sensing and temperature adjustmemt |
| CN114136367B (en) * | 2021-11-06 | 2025-07-04 | 国网山西省电力公司电力科学研究院 | A method for detecting defects in transformer oil storage cabinets based on edge computing monitoring device |
| CN115238754B (en) * | 2022-09-21 | 2023-02-14 | 国网江西省电力有限公司电力科学研究院 | Power transformer short-term operation temperature prediction method based on multivariate perception |
| CN117191157A (en) * | 2023-09-05 | 2023-12-08 | 国网山东省电力公司烟台供电公司 | A real-time monitoring device for oil temperature and oil level of oil-immersed transformer based on Hall effect and its monitoring method |
| CN117789422A (en) * | 2024-02-26 | 2024-03-29 | 江西依爱弘泰消防安全技术有限公司 | Combustible gas alarm control system and method |
| CN118655395B (en) * | 2024-07-15 | 2025-09-12 | 国网北京市电力公司 | Fault detection method, device and electronic equipment for oil-immersed transformer |
| CN119852994A (en) * | 2024-12-18 | 2025-04-18 | 连云港智源电力设计有限公司 | Dynamic voltage control method considering voltage risk assessment and network reconstruction |
| CN119961828A (en) * | 2025-01-09 | 2025-05-09 | 中国矿业大学 | A method for predicting and detecting abnormality of transformer electrical-thermal-vibration signals |
-
2025
- 2025-05-12 CN CN202510602188.5A patent/CN120121135B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115752652A (en) * | 2022-12-21 | 2023-03-07 | 深圳供电局有限公司 | A measuring device and measuring system for casing oil level |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120121135A (en) | 2025-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102604708B1 (en) | Switchboard diagnosis system based on artificial intelligence and switchboard diagnosis method based on artificial intelligence | |
| CN109524139B (en) | Real-time equipment performance monitoring method based on equipment working condition change | |
| US7967066B2 (en) | Method and apparatus for Christmas tree condition monitoring | |
| KR102470112B1 (en) | Intelligent condition monitoring method and system for nuclear power plants | |
| Mharakurwa | In‐service power transformer life time prospects: review and prospects | |
| CN118410279A (en) | Deep learning-based turbine unit fault processing method and system | |
| CN119851449A (en) | Intelligent early warning car washer | |
| CN118965114A (en) | Pumped storage unit fault detection method and detection device | |
| CN119063779A (en) | A method and system for detecting the transport status of a floating body of a floating photovoltaic power station | |
| CN118967106A (en) | A special release motor fault detection method | |
| CN119643132A (en) | Data detection method and system for valve faults | |
| CN120121135B (en) | A pointer type oil level gauge for monitoring the oil level of a transformer oil storage cabinet | |
| CN119515112B (en) | A real-time monitoring and early warning method for leakage status of long-line public facilities | |
| CN119494225A (en) | A data processing method and system for digital twin oil and gas pipeline | |
| CN118710251A (en) | Bridge erection machine maintenance system based on cloud data | |
| CN120763760B (en) | Real-time detection method and system for surface defects of high-voltage tubular busbars | |
| CN121026429A (en) | Water turbine main shaft seal monitoring method, device, equipment, storage medium and product | |
| CN120385812B (en) | A comprehensive monitoring method, system and storage medium for transformer oil quality | |
| CN119271968B (en) | Component reliability assessment method and system based on big data analysis | |
| CN120685985A (en) | A method for detecting electronic component parameters in an array channel under marine salt spray environment | |
| CN121027626A (en) | A method and system for health monitoring of electrical control boxes | |
| CN119199323A (en) | A flexible anode fault detection method and system | |
| CN120507601A (en) | Intelligent power grid fault diagnosis method, system, equipment and medium based on big data | |
| CN120275783A (en) | Insulation state evaluation method and system of voltage transformer on-line monitoring device | |
| CN121163652A (en) | Ship host fault early warning method and system based on LSTM dynamic threshold model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |