CN119813852A - AC/DC generator regulator control method, system, device and medium - Google Patents
AC/DC generator regulator control method, system, device and medium Download PDFInfo
- Publication number
- CN119813852A CN119813852A CN202411957429.XA CN202411957429A CN119813852A CN 119813852 A CN119813852 A CN 119813852A CN 202411957429 A CN202411957429 A CN 202411957429A CN 119813852 A CN119813852 A CN 119813852A
- Authority
- CN
- China
- Prior art keywords
- generator
- data
- load
- parameters
- load prediction
- 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.)
- Pending
Links
Landscapes
- Feedback Control In General (AREA)
Abstract
本申请涉及一种交直流发电机调节器控制方法、系统、设备及介质，该方法包括获取发电机实时负荷数据和所处环境数据，对发电机实时负荷数据和所处环境数据进行预处理，得到预处理后的数据；将预处理后的数据传输至预先训练好的负荷预测模型中进行比对分析，得到负载预测结果；根据负载预测结果，生成发电机的初步控制策略；利用数字孪生条件构建发电机的虚拟模型，模拟发电机在不同负荷和运行下的状态，并基于虚拟仿真数据对初步控制策略的参数进行优化，生成发电机的优化策略；基于发电机的优化策略，应用自适应抗干扰控制与模糊控制算法对发电机的运行参数进行调节，以实现平稳高效的运行。本申请具有提升发电机的调节精度的效果。
The present application relates to a method, system, device and medium for controlling an AC/DC generator regulator, which includes obtaining real-time load data and environment data of the generator, preprocessing the real-time load data and environment data of the generator to obtain preprocessed data; transmitting the preprocessed data to a pre-trained load prediction model for comparison and analysis to obtain a load prediction result; generating a preliminary control strategy for the generator based on the load prediction result; constructing a virtual model of the generator using digital twin conditions to simulate the state of the generator under different loads and operations, and optimizing the parameters of the preliminary control strategy based on the virtual simulation data to generate an optimization strategy for the generator; based on the optimization strategy of the generator, applying adaptive anti-interference control and fuzzy control algorithms to adjust the operating parameters of the generator to achieve smooth and efficient operation. The present application has the effect of improving the regulation accuracy of the generator.
Description
Technical Field
The application relates to the technical field of power electronic conversion, in particular to a control method, a control system, a control device and a control medium of an alternating current-direct current generator regulator.
Background
In recent years, with the increase in power demand and the advancement of technology, generator technology has been rapidly developed. The traditional generator regulator adopts an analog circuit design, and the analog regulator realizes voltage regulation by using a feedback loop formed by elements such as a resistor, a capacitor and the like, and has the advantages of low cost and simple structure, but has weak anti-interference capability, low regulation precision and difficult adaptation to complex working environments.
The prior art scheme has the defects that the prior generator regulator has low regulation precision and low response speed, and particularly under the condition of severe load change, the prior regulator has difficulty in quickly regulating the output voltage, so that the system performance is reduced, and therefore, the prior generator regulator has room for improvement.
Disclosure of Invention
In order to improve the regulation precision of a generator, the application provides a control method, a system, equipment and a medium of an alternating current-direct current generator regulator.
The first object of the present application is achieved by the following technical solutions:
An ac/dc generator regulator control method, the ac/dc generator regulator control method comprising:
acquiring real-time load data and environment data of a generator, and preprocessing the real-time load data and the environment data of the generator according to a filtering and impurity removing algorithm to obtain preprocessed data;
Transmitting the preprocessed data to a pre-trained load prediction model for comparison and analysis to obtain a load prediction result;
Generating a preliminary control strategy of the generator according to the load prediction result;
Constructing a virtual model of the generator by utilizing digital twin conditions, simulating states of the generator under different loads and running through a virtual environment, and optimizing parameters of the preliminary control strategy based on virtual simulation data to generate an optimization strategy of the generator;
And based on the optimization strategy of the generator, the operation parameters of the generator are adjusted by applying a self-adaptive anti-interference control and fuzzy control algorithm so as to realize stable and efficient operation.
According to the technical scheme, the load and environment data of the generator are obtained in real time, the filtering and impurity removing algorithm is applied to conduct data preprocessing, the accuracy and reliability of the data are improved, the preprocessed data are input into a trained load prediction model, accurate load prediction results are obtained through comparison and analysis, future load change trend of the generator can be predicted in advance, scientific basis is provided for formulating a control strategy, the response speed and adaptability of the generator are improved, a preliminary control strategy is formulated based on the load prediction results, the generator can be effectively adjusted under the predicted load change, stable operation of the generator is facilitated, unstable operation or efficiency reduction caused by load fluctuation is avoided, a virtual model of the generator is built through a digital twin technology, parameters of the preliminary control strategy are optimized by means of virtual simulation data, the risk in actual operation can be reduced, the control strategy is improved, the self-adaptive control algorithm can be effectively adjusted according to the fuzzy control algorithm, and the overall operation stability of the generator can be effectively improved, and the overall operation stability can be effectively improved according to the fuzzy control algorithm.
The method can be further configured in a preferred example, wherein the acquiring the real-time load data and the environmental data of the generator, preprocessing the real-time load data and the environmental data of the generator according to a filtering and impurity removing algorithm, and obtaining preprocessed data comprises the following steps:
Carrying out noise suppression and signal smoothing on the real-time load data of the generator by using a Kalman filtering algorithm to remove high-frequency interference signals and obtain preprocessed load data;
Removing abnormal values in the environment data by using a median filtering technology to obtain preprocessed environment data;
and carrying out normalization processing, and carrying out normalization processing on the preprocessed load data and the preprocessed environment data to obtain the preprocessed data.
By adopting the technical scheme, noise suppression and signal smoothing of load data are carried out by applying Kalman filtering, abnormal values in environmental data are removed by using median filtering, and data normalization processing is carried out, so that the accuracy, reliability and consistency of the data are remarkably improved, a solid data basis is provided for subsequent load prediction, dynamic resource allocation and system optimization, and the high-efficiency operation capacity and resource utilization rate of the cabinet under multitasking load are further improved.
The application can be further configured in a preferred example, wherein before the preprocessed data is transmitted to a pre-trained load prediction model for comparison and analysis, the control method of the ac/dc generator regulator further comprises:
Acquiring historical load data and historical environment parameters, and generating an input feature set by extracting features of the historical load data and the historical environment parameters;
Based on the input feature set, training a basic model by adopting a mode of combining a long-term memory network and a neural network model to obtain a load prediction model;
and optimizing parameters of the load prediction model through cross verification to obtain the pre-trained load prediction model.
By adopting the technical scheme, the input feature set is generated by extracting the features of the historical load data and the environmental parameters, the basic model training is performed by combining the long-term and short-term memory network with the neural network model, and the model parameters are optimized by cross verification, so that the accuracy, the robustness and the generalization capability of the load prediction model are remarkably improved, the reliable load prediction results can be ensured to be provided under different environmental conditions, the running scheduling and the resource allocation of the generator are optimized, and the overall running efficiency and the overall stability of the system are improved.
The present application may be further configured in a preferred example, wherein the transmitting the preprocessed data to a pre-trained load prediction model for comparison and analysis, to obtain a load prediction result includes:
capturing a time sequence rule of load change in the preprocessing data through a multi-layer neural network structure to obtain a load change rule;
And calculating the preprocessed data by utilizing the weight and parameters in the pre-trained load prediction model, and combining the load change rule to obtain the load prediction result.
By adopting the technical scheme, the load change time sequence rule in the preprocessing data is captured through the multi-layer neural network structure, the weight and the parameter of the pre-trained load prediction model are utilized to calculate in combination with the load change rule, the accuracy of load prediction and the adaptability of the model are remarkably improved, the dynamic change trend of the load can be reflected more accurately, more reliable prediction support is provided for the operation scheduling and resource optimization of the generator, and the overall efficiency and the stability of the system are improved.
The application may further be configured in a preferred example in that said generating a preliminary control strategy of said generator based on said load prediction result comprises:
Generating a load trend graph of the next time period based on the load prediction result, and marking and recording mutation points and abnormal fluctuation in the load trend graph of the next time period;
generating a preliminary control strategy of the generator according to the load trend graph in the next time period, wherein the preliminary control strategy of the generator comprises the steps of adjusting the output power of the generator, adjusting the exciting current of the generator and adjusting the frequency output of the generator.
By adopting the technical scheme, the monitoring capability and the running efficiency of the power system are obviously improved, the stability and the reliability of the system are enhanced, the power generator can rapidly and accurately respond to load change, the resource allocation is optimized, and the running performance of the whole power system is improved by generating the load trend graph and marking abnormal fluctuation and formulating a preliminary control strategy of the power generator.
The application can be further configured in a preferred example to construct a virtual model of the generator using digital twin conditions, simulate states of the generator under different loads and operations by a virtual environment, and optimize parameters of the preliminary control strategy based on virtual simulation data, the generating an optimization strategy of the generator comprising:
establishing a virtual model matched with physical characteristics of the generator, wherein the physical characteristics of the generator comprise electrical parameters, mechanical parameters and thermal parameters;
In a virtual environment, simulating the running states of the generator under different loads and working conditions, recording the influence of load changes on the voltage, current and temperature of the generator, and performing iterative optimization on the parameters of the preliminary control strategy by using a genetic algorithm and a particle swarm optimization algorithm to generate an optimization strategy of the generator.
By adopting the technical scheme, the running efficiency of the generator and the stability of the system are remarkably improved by establishing the virtual model matched with the physical characteristics of the generator, simulating the running state in the virtual environment and optimizing the control strategy by utilizing the genetic algorithm and the particle swarm optimization algorithm, the optimized control strategy enables the generator to keep stable running under various loads and working conditions, the energy consumption and the maintenance cost are reduced, and the overall performance of the power system is improved.
The present application may be further configured in a preferred example, in which the ac/dc generator regulator control method further includes:
Determining the working state of the generator by analyzing the real-time voltage, current, temperature and power of the generator and combining the load prediction result;
and starting a multi-level protection mechanism according to the working state of the generator, and adjusting the operation mode of the generator by using fuzzy logic and an adaptive algorithm.
By adopting the technical scheme, the operation safety and efficiency of the generator are remarkably improved, the stability and reliability of a power system are enhanced, the generator can be ensured to operate efficiently and stably under various loads and working conditions, the fault risk is reduced, and the energy utilization is optimized by analyzing the real-time voltage, current, temperature and power of the generator, combining the load prediction result, starting a multi-level protection mechanism and utilizing the fuzzy logic and the self-adaptive algorithm to adjust the operation mode.
The second object of the present application is achieved by the following technical solutions:
an ac-dc generator regulator control system, the ac-dc generator regulator control system comprising:
The data acquisition module is used for acquiring real-time load data and environment data of the generator, preprocessing the real-time load data and the environment data of the generator according to a filtering and impurity removal algorithm, and acquiring preprocessed data;
The comparison analysis module is used for transmitting the preprocessed data to a pre-trained load prediction model for comparison analysis to obtain a load prediction result;
The preliminary strategy generation module is used for generating a preliminary control strategy of the generator according to the load prediction result;
The optimizing strategy module is used for constructing a virtual model of the generator by utilizing digital twin conditions, simulating states of the generator under different loads and running through a virtual environment, optimizing parameters of the primary control strategy based on virtual simulation data, and generating an optimizing strategy of the generator;
and the adjusting module is used for adjusting the operation parameters of the generator by applying a self-adaptive anti-interference control and fuzzy control algorithm based on the optimization strategy of the generator so as to realize stable and efficient operation.
According to the technical scheme, the load and environment data of the generator are obtained in real time, the filtering and impurity removing algorithm is applied to conduct data preprocessing, the accuracy and reliability of the data are improved, the preprocessed data are input into a trained load prediction model, accurate load prediction results are obtained through comparison and analysis, future load change trend of the generator can be predicted in advance, scientific basis is provided for formulating a control strategy, the response speed and adaptability of the generator are improved, a preliminary control strategy is formulated based on the load prediction results, the generator can be effectively adjusted under the predicted load change, stable operation of the generator is facilitated, unstable operation or efficiency reduction caused by load fluctuation is avoided, a virtual model of the generator is built through a digital twin technology, parameters of the preliminary control strategy are optimized by means of virtual simulation data, the risk in actual operation can be reduced, the control strategy is improved, the self-adaptive control algorithm can be effectively adjusted according to the fuzzy control algorithm, and the overall operation stability of the generator can be effectively improved, and the overall operation stability can be effectively improved according to the fuzzy control algorithm.
The third object of the present application is achieved by the following technical solutions:
a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of a method of controlling an ac/dc generator regulator as described above when the computer program is executed.
The fourth object of the present application is achieved by the following technical solutions:
A computer readable storage medium storing a computer program which when executed by a processor performs the steps of a method of controlling an ac/dc generator regulator as described above.
In summary, the present application includes at least one of the following beneficial technical effects:
1. The method comprises the steps of acquiring load and environment data of a generator in real time, applying a filtering and impurity removing algorithm to perform data preprocessing, effectively removing noise and interference, improving the accuracy and reliability of the data, inputting the preprocessed data into a trained load prediction model, obtaining an accurate load prediction result through comparison and analysis, predicting a future load change trend of the generator in advance, providing scientific basis for formulating a control strategy, improving the response speed and adaptability of the generator, formulating a preliminary control strategy based on the load prediction result, ensuring that the generator can be effectively adjusted under the predicted load change, facilitating the realization of stable operation of the generator, and avoiding unstable operation or efficiency reduction caused by load fluctuation;
2. The method comprises the steps of constructing a virtual model of the generator by a digital twin technology, simulating generator states under different loads and running conditions in a virtual environment, optimizing parameters of a preliminary control strategy by utilizing virtual simulation data, generating a more accurate and efficient optimized control strategy, fully testing and adjusting the parameters before actual application, reducing risks in actual running, improving the effectiveness and adaptability of the control strategy, dynamically adjusting running parameters of the generator by adopting a self-adaptive anti-interference control and fuzzy control algorithm according to the optimized control strategy, effectively aiming at external interference and internal load changes, keeping the running stability of the generator, improving the running efficiency of the generator and realizing stable and efficient integral running.
Drawings
FIG. 1 is a flow chart of a method for controlling an AC/DC generator regulator according to an embodiment of the application;
FIG. 2 is a flowchart showing an implementation of step S10 in a control method of an AC/DC generator regulator according to an embodiment of the present application;
FIG. 3 is a flowchart showing another implementation of step S20 in a control method of an AC/DC generator regulator according to an embodiment of the present application;
FIG. 4 is a flowchart showing an implementation of step S20 in a control method of an AC/DC generator regulator according to an embodiment of the present application;
FIG. 5 is a flowchart showing an implementation of step S30 in a control method of an AC/DC generator regulator according to an embodiment of the present application;
FIG. 6 is a flowchart illustrating an implementation of step S40 in a method for controlling an AC/DC generator regulator according to an embodiment of the present application;
FIG. 7 is a flow chart of another implementation of a method for controlling an AC/DC generator regulator in accordance with an embodiment of the present application;
FIG. 8 is a schematic block diagram of an AC/DC generator regulator control system according to an embodiment of the present application;
fig. 9 is a schematic diagram of an apparatus in an embodiment of the application.
Detailed Description
The present application will be described in further detail with reference to the accompanying drawings.
In an embodiment, as shown in fig. 1, the application discloses a control method of an ac/dc generator regulator, which specifically comprises the following steps:
And S10, acquiring real-time load data and environment data of the generator, and preprocessing the real-time load data and the environment data of the generator according to a filtering and impurity removing algorithm to obtain preprocessed data.
Specifically, key operation data and environment data of the generator, such as voltage, current, power, temperature, humidity, air pressure and the like, are collected in real time through the sensor, and in order to improve the data quality, a filtering and impurity removing algorithm is adopted to conduct preprocessing, for example, the system is assumed to detect that load current data are 5A, 5.1A, 5.4A, 10A and 5.2A, after median filtering is applied, an abnormal value 10A is filtered, smooth current data are obtained, the accuracy of subsequent calculation is ensured, and finally preprocessed data are obtained.
And S20, transmitting the preprocessed data to a pre-trained load prediction model for comparison and analysis to obtain a load prediction result.
Specifically, the preprocessed data is transmitted to a pre-trained load prediction model, the model can be trained by using a deep learning algorithm (such as an LSTM network), the main purpose is to predict the future load change trend according to the load historical data and the current real-time data, and the prediction model captures the rule of the load change through time sequence characteristics, so that a load prediction result in a future period of time is provided, for example, the model predicts that the load increases to 10A in the future 10 minutes under the current condition. This prediction may help the control strategy prepare in advance, ensuring that the generator can smoothly cope with the upcoming load change.
And S30, generating a preliminary control strategy of the generator according to the load prediction result.
Specifically, the load prediction result is used for generating a preliminary control strategy of the generator, the control strategy comprises the steps of adjusting the output power, exciting current and frequency of the generator to adapt to future load demands, specifically, if a load prediction model shows that the future load will increase, the control strategy can correspondingly increase the power output, if the load decreases, the power output is reduced to avoid energy waste, if the load predicts that the future load will increase to 10A, the preliminary control strategy can increase the output power of the generator to 12kW, and the exciting current is appropriately increased to ensure voltage stability.
S40, constructing a virtual model of the generator by utilizing digital twin conditions, simulating states of the generator under different loads and running through a virtual environment, and optimizing parameters of a preliminary control strategy based on virtual simulation data to generate an optimization strategy of the generator.
Specifically, under the digital twin condition, a virtual model is created, so that the physical characteristics of the generator can be accurately reflected, through the virtual model, the running state of the generator can be simulated under different loads and working conditions, the influence of load change on parameters such as voltage, current and temperature of the generator is observed, and the preliminary control strategy is subjected to iterative optimization through a genetic algorithm or a particle swarm optimization algorithm to obtain a better control strategy, so that the generator can run efficiently, namely the working conditions when the load is increased to 10A are simulated in the virtual model, the voltage and current fluctuation condition is observed, the preliminary control strategy is gradually optimized, and finally an optimal strategy is generated, so that the generator runs with optimal energy efficiency under the load of 10A.
And S50, based on an optimization strategy of the generator, the operation parameters of the generator are adjusted by applying a self-adaptive anti-interference control and fuzzy control algorithm so as to realize stable and efficient operation.
Specifically, in the actual running of the generator, the adaptive anti-interference control and the fuzzy control algorithm are used for realizing fine adjustment, the adaptive anti-interference control can eliminate external interference in running, stable output is maintained, parameters of the generator are dynamically adjusted by setting fuzzy rules under different loads and environmental conditions, for example, when the actual load reaches 10A, the internal temperature of the generator is increased suddenly due to the sudden increase of the environmental temperature, the fuzzy control detects temperature change, exciting current is automatically adjusted, stable output voltage is ensured, meanwhile, the adaptive anti-interference control detects external load fluctuation, a control strategy is further optimized, frequency fluctuation is prevented, stable running can be maintained under load fluctuation, and the complex change of the load is adapted.
According to the technical scheme, the load and environment data of the generator are obtained in real time, the filtering and impurity removing algorithm is applied to conduct data preprocessing, the accuracy and reliability of the data are improved, the preprocessed data are input into a trained load prediction model, accurate load prediction results are obtained through comparison and analysis, future load change trend of the generator can be predicted in advance, scientific basis is provided for formulating a control strategy, the response speed and adaptability of the generator are improved, a preliminary control strategy is formulated based on the load prediction results, the generator can be effectively adjusted under the predicted load change, stable operation of the generator is facilitated, unstable operation or efficiency reduction caused by load fluctuation is avoided, a virtual model of the generator is built through a digital twin technology, parameters of the preliminary control strategy are optimized by means of virtual simulation data, the risk in actual operation can be reduced, the control strategy is improved, the self-adaptive control algorithm can be effectively adjusted according to the fuzzy control algorithm, and the overall operation stability of the generator can be effectively improved, and the overall operation stability can be effectively improved according to the fuzzy control algorithm.
In one embodiment, as shown in fig. 2, in step S10, real-time load data and environmental data of the generator are obtained, and the real-time load data and the environmental data of the generator are preprocessed according to a filtering and impurity removing algorithm to obtain preprocessed data, which specifically includes:
And S11, carrying out noise suppression and signal smoothing processing on the real-time load data of the generator by applying a Kalman filtering algorithm to remove high-frequency interference signals, and obtaining preprocessed load data.
Specifically, a Kalman filtering algorithm is applied to carry out noise suppression and signal smoothing on real-time load data of the generator, and for the real-time load data (such as current, voltage and the like) of the generator, the Kalman filtering algorithm can filter out high-frequency interference signals in a noisy environment, and meanwhile trend information of the data is reserved to remove the high-frequency interference signals, so that the preprocessed load data is finally obtained.
And S12, eliminating abnormal values in the environment data by using a median filtering technology to obtain the preprocessed environment data.
Specifically, the abnormal value in the environmental data is removed by using a median filtering technology, in the processing, the environmental data in a period of time window is taken, the median is calculated, the abnormal value is replaced by the median, namely, a proper window is selected, the median of the data in the window is calculated, and the value of the central position of the window is replaced by the median, so that the data flow is smoothed, and the preprocessed environmental data is obtained after the processing.
And S13, carrying out normalization processing, and carrying out standardization processing on the preprocessed load data and the preprocessed environment data to obtain preprocessed data.
Specifically, normalization processing is implemented, the preprocessed load data and the preprocessed environment data are subjected to normalization processing, the data are scaled to a fixed range, usually [0,1] or [ -1,1], the data with different sources and different dimensions can be compared in a unified range, the accuracy of a model is prevented from being influenced by different units of the data, and the preprocessed data are obtained after normalization processing.
In one embodiment, as shown in fig. 3, in step S20, the method further includes, before the preprocessed data is transmitted to a pre-trained load prediction model for comparison and analysis to obtain a load prediction result,:
S201, acquiring historical load data and historical environment parameters, and generating an input feature set by extracting features of the historical load data and the historical environment parameters.
Specifically, historical load data and historical environment parameters of the generator in different time periods are collected, the historical data reflect the running states of the generator under different load conditions and change rules influenced by external environments, a statistical method is adopted, such as calculating the average value, the maximum value, the minimum value, the standard deviation and the like of the load data, or periodic and trend characteristics are obtained through time sequence analysis, key characteristics in the historical load and the environment data are combined into a characteristic set, and the characteristic set can comprise characteristics such as average load of last hour, temperature change rate of last day and the like, so that the model is helped to learn the relation between the load and the environment, and finally the input characteristic set of the prediction model is obtained.
S202, training a basic model by adopting a mode of combining a long-term memory network and a neural network model based on an input characteristic set to obtain a load prediction model.
Specifically, the generated input feature set is input into a deep learning model for training, a long-term and short-term memory network and a neural network model are combined for training a basic model, the feature set is input into an LSTM layer, the LSTM layer learns long-term dependency features of time sequence data, then, the output of the LSTM can be transmitted to an MLP network for further processing, so that richer feature representation is obtained, the model is trained by inputting a large amount of historical data, so that the model learns the change rule of load and environment, the weight of the model is continuously adjusted by adopting a back propagation algorithm in the training process, the prediction error is reduced, and finally the model is trained to obtain the load prediction model.
And S203, optimizing parameters of the load prediction model through cross verification to obtain a pre-trained load prediction model.
Specifically, after model training is completed, cross-validation is performed to optimize model parameters, wherein the cross-validation is to divide a data set into a plurality of parts, one part is used as a test set each time, the rest is used as a training set, training and validation are repeatedly performed, in the cross-validation process, super parameters of the model, such as LSTM layer number, neuron number, learning rate and the like, are continuously adjusted, and finally, a parameter combination which enables a prediction error to be minimum is selected as a final parameter of the model, so that a pre-trained load prediction model is obtained through optimization.
In one embodiment, as shown in fig. 4, in step S20, the preprocessed data is transmitted to a pre-trained load prediction model for comparison and analysis, so as to obtain a load prediction result, which specifically includes:
s21, capturing a time sequence rule of load change in the preprocessing data through a multi-layer neural network structure to obtain a load change rule.
Specifically, the pre-processed load data is input into the neural network, the data is organized into a sequence of time steps, e.g., hourly, daily or weekly load data, and the trained multi-layer neural network is able to extract the time series characteristics in the load data, assuming we have a set of consecutive generator load data (e.g., currents) [8A, 10A, 12A, 11A, 13A, 15A ]. The method comprises the steps of utilizing a multilayer structure of an LSTM model, enabling a first layer to capture short-term changes, such as load fluctuation between every two moments, enabling a second layer to further integrate short-term change results, identifying long-term trends, such as overall increasing trend of loads, enabling the model to learn up to the increasing characteristics of the loads at different times through processing of the multilayer LSTM, and finally generating representation of load change rules.
S22, calculating the preprocessed data by utilizing the weight and parameters in the pre-trained load prediction model, and combining the load change rule to obtain a load prediction result.
Specifically, the preprocessed load data and environment data are input according to the format required by the model, such as tensor shape, batch size and the like, the input data are calculated by utilizing loaded weights and parameters through the forward propagation process of the model to obtain a preliminary load prediction result, the load change rule extracted in the first step is combined with the output of the pre-training model, for example, the time sequence characteristic is fused with the middle layer output or the final output of the model to serve as the input of the final prediction or the prediction result is adjusted according to the load change rule, for example, the output of the two is combined by using a weighted average method, and the load prediction result is finally generated.
In one embodiment, as shown in fig. 5, in step S30, a preliminary control strategy of the generator is generated according to the load prediction result, which specifically includes:
And S31, generating a load trend graph of the next time period based on the load prediction result, and marking and recording mutation points and abnormal fluctuation in the load trend graph of the next time period.
Specifically, a load prediction result of a future period of time, such as a future period of minutes or hours, is obtained through a load prediction model, these data points are drawn into a trend chart to intuitively show the change condition of the load, and abrupt points of load change and abnormal fluctuation, such as a point of abrupt rise or fall of the load with a larger change compared with the normal fluctuation amplitude, are marked in the trend chart, and these points are usually key nodes of a load adjustment strategy, for example, after the trend chart is drawn, the load gradually increases to a peak value of 25A in the first 30 minutes, and then the load gradually decreases in the last 30 minutes, at this time, the point of the load rapidly rising to 25A and the subsequent point of fall can be marked as abrupt points.
And S32, generating a preliminary control strategy of the generator according to the load trend graph in the next time period, wherein the preliminary control strategy of the generator comprises the steps of adjusting the output power of the generator, adjusting the exciting current of the generator and adjusting the frequency output of the generator.
Specifically, according to a load trend graph in the next time period, a preliminary control strategy of the generator is generated, for example, when load rising is predicted, power output of the generator is increased, when load falling is predicted, power output is reduced, energy waste is avoided, exciting current is properly increased when load is increased so as to keep voltage stable, exciting current is reduced when load falling, voltage is prevented from being too high, and when load suddenly changes or abnormally fluctuates, frequency output of the generator can be properly adjusted so as to stabilize the frequency of a power generation system and ensure output power quality.
In one embodiment, as shown in fig. 6, in step S40, a virtual model of the generator is constructed by using digital twin conditions, states of the generator under different loads and operations are simulated by the virtual environment, and parameters of the preliminary control strategy are optimized based on virtual simulation data, so as to generate an optimization strategy of the generator, which specifically includes:
and S41, establishing a virtual model matched with physical characteristics of the generator, wherein the physical characteristics of the generator comprise, but are not limited to, electrical parameters, mechanical parameters and thermal parameters.
Specifically, suitable simulation software such as MATLAB/Simulink, ANSYS, PSS/E is selected and used for establishing a virtual model of the generator, and the virtual model matched with the physical characteristics of the generator is established, wherein the physical characteristics of the generator include but are not limited to electrical parameters, mechanical parameters and thermal parameters, the model parameters are adjusted through comparison with actual generator operation data, the virtual model can be ensured to accurately reflect the physical characteristics of the generator, multiple simulation tests are carried out, and the accuracy and stability of the model under different working conditions are verified.
S42, in the virtual environment, simulating the running states of the generator under different loads and working conditions, recording the influence of load changes on the voltage, current and temperature of the generator, and performing iterative optimization on the parameters of the primary control strategy by utilizing a genetic algorithm and a particle swarm optimization algorithm to generate an optimization strategy of the generator.
Specifically, in the virtual environment, the running state of the generator under various conditions is simulated by adjusting the load and the working condition, for example, different load curves can be set, when the load is changed, the change condition of the voltage, the current and the temperature of the generator is observed, the influence of the load change on the electric and thermal parameters of the virtual generator is recorded, for example, as the load is increased, the current is possibly increased, the temperature is also increased, the change trend of the parameters is analyzed, possible limit values and abnormal conditions are found, the optimization results of a genetic algorithm and a particle swarm optimization algorithm are integrated, the optimal control parameters are determined, and a final generator optimization control strategy is generated.
In one embodiment, as shown in fig. 7, the control method of the ac/dc generator regulator further includes:
s60, determining the working state of the generator by analyzing the real-time voltage, current, temperature and power of the generator and combining the load prediction result.
Specifically, in actual operation, parameters such as voltage, current, temperature and power of the generator are monitored in real time, working states are classified into different grades according to the real-time parameters, for example, current is smaller than 20A and is light load, 20A-40A is normal load, and current is larger than 40A and is heavy load, temperature is lower than 60 ℃ and is normal, temperature is higher than 70 ℃ and is overheated, and the like, and the current working states of the generator such as light load, heavy load, overload and the like are determined by combining load prediction results.
And S70, starting a multi-level protection mechanism according to the working state of the generator, and adjusting the operation mode of the generator by using fuzzy logic and an adaptive algorithm.
Specifically, different protection mechanisms are started in a grading manner according to the real-time state of the generator, for example, a low-grade protection mechanism such as power-down operation is started when the generator is slightly overloaded, a high-grade protection mechanism such as output cutting or load limiting is started when the generator is severely overloaded, and a proper operation mode such as a stable mode, an energy-saving mode, an emergency mode and the like is selected according to different state levels through fuzzy logic and an adaptive algorithm to realize flexible control.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.
In an embodiment, an ac/dc generator regulator control system is provided, which corresponds to one of the ac/dc generator regulator control methods in the above embodiments. As shown in fig. 8, the ac/dc generator regulator control system includes a data acquisition module, an comparison analysis module, a preliminary strategy generation module, an optimization strategy module, and a regulation module. The functional modules are described in detail as follows:
The data acquisition module is used for acquiring real-time load data of the generator and the environmental data, and preprocessing the real-time load data of the generator and the environmental data according to a filtering and impurity removal algorithm to obtain preprocessed data;
The comparison analysis module is used for transmitting the preprocessed data to a pre-trained load prediction model for comparison analysis to obtain a load prediction result;
the primary strategy generation module is used for generating a primary control strategy of the generator according to the load prediction result;
The optimizing strategy module is used for constructing a virtual model of the generator by utilizing digital twin conditions, simulating the states of the generator under different loads and running conditions through a virtual environment, optimizing parameters of the primary control strategy based on virtual simulation data, and generating an optimizing strategy of the generator;
the adjusting module is used for adjusting the operation parameters of the generator by applying the self-adaptive anti-interference control and fuzzy control algorithm based on the optimization strategy of the generator so as to realize stable and efficient operation.
Optionally, the data acquisition module includes:
The load filtering sub-module is used for carrying out noise suppression and signal smoothing on the real-time load data of the generator by applying a Kalman filtering algorithm so as to remove high-frequency interference signals and obtain preprocessed load data;
the environment filtering sub-module is used for removing abnormal values in the environment data by utilizing a median filtering technology to obtain preprocessed environment data;
And the normalization sub-module is used for carrying out normalization processing and carrying out standardization processing on the preprocessed load data and the preprocessed environment data to obtain preprocessed data.
Optionally, the ac/dc generator regulator control system further includes:
The historical data acquisition module is used for acquiring historical load data and historical environment parameters, and generating an input feature set by extracting features of the historical load data and the historical environment parameters;
The model training module is used for training the basic model by adopting a mode of combining a long-term memory network and a neural network model based on an input feature set to obtain a load prediction model;
And the model verification module is used for obtaining a pre-trained load prediction model by cross verification of parameters of the optimized load prediction model.
The real-time monitoring module is used for determining the working state of the generator by analyzing the real-time voltage, current, temperature and power of the generator and combining the load prediction result;
And the protection adjusting module is used for starting a multi-level protection mechanism according to the working state of the generator and adjusting the operation mode of the generator by utilizing the fuzzy logic and the self-adaptive algorithm.
Optionally, the comparison analysis module includes:
the load change acquisition sub-module is used for capturing a time sequence rule of load change in the preprocessing data through a multi-layer neural network structure to obtain a load change rule;
And the calculation sub-module is used for calculating the preprocessed data by utilizing the weight and the parameters in the pre-trained load prediction model and combining the load change rule to obtain a load prediction result.
Optionally, generating the preliminary policy module includes:
The trend graph generation sub-module is used for generating a load trend graph of the next time period based on the load prediction result, and marking and recording mutation points and abnormal fluctuation in the load trend graph of the next time period;
And the primary strategy sub-module is used for generating a primary control strategy of the generator according to the load trend graph in the next time period, wherein the primary control strategy of the generator comprises the steps of adjusting the output power of the generator, adjusting the exciting current of the generator and adjusting the frequency output of the generator.
Optionally, the optimizing policy module includes:
The virtual construction sub-module is used for establishing a virtual model matched with the physical characteristics of the generator, wherein the physical characteristics of the generator comprise electrical parameters, mechanical parameters and thermal parameters;
And the strategy optimization sub-module is used for simulating the running states of the generator under different loads and working conditions in a virtual environment, recording the influence of load changes on the voltage, current and temperature of the generator, and carrying out iterative optimization on the parameters of the primary control strategy by utilizing a genetic algorithm and a particle swarm optimization algorithm to generate an optimization strategy of the generator.
For a specific limitation of an ac/dc generator regulator control system, reference may be made to the limitation of an ac/dc generator regulator control method hereinabove, and no further description is given here. Each of the modules in the ac/dc generator regulator control system described above may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 9. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a method of controlling an ac/dc generator regulator.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program:
acquiring real-time load data and environmental data of a generator, and preprocessing the real-time load data and the environmental data of the generator according to a filtering and impurity removing algorithm to obtain preprocessed data;
Transmitting the preprocessed data to a pre-trained load prediction model for comparison and analysis to obtain a load prediction result;
generating a preliminary control strategy of the generator according to the load prediction result;
Constructing a virtual model of the generator by utilizing digital twin conditions, simulating states of the generator under different loads and running through a virtual environment, and optimizing parameters of a preliminary control strategy based on virtual simulation data to generate an optimization strategy of the generator;
Based on an optimization strategy of the generator, the operation parameters of the generator are adjusted by applying a self-adaptive anti-interference control and fuzzy control algorithm so as to realize stable and efficient operation
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring real-time load data and environmental data of a generator, and preprocessing the real-time load data and the environmental data of the generator according to a filtering and impurity removing algorithm to obtain preprocessed data;
Transmitting the preprocessed data to a pre-trained load prediction model for comparison and analysis to obtain a load prediction result;
generating a preliminary control strategy of the generator according to the load prediction result;
Constructing a virtual model of the generator by utilizing digital twin conditions, simulating states of the generator under different loads and running through a virtual environment, and optimizing parameters of a preliminary control strategy based on virtual simulation data to generate an optimization strategy of the generator;
Based on an optimization strategy of the generator, the operation parameters of the generator are adjusted by applying a self-adaptive anti-interference control and fuzzy control algorithm so as to realize stable and efficient operation
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the system is divided into different functional units or modules to perform all or part of the above-described functions.
The foregoing embodiments are merely illustrative of the technical solutions of the present application, and not restrictive, and although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that modifications may still be made to the technical solutions described in the foregoing embodiments or equivalent substitutions of some technical features thereof, and that such modifications or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. The control method of the alternating current-direct current generator regulator is characterized by comprising the following steps of:
acquiring real-time load data and environment data of a generator, and preprocessing the real-time load data and the environment data of the generator according to a filtering and impurity removing algorithm to obtain preprocessed data;
Transmitting the preprocessed data to a pre-trained load prediction model for comparison and analysis to obtain a load prediction result;
Generating a preliminary control strategy of the generator according to the load prediction result;
Constructing a virtual model of the generator by utilizing digital twin conditions, simulating states of the generator under different loads and running through a virtual environment, and optimizing parameters of the preliminary control strategy based on virtual simulation data to generate an optimization strategy of the generator;
And based on the optimization strategy of the generator, the operation parameters of the generator are adjusted by applying a self-adaptive anti-interference control and fuzzy control algorithm so as to realize stable and efficient operation.
2. The method for controlling an ac/dc power generator regulator according to claim 1, wherein the obtaining real-time load data and environmental data of the power generator, preprocessing the real-time load data and the environmental data of the power generator according to a filtering and impurity removing algorithm, and obtaining preprocessed data comprises:
Carrying out noise suppression and signal smoothing on the real-time load data of the generator by using a Kalman filtering algorithm to remove high-frequency interference signals and obtain preprocessed load data;
Removing abnormal values in the environment data by using a median filtering technology to obtain preprocessed environment data;
and carrying out normalization processing, and carrying out normalization processing on the preprocessed load data and the preprocessed environment data to obtain the preprocessed data.
3. The method according to claim 1, wherein before the pre-processed data is transmitted to a pre-trained load prediction model for comparison and analysis, the method further comprises:
Acquiring historical load data and historical environment parameters, and generating an input feature set by extracting features of the historical load data and the historical environment parameters;
Based on the input feature set, training a basic model by adopting a mode of combining a long-term memory network and a neural network model to obtain a load prediction model;
and optimizing parameters of the load prediction model through cross verification to obtain the pre-trained load prediction model.
4. The method for controlling an ac/dc generator regulator according to claim 1, wherein said transmitting the preprocessed data to a pre-trained load prediction model for comparison and analysis, and obtaining a load prediction result comprises:
capturing a time sequence rule of load change in the preprocessing data through a multi-layer neural network structure to obtain a load change rule;
And calculating the preprocessed data by utilizing the weight and parameters in the pre-trained load prediction model, and combining the load change rule to obtain the load prediction result.
5. An ac/dc generator regulator control method according to claim 1, wherein said generating a preliminary control strategy for said generator based on said load prediction result comprises:
Generating a load trend graph of the next time period based on the load prediction result, and marking and recording mutation points and abnormal fluctuation in the load trend graph of the next time period;
generating a preliminary control strategy of the generator according to the load trend graph in the next time period, wherein the preliminary control strategy of the generator comprises the steps of adjusting the output power of the generator, adjusting the exciting current of the generator and adjusting the frequency output of the generator.
6. An ac/dc generator regulator control method according to claim 1, wherein the constructing a virtual model of the generator using digital twin conditions, simulating states of the generator under different loads and operations by a virtual environment, and optimizing parameters of the preliminary control strategy based on virtual simulation data, generating an optimization strategy of the generator comprises:
establishing a virtual model matched with physical characteristics of the generator, wherein the physical characteristics of the generator comprise electrical parameters, mechanical parameters and thermal parameters;
In a virtual environment, simulating the running states of the generator under different loads and working conditions, recording the influence of load changes on the voltage, current and temperature of the generator, and performing iterative optimization on the parameters of the preliminary control strategy by using a genetic algorithm and a particle swarm optimization algorithm to generate an optimization strategy of the generator.
7. An ac/dc generator regulator control method according to claim 1, characterized in that said ac/dc generator regulator control method further comprises:
Determining the working state of the generator by analyzing the real-time voltage, current, temperature and power of the generator and combining the load prediction result;
and starting a multi-level protection mechanism according to the working state of the generator, and adjusting the operation mode of the generator by using fuzzy logic and an adaptive algorithm.
8. An ac/dc generator regulator control system, the ac/dc generator regulator control system comprising:
The data acquisition module is used for acquiring real-time load data and environment data of the generator, preprocessing the real-time load data and the environment data of the generator according to a filtering and impurity removal algorithm, and acquiring preprocessed data;
The comparison analysis module is used for transmitting the preprocessed data to a pre-trained load prediction model for comparison analysis to obtain a load prediction result;
The preliminary strategy generation module is used for generating a preliminary control strategy of the generator according to the load prediction result;
The optimizing strategy module is used for constructing a virtual model of the generator by utilizing digital twin conditions, simulating states of the generator under different loads and running through a virtual environment, optimizing parameters of the primary control strategy based on virtual simulation data, and generating an optimizing strategy of the generator;
and the adjusting module is used for adjusting the operation parameters of the generator by applying a self-adaptive anti-interference control and fuzzy control algorithm based on the optimization strategy of the generator so as to realize stable and efficient operation.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, carries out the steps of a method for controlling an ac/dc generator regulator according to any one of claims 1 to 7.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of a method for controlling an ac/dc generator regulator according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411957429.XA CN119813852A (en) | 2024-12-30 | 2024-12-30 | AC/DC generator regulator control method, system, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411957429.XA CN119813852A (en) | 2024-12-30 | 2024-12-30 | AC/DC generator regulator control method, system, device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119813852A true CN119813852A (en) | 2025-04-11 |
Family
ID=95274050
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411957429.XA Pending CN119813852A (en) | 2024-12-30 | 2024-12-30 | AC/DC generator regulator control method, system, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119813852A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120410354A (en) * | 2025-07-01 | 2025-08-01 | 中电华瑞技术有限公司 | Electric energy metering and scheduling optimization method and system based on real-time load changes |
-
2024
- 2024-12-30 CN CN202411957429.XA patent/CN119813852A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120410354A (en) * | 2025-07-01 | 2025-08-01 | 中电华瑞技术有限公司 | Electric energy metering and scheduling optimization method and system based on real-time load changes |
| CN120410354B (en) * | 2025-07-01 | 2025-09-30 | 中电华瑞技术有限公司 | Electric energy metering and scheduling optimization method and system based on real-time load changes |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118900275A (en) | Industrial Internet cloud platform based on data intelligence | |
| CN119363495B (en) | Communication equipment optimization method and device based on power management | |
| CN119578923A (en) | A method for optimizing power energy efficiency based on intelligent load management | |
| CN119787513B (en) | Intelligent regulation and control method and system for generator output | |
| CN118249683B (en) | Intelligent excitation control method and system for thermal power units based on autonomous controllable algorithm | |
| CN119813852A (en) | AC/DC generator regulator control method, system, device and medium | |
| CN119628413A (en) | A control method, system, device and storage medium for a switching power supply | |
| CN118336893B (en) | Uninterruptible power supply control method, device and uninterruptible power supply | |
| CN119765380A (en) | A method, system, device and medium for compensating and controlling instantaneous power fluctuations in a power grid | |
| CN119088648A (en) | A circuit board low power sleep mode switching method based on fuzzy logic | |
| CN118316352B (en) | Operation control method, system and storage medium of motor | |
| CN119134278B (en) | Voltage quality compensation method for high-voltage power grid based on passive control strategy | |
| CN112909936B (en) | Monitoring method, device and system for operating state of thermal power unit | |
| CN120033836A (en) | A method and system for controlling intelligent power supply in shelters based on 5G communication | |
| CN118074485B (en) | Control method, control device and switching power supply of surge protection circuit | |
| CN120433272A (en) | Method, device, electronic device and storage medium for optimizing the efficiency of power distribution system | |
| CN118300128A (en) | Frequency modulation control strategy optimization method and system for power grid unit | |
| CN117094478A (en) | Energy scheduling management method, device, equipment and storage medium | |
| CN119401870B (en) | Dynamic control method and system of hydroelectric generator based on environmental changes | |
| CN116488149A (en) | Microgrid power generation strategy determination method, device and microgrid | |
| CN118589693B (en) | Power equipment treatment method, device, terminal and storage medium based on data center | |
| CN119834231B (en) | Distribution switch control method, device, terminal and medium of new energy grid-connected system | |
| CN119628220B (en) | Converter transformer on-load tap changer control system and method | |
| CN120631121B (en) | A cloud computing-based energy-saving control method and system for computer rooms | |
| CN120317769B (en) | Energy management methods, systems, media, and products based on collaboration between AI and energy gateways |
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 |