CN119321834B - A temperature monitoring method and related device for power transformer - Google Patents
A temperature monitoring method and related device for power transformer Download PDFInfo
- Publication number
- CN119321834B CN119321834B CN202411881471.8A CN202411881471A CN119321834B CN 119321834 B CN119321834 B CN 119321834B CN 202411881471 A CN202411881471 A CN 202411881471A CN 119321834 B CN119321834 B CN 119321834B
- Authority
- CN
- China
- Prior art keywords
- temperature
- power transformer
- feature
- module
- fault diagnosis
- 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
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Measuring Temperature Or Quantity Of Heat (AREA)
Abstract
The application discloses a temperature monitoring method and a related device of a power transformer, which relate to the field of non-electric quantity protection of transformers and are arranged in the power transformer, the intelligent temperature measuring bolts at the positions of all heat source points, the temperature difference of which reaches a preset temperature difference threshold value with the external environment, collect temperature data at all positions on the power transformer, and then input the collected temperature data into a temperature characteristic fault diagnosis model for processing, so that a temperature characteristic fault diagnosis result is obtained. The intelligent temperature measuring bolt can be arranged at any position meeting the installation conditions in the power transformer, namely, the temperature data of each heat source point of the power transformer can be comprehensively acquired, the internal temperature of the power transformer can be naturally acquired, and then the temperature data is processed by adopting a temperature characteristic fault diagnosis model comprising a multi-scale convolution module, a densely stacked network module, a residual module and a compression and excitation attention mechanism module, so that an accurate temperature characteristic fault diagnosis result is obtained.
Description
Technical Field
The application relates to the technical field of non-electric quantity protection of transformers, in particular to a temperature monitoring method and a related device of a power transformer.
Background
A power transformer is a stationary electrical device that is used mainly to transform an ac voltage (current) of a certain value into another voltage (current) of the same frequency or of different values.
Power transformers are vital devices in power systems, and their stable operation is critical to ensure reliable delivery, flexible distribution and safe use of electrical energy. Among the numerous parameters that a power transformer needs to detect, temperature is one of the core indicators that monitor the state of the power transformer.
In the prior art, a traditional temperature sensor is adopted to collect temperature data of a power transformer, the collected temperature data is transmitted to a monitoring station in real time, and further, by means of a wireless sensor network and a gateway, the real-time monitoring of the running state of the power transformer is realized. The real-time monitoring of the running state of the power transformer provides a key reference for the safety and stability of the power system.
The traditional temperature sensor is an infrared camera device, and particularly adopts an infrared camera to detect the temperature of the power transformer, but the monitoring means can not monitor the internal temperature of the power transformer.
Disclosure of Invention
In view of the above problems, the present application provides a method and a related device for monitoring the temperature of a power transformer, so as to achieve the purpose of comprehensively monitoring the temperature of the power transformer. The specific scheme is as follows:
The first aspect of the application provides a temperature monitoring method of a power transformer, comprising the following steps:
each temperature measuring node is an intelligent temperature measuring bolt which is arranged in the power transformer and has a temperature difference with the external environment reaching a heat source point position of a preset temperature difference threshold;
The temperature characteristic fault diagnosis model is configured to process the temperature data in sequence according to the sequence of the multi-scale convolution module, the densely stacked network module, the residual module and the compression and excitation attention mechanism module, and then output the temperature characteristic fault diagnosis result.
In one possible implementation, the design process of the wireless link includes:
Determining a temperature measuring node pair required to be subjected to time synchronization by adopting a bidirectional information exchange model;
time synchronization between temperature measuring node pairs is achieved through a receiver-receiver synchronization model.
In one possible implementation, the operating process of the temperature characteristic fault diagnosis model includes:
The multi-scale convolution module adopts filters with different scales to carry out convolution fusion of preset times on the temperature data to obtain feature vectors with different scales;
The method comprises the steps of inputting feature vectors under different scales into a dense stacking network module, wherein the dense stacking network module performs feature fusion on the feature vectors under different scales to obtain fusion features;
The residual module processes the fusion characteristics through a jump connection processing mode to obtain deep characteristic representations suitable for being transmitted in a deep network;
The deep feature representation is input into a compression and excitation attention mechanism module, and the compression and excitation attention mechanism module sequentially inputs the deep feature representation into a global average pooling layer and a full connection layer, models to generate a feature channel and then adjusts the weight of the feature channel to obtain a temperature fault feature;
And comparing the temperature fault characteristics with each sub-fault characteristic in the fault characteristic set in the temperature fault characteristic diagnosis model to obtain a fault diagnosis result of the temperature fault characteristics.
In one possible implementation, the compressing and exciting attention mechanism module inputs deep feature representations into the global averaging pooling layer and the full connection layer in turn, models to generate feature channels, and adjusts weights of the feature channels to obtain temperature fault features, including:
The compression and excitation attention mechanism module inputs the deep feature representation into the global average pooling layer, and adopts compression operation to process the deep feature representation to obtain a first processing result;
inputting the first processing result into the full-connection layer, and processing the first processing result by adopting excitation operation to obtain a second processing result;
and processing the second processing result by adopting scaling operation to obtain the temperature fault characteristic.
In one possible implementation, the method is applied to a data processing end, and a wireless channel with consistent frequency band is adopted between each temperature measuring node on the wireless link and the data processing end.
In one possible implementation, the intelligent temperature measuring bolt comprises a temperature sensor, a thermoelectric generator and a radiator, wherein the temperature sensor is arranged on a temperature sensing surface inside the intelligent temperature measuring bolt, the thermoelectric generator is arranged inside the intelligent temperature measuring bolt, and the radiator is arranged on the top of the intelligent temperature measuring bolt.
A second aspect of the present application provides a temperature monitoring device for a power transformer, comprising:
an acquisition unit and a processing unit, wherein:
The system comprises an acquisition unit, a wireless link, a wireless sensor unit and a wireless sensor unit, wherein the acquisition unit is used for at least acquiring temperature data of a power transformer through each temperature measuring node on the wireless link, and each temperature measuring node is an intelligent temperature measuring bolt arranged in the power transformer and at a heat source point position with the temperature difference reaching a preset temperature difference threshold value with the external environment;
The temperature characteristic fault diagnosis module is configured to process the temperature data in sequence according to the multi-scale convolution module, the densely stacked network module, the residual module and the compression and excitation attention mechanism module, and then output the temperature characteristic fault diagnosis result.
A third aspect of the application provides a computer program product comprising computer readable instructions which, when run on an electronic device, cause the electronic device to implement a method of temperature monitoring of any of the power transformers as hereinbefore described.
A fourth aspect of the application provides a temperature monitoring device for a power transformer comprising at least one processor and a memory coupled to the processor, wherein:
the memory is used for storing a computer program;
The processor is configured to execute a computer program to enable the temperature monitoring device of the power transformer to implement any one of the methods of monitoring the temperature of the power transformer as described above.
A fifth aspect of the application provides a computer storage medium carrying one or more computer programs which, when executed by an electronic device, enable the electronic device to implement a method of temperature monitoring of any one of the power transformers as hereinbefore described.
By means of the technical scheme, the temperature monitoring method and the temperature monitoring device for the power transformer are characterized in that the intelligent temperature measuring bolts arranged in the power transformer and at the positions of all heat source points with the temperature difference reaching the preset temperature difference threshold value are used for collecting temperature data of all positions on the power transformer, and then the collected temperature data are input into a temperature characteristic fault diagnosis model for processing, so that a temperature characteristic fault diagnosis result is obtained. The intelligent temperature measuring bolt can be arranged at any position meeting the installation conditions in the power transformer, namely, the temperature data of each heat source point of the power transformer can be comprehensively acquired, the internal temperature of the power transformer can be naturally acquired, and then the temperature data are processed by adopting a temperature characteristic fault diagnosis model comprising a multi-scale convolution module, a densely stacked network module, a residual module and a compression and excitation attention mechanism module, so that an accurate temperature characteristic fault diagnosis result is obtained.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
Fig. 1 is a schematic flow chart of a temperature monitoring method of a power transformer according to the present application;
FIG. 2 is an exemplary diagram of ITMB-1000 models of intelligent temperature measuring bolts provided by the application;
FIG. 3 is an exemplary graph of a diagnostic accuracy curve and an exemplary graph of a loss of a temperature signature fault diagnosis model provided by the present application;
FIG. 4 is a diagram showing an example of a connection of a method for monitoring a temperature of a power transformer according to the present application;
Fig. 5 is a schematic structural diagram of a temperature monitoring device of a power transformer according to the present application;
Fig. 6 is a schematic structural diagram of a temperature monitoring device of a power transformer according to the present application.
Detailed Description
Embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application. The terminology used in the description of the embodiments of the application herein is for the purpose of describing particular embodiments of the application only and is not intended to be limiting of the application.
Embodiments of the present application are described below with reference to the accompanying drawings. As one of ordinary skill in the art can know, with the development of technology and the appearance of new scenes, the technical scheme provided by the embodiment of the application is also applicable to similar technical problems.
The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely illustrative of the manner in which embodiments of the application have been described in connection with the description of the objects having the same attributes. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Temperature is one of the core indicators of monitoring power transformers. The existing temperature monitoring technology of the power transformer mainly depends on infrared camera equipment, and utilizes an infrared thermal imaging technology to monitor the running state of the power transformer in real time and discover potential overheating problems in time, so that faults are prevented.
However, the temperature monitoring technology of such a power transformer in the known technology has the following problems:
The infrared temperature measuring technology is easy to be influenced by external environments, such as sunlight, radiation of surrounding objects and the like, so that temperature measuring data are inaccurate, the infrared camera equipment needs to be calibrated and maintained regularly to ensure measuring precision and stability, but because the equipment is complex and precise, maintenance work often needs professional staff, operation and maintenance cost is increased, the infrared camera equipment depends on an external power supply to supply power, and the application range is limited.
In order to solve the above problems, the present application provides a temperature monitoring method and related device for a power transformer.
Optionally, referring to fig. 1, a flow chart of a temperature monitoring method of a power transformer is provided in the present application.
As shown in fig. 1, the temperature monitoring method of the power transformer comprises the following steps:
And 101, acquiring temperature data of the power transformer through all temperature measuring nodes on a wireless link, wherein all temperature measuring nodes are intelligent temperature measuring bolts which are arranged in the power transformer and are at the positions of heat source points with the temperature difference reaching a preset temperature difference threshold value with the external environment.
The temperature acquisition component of the power transformer provided by the application is an intelligent temperature measurement bolt, and particularly the intelligent temperature measurement bolt is arranged at a heating part (also called a heat source) of the power transformer which can not be wired and can be fastened by the bolt. The intelligent temperature measuring bolt comprises, but is not limited to, an intelligent temperature measuring bolt body, a temperature sensor, a thermoelectric generator and a radiator.
The temperature sensor is mainly used for collecting temperature data of the electrical connection point and is generally arranged on the temperature sensing surface inside the intelligent temperature measuring bolt.
The radiator is mainly used for directly conducting heat with the thermoelectric generator to help radiating, and is generally arranged at the top of the intelligent temperature measuring bolt.
Thermoelectric generators are used primarily to convert thermal energy into electrical energy, powering temperature sensors and heat sinks, as well as other components. Specifically, the thermoelectric generator converts the temperature difference between the heating part of the power transformer and the intelligent temperature measuring bolt radiator into electric energy. It is understood that the thermoelectric generator can perform the thermoelectric effect only when the temperature difference between the heating place of the power transformer and the radiator reaches a preset threshold, wherein the temperature of the radiator corresponds to the ambient temperature. For example, the preset threshold of the temperature difference may be 5K, that is, when the temperature difference between the heating place of the power transformer and the environment is greater than 5K, the thermoelectric generator may convert thermal energy into electrical energy to power other components. The thermoelectric generator consumes very little heat energy for performing the thermoelectric effect, and the heat energy of the power transformer is in a state of being constantly replenished, so that the heat energy consumed by the thermoelectric generator does not affect the acquisition accuracy of the temperature sensor.
It should be noted that the type of the intelligent temperature measuring screw in the application can be ITMB-1000, the performance of the intelligent temperature measuring screw in the model is excellent, and if an intelligent temperature measuring bolt or other intelligent temperature measuring components with more excellent performance appear in the future, the intelligent temperature measuring screw can be replaced.
For the intelligent temperature measuring bolt with the model number of ITMB-1000, the intelligent temperature measuring bolt mainly comprises a bolt body and a temperature measuring device. The bolt body mainly comprises a screw rod and a screw cap for fastening electric joints, the temperature measuring device mainly comprises a PCB circuit board, a radiator and a thermoelectric generator, the PCB (Printed Circuit Board ) board is provided with a temperature measuring sensor and a transmitting antenna for monitoring temperature in real time and transmitting data, the thermoelectric generator is provided with a cold end and a hot end, the temperature difference of the electric joints between the radiator ends is utilized to convert the electric energy into electric energy for supplying power for the PCB, and the radiator is positioned on one side of the cold end of the thermoelectric generator and is in direct heat conduction with the cold end to help heat dissipation. The temperature sensor of the intelligent temperature measuring bolt adopts IP66 protection grade design, can work in the temperature environment of-20 ℃ to 85 ℃, and has the service life of 20 years.
Exemplary, referring to FIG. 2, the present application provides an exemplary diagram of ITMB-1000 model intelligent thermometric bolts.
As shown in FIG. 2, the surface of the intelligent temperature measuring bolt is visible and provided with a heat input surface, a radiator, an antenna and an indicator lamp. The intelligent temperature measuring bolt comprises a heat input surface, a radiator, an antenna and an indicator lamp, wherein the heat input surface is a temperature sensing surface of a temperature sensor in the intelligent temperature measuring bolt, the radiator is used for helping radiating, the antenna is an emitting antenna arranged in the intelligent temperature measuring bolt, the indicator lamp is used for displaying working states or warning information of the intelligent temperature measuring bolt, for example, whether the intelligent temperature measuring bolt is in a normal working state (whether data are normally collected or not), and in addition, when the temperature of a collected power transformer exceeds a preset safety threshold, the indicator lamp may flash or change color so as to remind operation and maintenance personnel to timely check and process potential problems.
The wireless link is formed by each intelligent temperature measuring bolt arranged at the heating part of the power transformer and the multifunctional data acquisition monitoring device positioned at the data processing end, the temperature measuring node in the wireless link is each intelligent temperature measuring bolt arranged in the power transformer, the frequency band of each wireless channel between each intelligent temperature measuring bolt and the multifunctional data acquisition monitoring device at the data processing end is consistent, for example, the frequency band of the wireless channel can be 433MHz, the frequency band of the wireless channel can be changed, but the frequency band of the wireless channel between each intelligent temperature measuring bolt on the wireless link and between each intelligent temperature measuring bolt and the multifunctional data acquisition monitoring device is consistent, and the selected channel can be used in the practical application environment.
The installation position of the intelligent temperature measuring bolt is selected from a heating position of the power transformer which can be fastened by the bolt, that is, a position which meets the above conditions can be selected for installing the intelligent temperature measuring bolt. Further, a finer mounting position is preferably selected at the heat generation portion of the screw-fastened power transformer where the temperature difference from the external environment reaches a preset threshold, where the preset threshold may be set to 10K.
The installation direction of the intelligent temperature measuring bolt is also important, and has important significance for radio frequency and data acquisition. Specifically, the intelligent temperature measuring bolt is arranged at a position of the bolt radiator, which is prevented from being affected by intensive shearing or vibration mechanical stress, the radiator is kept at a certain distance from the heat source, the fins of the radiator face the heat source and are vertical to the ground, so that natural convection heat dissipation is used, the intelligent temperature measuring bolt is prevented from being arranged in the horizontal direction, the collected heat energy is greatly reduced if the intelligent temperature measuring bolt is arranged in the horizontal direction, the best installation position is the side face or the bottom face of a heat source point, and the data collection performance of the intelligent temperature measuring bolt can be greatly improved if forced convection is generated by an electric fan or a ventilating fan.
In addition, before the intelligent temperature measuring bolt is installed, the installation surface of the power transformer can be cleaned, specifically acetone or absolute ethyl alcohol can be adopted for cleaning, impurities such as rust, oil stains and the like are removed, and for better thermal performance, heat conduction silicone grease can be filled between the heat source surface of the power transformer and a temperature sensor of the intelligent temperature measuring bolt.
In addition, the temperature sensor of the intelligent temperature measuring bolt can also collect the emission energy of the antenna and the wireless link signal strength of the intelligent temperature measuring bolt to which the temperature sensor belongs. The transmitted energy, the wireless link signal intensity and the acquired temperature data are transmitted to the multifunctional data acquisition monitoring device. The multifunctional data acquisition monitoring device adopts the emission energy to evaluate whether the emission energy of the current antenna of the intelligent temperature measuring bolt is stable or not, and adopts the wireless link signal intensity to evaluate the signal quality of the intelligent temperature measuring bolt.
In conclusion, the intelligent temperature measuring bolt adopted in the temperature monitoring method of the power transformer can realize independent power supply through the self-generating function, can also transmit temperature data through a wireless transmission technology, and is suitable for temperature monitoring in the power transformer.
Optionally, the data processing end obtains temperature data of the power transformer from each intelligent temperature measuring bolt installed in the power transformer through a wireless channel of a preselected frequency band.
For the wireless link mentioned above, the design needs to be completed before the power transformer temperature is monitored, and the design process of the wireless link includes the following steps:
step one, a bidirectional information exchange model is adopted to determine a temperature measuring node pair required to be subjected to time synchronization.
The design of the wireless link mainly needs to complete the time synchronization of each intelligent temperature measuring bolt installed in the power transformer, and the application mainly adopts a bidirectional information exchange model and a receiver-receiver synchronization model to complete the time synchronization process of each intelligent bolt.
In the application, a bidirectional information exchange model is adopted to determine a temperature measuring node pair needing bidirectional information exchange, and in particular, the bidirectional information exchange model is adopted to determine a temperature measuring node pair carrying out time synchronization.
Alternatively, a two-way information exchange model is adopted to perform time synchronization on the temperature measuring node pair.
And step two, realizing time synchronization between temperature measuring node pairs through a receiver-receiver synchronization model.
Then, a receiver-receiver synchronization model is used to complete time synchronization between the temperature measuring node pairs.
It should be noted that, the time synchronization between the intelligent temperature measuring bolts on the wireless link is completed through the two steps, so as to ensure the time consistency of data acquisition between the intelligent temperature measuring bolts and the accuracy of subsequent data transmission. In addition, in the time synchronization process, the intelligent temperature measuring bolts are communicated by adopting wireless channels, the frequency bands of the wireless channels are consistent with the frequency bands of the wireless channels adopted by the follow-up intelligent temperature measuring bolts and the data processing end for data transmission, and it can be understood that the intelligent temperature measuring bolts have the wireless communication function.
Taking a group of adjacent temperature measuring nodes A and B as an example, taking the temperature measuring node B as a reference node, the temperature measuring node A needs to be synchronous with the temperature measuring node B.
Assuming that the K-th round of information exchange is performed, the temperature measuring node a sends a synchronization message to the temperature measuring node B at time T 1,k, the temperature measuring node B records time T 2,k when the synchronization message is received, replies a message containing a time stamp T 3,k to the temperature measuring node a, and finally records time T 4,k when the reply message from the temperature measuring node B is received. And finally realizing message synchronization through the exchange of the time messages of N rounds.
In this process, the time synchronization calculation formula in the receiver-receiver synchronization model can be expressed as:
;
;
Wherein f is the time skew of the temperature measuring node A relative to the temperature measuring node B, For the time offset of thermometric node a relative to thermometric node B,For a fixed time delay, X k is the variable time delay from temperature node A to temperature node B, and Y k is the variable time delay from temperature node B to temperature node A.
Correspondingly, substituting all collected timestamp information into a time synchronization formula in a receiver-receiver synchronization model in a matrix form can obtain:
;
Wherein 1 2N is the number of synchronous rounds, X 1 is the initial position of the temperature measuring node A in the synchronous process, X N is the final position of the temperature measuring node A in the synchronous process, Y 1 is the initial coordinate of the temperature measuring node A in the synchronous process, Y N is the final coordinate of the temperature measuring node A in the synchronous process, T 1,1,T1,N,T4,1,T4,N is a time stamp indicating the time record of sending and receiving the synchronous message by the temperature measuring node A in the time message exchange process of the 1 st round to the N th round, and T 2,1,T2,N,T3,1,T3,N is a time stamp indicating the time record of receiving and sending the time message by the temperature measuring node B in a plurality of rounds.
Further, for the time synchronization formula in the receiver-receiver synchronization model between any two thermometric nodes A and B, the formula is:
;
;
Wherein, AndIndicating, in the kth round of message exchange, the reception time stamps of the thermometric node a and the thermometric node B,AndThe clock frequency multiplying power of the temperature measuring node A and the temperature measuring node B is represented, and T 1,k is the time when the time message is sent out from the temperature measuring node A in the k-th round of message exchange.AndIs the fixed transmission delay of the temperature measuring node A and the temperature measuring node B,AndRepresenting the variable time delays from thermometric node a to thermometric node B and from thermometric node B to thermometric node a in the kth round,AndIndicating the time offsets of thermometric node a and thermometric node B.
Substituting all the timestamp information collected above into the time synchronization formula in the above-mentioned receiver-receiver synchronization model in the form of a matrix, the method can obtain:
;
Wherein, T 1,1,T1,2,…,T1,N is the time stamp of the synchronous message sent by the temperature measuring node A in the process of message exchange of the Nth round, and is used for pairing with the receiving time stamp of the temperature measuring node B so as to analyze the time difference between the two time stamps; Is the relative clock frequency factor between the temperature measuring node A and the temperature measuring node B, and is used for adjusting the clock rate difference between the two temperature measuring nodes. The clock offset of the temperature measuring node A relative to the temperature measuring node B is used for representing the initial difference of the two temperature measuring nodes in relative time; representing a fixed transmission delay for each of 2N syncs; is a variable time delay representing the dynamic delay variation in the ith round of message exchange from thermometric node a to thermometric node B or between thermometric node B to thermometric node a.
It should be noted that if there is no relative clock skew between the two temperature measurement nodes, the clock is shiftedThe least squares estimate of (c) can be written as:
;
In summary, the wireless links to which each intelligent bolt belongs are designed based on a two-way information exchange model and a receiver-receiver synchronization model.
And 102, inputting the temperature data into a temperature characteristic fault diagnosis model for processing to obtain a temperature characteristic fault diagnosis result, wherein the temperature characteristic fault diagnosis model is configured to process the temperature data in sequence according to a multi-scale convolution module, a dense stacking network module, a residual module and a compression and excitation attention mechanism module, and then output the temperature characteristic fault diagnosis result.
The temperature characteristic fault diagnosis model is trained and used based on a convolutional neural network and is mainly used for diagnosing whether a power transformer has faults or not through temperature data acquired from each intelligent temperature measuring bolt. The model mainly comprises four modules, namely a multi-scale convolution module, a densely stacked network module, a residual module and a compression and Excitation attention mechanism module, wherein the compression and Excitation attention mechanism module can also be called as an SE (sequential-and-specification) attention mechanism module.
The multi-scale convolution module is mainly used for obtaining feature vectors under different scales after carrying out convolution on temperature data for preset times by adopting filters with different scales, and can improve the recognition capability of a convolution network on features with different sizes and complexity and improve the robustness of fault diagnosis.
The densely stacked network module receives the feature vectors under different scales output by the multi-scale convolution module, performs feature fusion processing on the feature vectors under different scales to obtain fusion features, and can connect the output of each layer with the input of a subsequent layer to realize efficient fusion of the features, thereby being beneficial to extracting finer features and improving early detection capability of faults.
The residual module receives the fusion characteristics output by the densely stacked network module, and processes the fusion characteristics through a jump connection processing mode to obtain deep characteristic representation suitable for being transmitted in a deep network, wherein the jump connection can solve the gradient message problem in the deep network, so that characteristic information can be effectively transmitted in the deep network, and the training effect and accuracy of the temperature characteristic fault diagnosis model can be improved.
The SE attention mechanism module receives the deep feature representation output by the residual module, the deep feature representation is sequentially input into the global averaging pooling layer and the full connection layer, the modeling is performed to generate a feature channel, the weight of the feature channel is adjusted to obtain a temperature fault feature, the weight of the generated feature channel is used for weighting the feature channel, the weight of important features is enhanced, irrelevant features are restrained, the feature expression capability of the temperature feature fault diagnosis model is improved, and the fault recognition accuracy of the temperature feature fault diagnosis model is further improved.
And finally, comparing the temperature fault characteristics output by the SE attention mechanism module with each sub-fault characteristic in the fault characteristic set generated in the training process in the temperature characteristic fault diagnosis model. Specifically, the fault feature set is formed by processing preset fault data in a convolutional neural network through preset fault data in the model training process, obtaining waveforms corresponding to different fault data, obtaining various waveforms corresponding to different fault features through multiple times of training, forming the fault feature set, judging the fault feature and each fault feature in the fault feature set after the temperature feature fault diagnosis model processes the temperature data to obtain the fault feature, comparing the fault feature with each fault feature in the fault feature set, and diagnosing the power transformer as a fault type indicated by the sub fault feature when the sub fault feature similar to or identical to the fault feature exists in the fault feature set.
In conclusion, the temperature characteristic fault diagnosis model integrates multi-scale characteristic fusion, residual error learning and attention mechanisms, can accurately and efficiently extract and diagnose fault characteristics when processing complex temperature signal data, and has higher robustness and accuracy.
Exemplary, referring to fig. 3, the temperature characteristic fault diagnosis model provided by the application is a diagnosis accuracy curve illustration and a loss illustration.
As can be seen from fig. 3, the temperature characteristic fault diagnosis model has reached 96% training accuracy and has tended to stabilize at the 20 th iteration.
The formula related to the training process of each module in the temperature characteristic fault diagnosis model is as follows:
And the multi-scale convolution module is used for carrying out convolution on the temperature data for multiple times by adopting filters with different scales to obtain feature vectors with different scales, then, the feature vectors with different scales are fused, the feature vectors with different fine granularity are further extracted and obtained, and the robustness of the convolution neural network can be improved by the arrangement of the multi-scale convolution module.
The calculation formula is as follows:
;
Wherein Y represents output data after one-dimensional multi-scale convolution fusion, X i=[X1, X2, X3, …, Xn represents feature vectors extracted under different scales, and Concat represents a feature fusion process.
And then, inputting feature vectors with different fine granularities into a densely stacked network module, fusing an input layer and an output layer after a first convolution layer by Concat layers, fusing an output layer after a first convolution layer and an output layer after a second convolution layer by Concat layers, and fusing temperature data by Concat layers after the first, second and third convolutions of the input layer. It should be noted that the densely stacked network modules are advantageous for mining fine features of temperature data and for finding early failures of the power transformer. The calculation formula of the module can be:
;
wherein C i is the output after the ith feature fusion, X is the temperature data, For the weights of the convolution, b i is the bias of the convolution.
Furthermore, the fusion characteristics output in the densely stacked network modules are input into a residual module, the residual module is usually composed of a plurality of residual blocks, when the input dimension and the output dimension of one residual block are the same, the jump connection structure is simple identical mapping, and when the input dimension and the output dimension of the residual block are different, a 1X 1 convolution channel is added at the jump connection position, so that the two dimensions are kept consistent.
The calculation formula of the residual module may be as follows:
;
where L is the total number of residual blocks, L represents the number of layers of the residual block, Representing the input of a layer i residual block,Representing the output of the residual block, F (·) representing the identity mapping function,Representing the bias or weight matrix of the first layer.
The deep characteristic representation suitable for being propagated in the deep network is obtained in the residual module, and then the deep characteristic representation output in the residual module is input into the SE attention mechanism module, and the module mainly comprises three working steps:
Firstly, inputting deep feature representation into a global average pooling layer, and adopting compression operation to process the deep feature representation to obtain a first processing result. The compression operation may also be referred to as a Squeeze operation, among other things.
The equation for the Squeeze operation can be as follows:
;
Wherein, For a particular class of predicted values,For a given one-dimensional input, C is the number of channels, L is the sequence length,For global average pooled output,Is a channelAnd positionIs a characteristic value of (a).
And then, inputting the first processing result into the full-connection layer, and processing the first processing result by adopting excitation operation to obtain a second processing result. Wherein the incentive operation may also be referred to as an accounting operation.
The calculation formula of the expression operation can be as follows:
;
Wherein s is the output of the full connection layer, The activation function representing the Sigmoid,Representing the activation function of the ReLU,Is the weight of the full connection layer,The weight of the full connection layer is that z is a reduction ratio.
And finally, processing a second processing result by adopting a scaling operation to obtain the temperature fault characteristics. Specifically, the calculated characteristic channel is multiplied by the original channel characteristic, thereby performing characteristic charge calibration. Wherein the scaling operation may also be referred to as Scale operation.
The calculation formula for this operation may be as follows:
;
Wherein, Is the characteristic value after the scaling and is used for the scaling,Is the weighting coefficient of channel c.
Finally, the result is recorded again.
In summary, according to the temperature monitoring method for the power transformer provided by the application, the intelligent temperature measuring bolts arranged in the power transformer and at the positions of all heat source points, the temperature difference of which reaches the preset temperature difference threshold value with the external environment, are used for collecting the temperature data of all positions on the power transformer, and then the collected temperature data are input into the temperature characteristic fault diagnosis model for processing, so that the temperature characteristic fault diagnosis result is obtained. The intelligent temperature measuring bolt can be arranged at any position meeting the installation conditions in the power transformer, namely, the temperature data of each heat source point of the power transformer can be comprehensively acquired, the internal temperature of the power transformer can be naturally acquired, and then the temperature data are processed by adopting a temperature characteristic fault diagnosis model comprising a multi-scale convolution module, a densely stacked network module, a residual module and an SE attention mechanism module, so that an accurate temperature characteristic fault diagnosis result is obtained.
The temperature monitoring method of the power transformer can monitor the temperature of the interior of the power transformer through the intelligent temperature measuring bolt, breaks the limitation of monitoring of the traditional infrared camera equipment, has good market applicability, can be widely applied to the connecting position of the closed bus of the circuit breaker, the connecting position of the closed bus of the sleeve, the pressure equalizing interior of the sleeve, the switch cabinet, the rectifier and other power equipment, and has wide application prospect.
Referring to fig. 4, an exemplary diagram of a method for monitoring a temperature of a power transformer is provided.
The intelligent temperature measuring bolt arranged on the power transformer is used for collecting temperature data, the collected temperature data is transmitted to the multifunctional data collecting and monitoring device through a wireless channel, fault diagnosis is carried out after the temperature data are analyzed and processed by the monitoring device, and the monitoring and diagnosing result is sent to the mobile phone APP end or the Web end for display.
The foregoing describes a temperature monitoring method for a power transformer according to an embodiment of the present application, and an apparatus for performing the temperature monitoring method for a power transformer will be described below.
Referring to fig. 5, a schematic structure diagram of a temperature monitoring device of a power transformer is provided. As shown in fig. 5, the apparatus includes:
an acquisition unit 10 and a processing unit 20, wherein:
in an embodiment, the apparatus further comprises a radio link design unit for:
Determining a temperature measuring node pair required to be subjected to time synchronization by adopting a bidirectional information exchange model;
time synchronization between temperature measuring node pairs is achieved through a receiver-receiver synchronization model.
In one embodiment, the processing unit 20 is specifically configured to:
The multi-scale convolution module adopts filters with different scales to carry out convolution fusion of preset times on the temperature data to obtain feature vectors with different scales;
The method comprises the steps of inputting feature vectors under different scales into a dense stacking network module, wherein the dense stacking network module performs feature fusion on the feature vectors under different scales to obtain fusion features;
The residual module processes the fusion characteristics through a jump connection processing mode to obtain deep characteristic representations suitable for being transmitted in a deep network;
The deep feature representation is input into a compression and excitation attention mechanism module, and the compression and excitation attention mechanism module sequentially inputs the deep feature representation into a global average pooling layer and a full connection layer, models to generate a feature channel and then adjusts the weight of the feature channel to obtain a temperature fault feature;
And comparing the temperature fault characteristics with each sub-fault characteristic in the fault characteristic set in the temperature fault characteristic diagnosis model to obtain a fault diagnosis result of the temperature fault characteristics.
In one embodiment, the processing unit 20 is specifically configured to:
The compression and excitation attention mechanism module inputs the deep feature representation into the global average pooling layer, and adopts compression operation to process the deep feature representation to obtain a first processing result;
inputting the first processing result into the full-connection layer, and processing the first processing result by adopting excitation operation to obtain a second processing result;
and processing the second processing result by adopting scaling operation to obtain the temperature fault characteristic.
In one embodiment, a radio channel with a consistent frequency band is used between each temperature measurement node and the data processing end on the radio link in the acquisition unit 10.
In one embodiment, the intelligent temperature measuring bolt in the acquisition unit 10 comprises a temperature sensor, a thermoelectric generator and a radiator, wherein the temperature sensor is arranged on a temperature sensing surface inside the intelligent temperature measuring bolt, the thermoelectric generator is arranged inside the intelligent temperature measuring bolt, and the radiator is arranged on the top of the intelligent temperature measuring bolt.
The embodiment of the application also provides temperature monitoring equipment of the power transformer. Referring to fig. 6, a schematic diagram of a temperature monitoring device suitable for use in implementing the power transformer provided by the present application is shown. The temperature monitoring device of the power transformer in the embodiment of the present application may include, but is not limited to, a fixed terminal such as a mobile phone, a notebook computer, a PDA (personal digital assistant), a PAD (tablet computer), a desktop computer, and the like. The temperature monitoring device of the power transformer shown in fig. 6 is only an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present application.
As shown in fig. 6, the temperature monitoring device of the power transformer may include a processing means (e.g., a central processing unit, a graphic processor, etc.) 601, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the temperature monitoring apparatus of the power transformer are also stored in the state where the temperature monitoring apparatus of the power transformer is powered on. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
In general, devices may be connected to I/O interface 605 including input devices 606, including for example, touch screens, touch pads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc., output devices 607, including for example, liquid Crystal Displays (LCDs), speakers, vibrators, etc., storage devices 608, including for example, memory cards, hard disks, etc., and communication devices 609. The communication means 609 may allow the temperature monitoring device of the power transformer to communicate wirelessly or by wire with other devices to exchange data. While fig. 6 shows a temperature monitoring apparatus for a power transformer having various devices, it should be understood that not all of the illustrated devices are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
Embodiments of the present application also provide a computer program product including computer readable instructions, which when executed on an electronic device, cause the electronic device to implement any of the methods for monitoring a temperature of a power transformer provided by the embodiments of the present application.
The embodiment of the application also provides a computer storage medium, which carries one or more computer programs, and when the one or more computer programs are executed by the electronic equipment, the electronic equipment can realize the temperature monitoring method of any power transformer provided by the embodiment of the application.
It should be further noted that the above-described apparatus embodiments are merely illustrative, where elements described as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the application, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines.
From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general purpose hardware, or of course by means of special purpose hardware including application specific integrated circuits, special purpose CPUs, special purpose memories, special purpose components, etc. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions can be varied, such as analog circuits, digital circuits, or dedicated circuits. But a software program implementation is a preferred embodiment for many more of the cases of the present application. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk or an optical disk of a computer, etc., comprising several instructions for causing a computer device (which may be a personal computer, a training device, a network device, etc.) to perform the method of the various embodiments of the present application.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.
The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center by a wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). Computer readable storage media can be any available media that can be stored by a computer or data storage devices such as training devices, data centers, and the like, that contain an integration of one or more available media. Usable media may be magnetic media (e.g., floppy disk, hard disk, magnetic tape), optical media (e.g., DVD), or semiconductor media (e.g., solid state disk (Solid STATE DISK, SSD)), etc.
Claims (9)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411881471.8A CN119321834B (en) | 2024-12-19 | 2024-12-19 | A temperature monitoring method and related device for power transformer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411881471.8A CN119321834B (en) | 2024-12-19 | 2024-12-19 | A temperature monitoring method and related device for power transformer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119321834A CN119321834A (en) | 2025-01-17 |
| CN119321834B true CN119321834B (en) | 2025-04-04 |
Family
ID=94234063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411881471.8A Active CN119321834B (en) | 2024-12-19 | 2024-12-19 | A temperature monitoring method and related device for power transformer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119321834B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102566621A (en) * | 2010-12-29 | 2012-07-11 | 上海市电力公司 | Wireless temperature monitoring system for electric power device |
| CN114111886A (en) * | 2021-10-29 | 2022-03-01 | 广州贯行电能技术有限公司 | Power transformer defect online diagnosis method using operation information |
| CN118032160A (en) * | 2023-12-07 | 2024-05-14 | 广东科源电气股份有限公司 | Transformer wireless temperature measurement method, system, electronic equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6817760B2 (en) * | 2002-11-22 | 2004-11-16 | Tektronix, Inc. | Method of monitoring current probe transformer temperature |
| CN105259435A (en) * | 2015-09-23 | 2016-01-20 | 国网山东莒县供电公司 | Transformer monitoring device and fault diagnosis method |
| US11835392B2 (en) * | 2018-01-19 | 2023-12-05 | Hitachi Energy Ltd | Apparatus, system and method for temperature measurement for dry-type transformer |
| CN116295930A (en) * | 2023-03-20 | 2023-06-23 | 华能昭觉风力发电有限公司 | Temperature measurement system of power transmission and transformation equipment |
| CN118332427B (en) * | 2024-06-13 | 2024-09-17 | 湖南恩智测控技术有限公司 | Energy storage capacitor high-low temperature performance evaluation method based on multistage residual feature fusion |
| CN118982726A (en) * | 2024-10-11 | 2024-11-19 | 国网安徽省电力有限公司超高压分公司 | A method, device and storage medium for fault diagnosis of ultra-high voltage converter transformer |
-
2024
- 2024-12-19 CN CN202411881471.8A patent/CN119321834B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102566621A (en) * | 2010-12-29 | 2012-07-11 | 上海市电力公司 | Wireless temperature monitoring system for electric power device |
| CN114111886A (en) * | 2021-10-29 | 2022-03-01 | 广州贯行电能技术有限公司 | Power transformer defect online diagnosis method using operation information |
| CN118032160A (en) * | 2023-12-07 | 2024-05-14 | 广东科源电气股份有限公司 | Transformer wireless temperature measurement method, system, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119321834A (en) | 2025-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12013439B2 (en) | Data processor, data processing method, and computer program | |
| CN113176011B (en) | Intelligent temperature measuring method and system of surface mounted sensor based on Internet of things | |
| JP2019015599A (en) | Control circuit, sensor device, and battery remaining amount measuring method | |
| CN112598201B (en) | A power grid load estimation method and device based on distributed optical fiber temperature measurement | |
| CN106203805A (en) | A kind of active power distribution network probabilistic reliability method of estimation and device | |
| CN116029116B (en) | Intelligent substation wisdom management and control digital twin system | |
| CN119321834B (en) | A temperature monitoring method and related device for power transformer | |
| KR102116613B1 (en) | FOOD THERMOMETER HAVING LoRa COMMUNICATION FUNCTION AND REMOTE MANAGING SYSTEM USING THIS | |
| CN119783317A (en) | A single-core cable contact resistance inversion method and system | |
| JP6542365B2 (en) | Generator for piston apparatus | |
| Gallo et al. | Multisensor network for urban electromagnetic field monitoring | |
| Wang et al. | A self-powered wireless temperature sensing system using flexible thermoelectric generators under simulated thermal condition | |
| CN115825548A (en) | Method and device for determining non-invasive voltage measurement model of high-voltage transmission line | |
| CN106248215A (en) | A kind of real-time calculating system of power transformer critical component running temperature | |
| CN111859802B (en) | Method, system and equipment for calculating steady-state temperature of overhead conductor | |
| CN204964649U (en) | Stator module's thermally stable testing arrangement | |
| CN105841663B (en) | A kind of intelligent power station that can predict shelf-life in real time | |
| CN205981453U (en) | Non -contact infrared thermal imaging intelligence transformer temperature -measuring device | |
| CN114204680A (en) | Multi-type automatic detection equipment fusion remote diagnosis system and method | |
| CN120409377B (en) | PCBA reliability prediction method, device, storage medium and program product | |
| Niedermayer et al. | Wireless condition monitoring for industrial applications based on radio sensor nodes with energy harvesting | |
| Goldsmith et al. | Wireless sensor networks for aerospace applications-thermal monitoring for a gas turbine engine | |
| CN120492990B (en) | Temperature sensor fault detection system, temperature sensor fault tolerance control method, temperature sensor fault tolerance control equipment and storage medium | |
| CN220251046U (en) | Multifunctional high-voltage live display device and power cabinet monitoring system | |
| CN119826994B (en) | Wireless temperature measurement method and wireless temperature measurement sensor |
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 |