Alternating current and direct current generator regulator control method, system, equipment and medium

Abstract

The invention relates to an AC / DC generator regulator control method, system and device and a medium, and the method comprises the steps: obtaining the real-time load data and environment data of a generator, carrying out the preprocessing of the real-time load data and environment data of the generator, and obtaining the preprocessed data; transmitting the preprocessed data to a pre-trained load prediction model for comparative 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 using a digital twin condition, simulating states of the generator under different loads and operation, optimizing parameters of the preliminary control strategy based on virtual simulation data, and generating 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. The method has the effect of improving the adjustment precision of the generator.

Description

Technical Field

[0001] The present application relates to the field of power electronic conversion technology, and in particular to an AC / DC generator regulator control method, system, device and medium. Background Art

[0002] In recent years, with the growth of electricity demand and technological advancement, generator technology has developed rapidly. Traditional generator regulators mostly use analog circuit design. Analog regulators use feedback loops composed of resistors, capacitors and other components to achieve voltage regulation. They have the advantages of low cost and simple structure, but weak anti-interference ability, low regulation accuracy, and difficulty in adapting to complex working environments.

[0003] The above-mentioned existing technical solutions have the following defects: the existing generator regulators generally have the problems of low regulation accuracy and slow response speed. Especially when the load changes drastically, it is difficult for traditional regulators to quickly adjust the output voltage, resulting in a decrease in system performance. Therefore, there is room for improvement. Summary of the invention

[0004] In order to improve the regulation accuracy of a generator, the present application provides an AC / DC generator regulator control method, system, device and medium.

[0005] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A method for controlling an AC / DC generator regulator, the method comprising: Acquire real-time load data and environment data of the generator, and preprocess the real-time load data and environment data of the generator according to a filtering and impurity removal algorithm to obtain preprocessed data; The preprocessed data is transmitted to a pre-trained load forecasting model for comparison and analysis to obtain a load forecasting result; generating a preliminary control strategy for the generator according to the load prediction result; Using digital twin conditions to build a virtual model of the generator, simulating the state of the generator under different loads and operations through a virtual environment, and optimizing the parameters of the preliminary control strategy based on virtual simulation data to generate an optimization strategy for the generator; Based on the optimization strategy of the generator, adaptive anti-interference control and fuzzy control algorithms are applied to adjust the operating parameters of the generator to achieve smooth and efficient operation.

[0006] By adopting the above technical solution, the load and environmental data of the generator are obtained in real time, and the filtering and clutter removal algorithm is applied to preprocess the data to effectively remove noise and interference, thereby improving the accuracy and reliability of the data; the preprocessed data is input into the trained load prediction model, and accurate load prediction results are obtained through comparative analysis, which can foresee the future load change trend of the generator in advance, provide a scientific basis for the formulation of control strategies, and improve the response speed and adaptability of the generator; based on the load prediction results, a preliminary control strategy is formulated to ensure that the generator can be effectively adjusted under the predicted load changes, which helps to achieve smooth operation of the generator and avoid unstable operation caused by load fluctuations. Or efficiency decreases; build a virtual model of the generator through digital twin technology, simulate the generator status under different loads and operating conditions in a virtual environment, use virtual simulation data to optimize the parameters of the preliminary control strategy, and generate a more accurate and efficient optimization control strategy, which can be fully tested and adjusted before actual application, reduce the risks in actual operation, and improve the effectiveness and adaptability of the control strategy; adopt adaptive anti-interference control and fuzzy control algorithms, and dynamically adjust the operating parameters of the generator according to the optimized control strategy, which can not only effectively respond to external interference and internal load changes and maintain the stability of the generator operation, but also improve the operating efficiency of the generator and achieve smooth and efficient overall operation.

[0007] In a preferred example, the present application can be further configured as follows: the real-time load data and the environment data of the generator are obtained, and the real-time load data and the environment data of the generator are preprocessed according to a filtering and impurity removal algorithm, and the preprocessed data includes: The Kalman filter algorithm is used to suppress noise and smooth the signal of the real-time load data of the generator to remove high-frequency interference signals and obtain pre-processed load data; The median filtering technology is used to remove abnormal values ​​in the environmental data to obtain pre-processed environmental data; A normalization process is performed to normalize the preprocessed load data and the preprocessed environmental data to obtain the preprocessed data.

[0008] By adopting the above technical solutions, applying Kalman filtering to suppress noise and smooth signals of load data, using median filtering to eliminate outliers in environmental data, and implementing data normalization, the accuracy, reliability and consistency of the data can be significantly improved, providing a solid data foundation for subsequent load prediction, dynamic resource allocation and system optimization, thereby improving the efficient operation capability and resource utilization of the cabinet under multi-task loads.

[0009] In a preferred example, the present application may be further configured as follows: before transmitting the preprocessed data to a pre-trained load prediction model for comparison and analysis to obtain a load prediction result, the AC / DC generator regulator control method further includes: Acquire historical load data and historical environmental parameters, and generate an input feature set by performing feature extraction on the historical load data and the historical environmental parameters; Based on the input feature set, the basic model is trained by combining the long short-term memory network with the neural network model to obtain a load forecasting model; The parameters of the load forecasting model are optimized through cross-validation to obtain the pre-trained load forecasting model.

[0010] By adopting the above technical solution, by extracting features from historical load data and environmental parameters to generate an input feature set, combining long short-term memory networks with neural network models for basic model training, and optimizing model parameters through cross-validation, the accuracy, robustness and generalization ability of the load forecasting model can be significantly improved, ensuring that reliable load forecasting results can be provided under different environmental conditions, thereby optimizing the operation scheduling and resource allocation of generators and improving the overall operation efficiency and stability of the system.

[0011] In a preferred example, the present application may be further configured as follows: the pre-processed data is transmitted to a pre-trained load forecasting model for comparison and analysis, and the load forecasting result obtained includes: Capturing the time series law of load changes in the preprocessed data through a multi-layer neural network structure to obtain the load change law; The preprocessed data is calculated using the weights and parameters within the pre-trained load forecasting model, and combined with the load variation law, the load forecasting result is obtained.

[0012] By adopting the above technical solution, the time series rules of load changes in pre-processed data are captured through a multi-layer neural network structure, and the weights and parameters of the pre-trained load prediction model are combined with the load change rules for calculation. This can significantly improve the accuracy of load prediction and the adaptability of the model, and can more accurately reflect the dynamic change trend of the load, thereby providing more reliable prediction support for the operation scheduling and resource optimization of the generator, and improving the overall efficiency and stability of the system.

[0013] In a preferred example, the present application may be further configured as follows: generating a preliminary control strategy for the generator according to the load prediction result includes: Based on the load forecast result, a load trend graph for the next time period is generated, and mutation points and abnormal fluctuations in the load trend graph for the next time period are marked and recorded; According to the load trend diagram in the next time period, a preliminary control strategy of the generator is generated, and the preliminary control strategy of the generator includes adjusting the output power of the generator, adjusting the excitation current of the generator, and adjusting the frequency output of the generator.

[0014] By adopting the above technical solution, by generating load trend graphs and marking abnormal fluctuations, and formulating preliminary control strategies for generators, the monitoring capabilities and operating efficiency of the power system can be significantly improved, the stability and reliability of the system can be enhanced, and it can be ensured that the generators can respond quickly and accurately to load changes, optimize resource allocation, and improve the operating performance of the overall power system.

[0015] In a preferred example, the present application can be further configured as follows: the virtual model of the generator is constructed using the digital twin condition, the state of the generator under different loads and operations is simulated through a virtual environment, and the parameters of the preliminary control strategy are optimized based on the virtual simulation data, and the optimization strategy of the generator is generated, including: Establishing a virtual model that matches the physical characteristics of the generator, the physical characteristics of the generator including but not limited to electrical parameters, mechanical parameters and thermal parameters; In a virtual environment, the operating state of the generator under different loads and working conditions is simulated, the impact of load changes on the voltage, current and temperature of the generator is recorded, and the parameters of the preliminary control strategy are iteratively optimized using a genetic algorithm and a particle swarm optimization algorithm to generate an optimization strategy for the generator.

[0016] By adopting the above technical solution, by establishing a virtual model that matches the physical characteristics of the generator, simulating the operating status in a virtual environment and optimizing the control strategy using genetic algorithms and particle swarm optimization algorithms, the operating efficiency of the generator and the stability of the system can be significantly improved. The optimized control strategy enables the generator to maintain stable operation under various loads and operating conditions, reduce energy consumption and maintenance costs, and improve the overall performance of the power system.

[0017] In a preferred example, the present application can be further configured as follows: the AC / DC generator regulator control method further includes: Determine the working state of the generator by analyzing the real-time voltage, current, temperature and power of the generator in combination with the load prediction result; According to the working state of the generator, a multi-level protection mechanism is started, and the operation mode of the generator is adjusted by using fuzzy logic and adaptive algorithm.

[0018] By adopting the above technical solutions, by analyzing the real-time voltage, current, temperature and power of the generator, combining the load prediction results, and starting the multi-level protection mechanism and using fuzzy logic and adaptive algorithms to adjust the operation mode, the operating safety and efficiency of the generator are significantly improved, the stability and reliability of the power system are enhanced, and the generator can be ensured to operate efficiently and stably under various loads and working conditions, reduce the risk of failure, and optimize energy utilization.

[0019] The second object of the invention is achieved by the following technical solutions: An AC / DC generator regulator control system, the AC / DC generator regulator control system comprising: A data acquisition module is used to acquire real-time load data of the generator and data of the environment in which the generator is located, and pre-process the real-time load data of the generator and the data of the environment in which the generator is located according to a filtering and impurity removal algorithm to obtain pre-processed data; A comparison and analysis module, used for transmitting the preprocessed data to a pre-trained load forecasting model for comparison and analysis to obtain a load forecasting result; A preliminary strategy generation module is used to generate a preliminary control strategy for the generator according to the load prediction result; An optimization strategy module, used to construct a virtual model of the generator using digital twin conditions, simulate the state of the generator under different loads and operations through a virtual environment, and optimize the parameters of the preliminary control strategy based on virtual simulation data to generate an optimization strategy for the generator; The regulating module is used to adjust the operating parameters of the generator based on the optimization strategy of the generator and apply adaptive anti-interference control and fuzzy control algorithms to achieve smooth and efficient operation.

[0020] By adopting the above technical solution, the load and environmental data of the generator are obtained in real time, and the filtering and clutter removal algorithm is applied to preprocess the data to effectively remove noise and interference, thereby improving the accuracy and reliability of the data; the preprocessed data is input into the trained load prediction model, and accurate load prediction results are obtained through comparative analysis, which can foresee the future load change trend of the generator in advance, provide a scientific basis for the formulation of control strategies, and improve the response speed and adaptability of the generator; based on the load prediction results, a preliminary control strategy is formulated to ensure that the generator can be effectively adjusted under the predicted load changes, which helps to achieve smooth operation of the generator and avoid unstable operation caused by load fluctuations. Or efficiency decreases; build a virtual model of the generator through digital twin technology, simulate the generator status under different loads and operating conditions in a virtual environment, use virtual simulation data to optimize the parameters of the preliminary control strategy, and generate a more accurate and efficient optimization control strategy, which can be fully tested and adjusted before actual application, reduce the risks in actual operation, and improve the effectiveness and adaptability of the control strategy; adopt adaptive anti-interference control and fuzzy control algorithms, and dynamically adjust the operating parameters of the generator according to the optimized control strategy, which can not only effectively respond to external interference and internal load changes and maintain the stability of the generator operation, but also improve the operating efficiency of the generator and achieve smooth and efficient overall operation.

[0021] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned AC / DC generator regulator control method are implemented.

[0022] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned AC / DC generator regulator control method are implemented.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: 1. By acquiring the load and environmental data of the generator in real time and applying filtering and clutter removal algorithms to preprocess the data, noise and interference can be effectively removed to improve the accuracy and reliability of the data; the preprocessed data is input into the trained load prediction model, and accurate load prediction results are obtained through comparative analysis, which can foresee the future load change trend of the generator in advance, provide a scientific basis for the formulation of control strategies, and improve the response speed and adaptability of the generator; based on the load prediction results, a preliminary control strategy is formulated to ensure that the generator can be effectively adjusted under the predicted load changes, which helps to achieve the smooth operation of the generator and avoid unstable operation or reduced efficiency caused by load fluctuations; 2. Build a virtual model of the generator through digital twin technology, simulate the generator status under different loads and operating conditions in a virtual environment, use virtual simulation data to optimize the parameters of the preliminary control strategy, and generate a more accurate and efficient optimization control strategy, which can be fully tested and adjusted before actual application, reduce the risks in actual operation, and improve the effectiveness and adaptability of the control strategy; adopt adaptive anti-interference control and fuzzy control algorithms, and dynamically adjust the operating parameters of the generator according to the optimized control strategy, which can not only effectively respond to external interference and internal load changes and maintain the stability of the generator operation, but also improve the operating efficiency of the generator and achieve smooth and efficient overall operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of a method for controlling an AC / DC generator regulator in one embodiment of the present application; Figure 2 It is a flowchart for implementing step S10 in a method for controlling an AC / DC generator regulator in an embodiment of the present application; Figure 3 is another implementation flow chart of step S20 in a method for controlling an AC / DC generator regulator in one embodiment of the present application; Figure 4 It is a flowchart for implementing step S20 in a method for controlling an AC / DC generator regulator in an embodiment of the present application; Figure 5 It is a flowchart for implementing step S30 in a method for controlling an AC / DC generator regulator in an embodiment of the present application; Figure 6 It is a flowchart for implementing step S40 in a method for controlling an AC / DC generator regulator in an embodiment of the present application; Figure 7 is another implementation flow chart of a method for controlling an AC / DC generator regulator in one embodiment of the present application; Figure 8 This is a principle block diagram of an AC / DC generator regulator control system in an embodiment of the present application; Fig. 9 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The present application is further described in detail below in conjunction with the accompanying drawings.

[0026] In one embodiment, if Figure 1 As shown, the present application discloses a method for controlling an AC / DC generator regulator, which specifically includes the following steps: S10: Acquire real-time load data of the generator and data of the environment in which the generator is located, and preprocess the real-time load data of the generator and data of the environment in which the generator is located according to a filtering and impurity removal algorithm to obtain preprocessed data.

[0027] Specifically, sensors are used to collect key operating data and environmental data of the generator in real time, such as voltage, current, power, temperature, humidity, air pressure, etc. In order to improve data quality, a filtering and impurity removal algorithm is used for preprocessing. For example, assuming that the system detects that the load current data is 5A, 5.1A, 5.4A, 10A, and 5.2A, after applying the median filter, the abnormal value 10A will be filtered out to obtain smoothed current data, thereby ensuring the accuracy of subsequent calculations and finally obtaining preprocessed data.

[0028] S20: The preprocessed data is transmitted to a pre-trained load forecasting model for comparison and analysis to obtain a load forecasting result.

[0029] Specifically, the preprocessed data is transferred to a pre-trained load forecasting model. The model can be trained using a deep learning algorithm (such as an LSTM network). The main purpose is to predict future load change trends based on historical load data and current real-time data. The forecasting model captures the law of load changes through time series characteristics, thereby providing load forecast results for a period of time in the future. For example, under current conditions, the model predicts that the load will increase to 10A in the next 10 minutes. This forecast result can help the control strategy prepare in advance to ensure that the generator can smoothly cope with the upcoming load changes.

[0030] S30: Generate a preliminary control strategy for the generator according to the load prediction result.

[0031] Specifically, the load forecast results are used to generate a preliminary control strategy for the generator. The control strategy includes adjusting the generator's output power, excitation current and frequency to adapt to future load demands. Specifically, if the load forecast model shows that the future load will increase, the control strategy will increase the power output accordingly; if the load decreases, the power output will be reduced to avoid energy waste. For example, if the forecast shows that the future load will increase to 10A, the preliminary control strategy will increase the generator's output power to 12kW and increase the excitation current appropriately to ensure voltage stability.

[0032] S40: Use digital twin conditions to build a virtual model of the generator, simulate the state of the generator under different loads and operations through a virtual environment, and optimize the parameters of the preliminary control strategy based on the virtual simulation data to generate an optimization strategy for the generator.

[0033] Specifically, under the conditions of digital twins, a virtual model is created to accurately reflect the physical characteristics of the generator. Through the virtual model, the operating status of the generator can be simulated under different loads and operating conditions, and the impact of load changes on the generator voltage, current, temperature and other parameters can be observed. The preliminary control strategy is iteratively optimized through genetic algorithms or particle swarm optimization algorithms to obtain a better control strategy so that the generator can operate efficiently, just like simulating the operating conditions when the load increases to 10A in the virtual model, observing the voltage and current fluctuations, and gradually optimizing the preliminary control strategy, and finally generating an optimal strategy to enable the generator to operate with optimal energy efficiency at a load of 10A.

[0034] S50: Based on the optimization strategy of the generator, the operating parameters of the generator are adjusted by applying adaptive anti-interference control and fuzzy control algorithms to achieve smooth and efficient operation.

[0035] Specifically, in the actual operation of the generator, adaptive anti-interference control and fuzzy control algorithms are used to achieve fine-grained regulation. Adaptive anti-interference control can eliminate external interference during operation and maintain stable output. By setting fuzzy rules under different loads and environmental conditions, the generator parameters can be dynamically adjusted. For example, when the actual load reaches 10A, the internal temperature of the generator increases due to a sudden increase in ambient temperature. The fuzzy control detects the temperature change and automatically adjusts the excitation current to ensure stable output voltage. At the same time, the adaptive anti-interference control detects external load fluctuations and further optimizes the control strategy to prevent frequency fluctuations, so that it can maintain stable operation under load fluctuations and adapt to complex load changes.

[0036] By adopting the above technical solution, the load and environmental data of the generator are obtained in real time, and the filtering and clutter removal algorithm is applied to preprocess the data to effectively remove noise and interference, thereby improving the accuracy and reliability of the data; the preprocessed data is input into the trained load prediction model, and accurate load prediction results are obtained through comparative analysis, which can foresee the future load change trend of the generator in advance, provide a scientific basis for the formulation of control strategies, and improve the response speed and adaptability of the generator; based on the load prediction results, a preliminary control strategy is formulated to ensure that the generator can be effectively adjusted under the predicted load changes, which helps to achieve smooth operation of the generator and avoid unstable operation caused by load fluctuations. Or efficiency decreases; build a virtual model of the generator through digital twin technology, simulate the generator status under different loads and operating conditions in a virtual environment, use virtual simulation data to optimize the parameters of the preliminary control strategy, and generate a more accurate and efficient optimization control strategy, which can be fully tested and adjusted before actual application, reduce the risks in actual operation, and improve the effectiveness and adaptability of the control strategy; adopt adaptive anti-interference control and fuzzy control algorithms, and dynamically adjust the operating parameters of the generator according to the optimized control strategy, which can not only effectively respond to external interference and internal load changes and maintain the stability of the generator operation, but also improve the operating efficiency of the generator and achieve smooth and efficient overall operation.

[0037] In one embodiment, if Figure 2 As shown, in step S10, the real-time load data of the generator and the surrounding environment data are obtained, and the real-time load data of the generator and the surrounding environment data are preprocessed according to the filtering and impurity removal algorithm to obtain the preprocessed data, which specifically includes: S11: Apply the Kalman filter algorithm to perform noise suppression and signal smoothing on the real-time load data of the generator to remove high-frequency interference signals and obtain pre-processed load data.

[0038] Specifically, the Kalman filter algorithm is used to suppress noise and smooth signals of the real-time load data of the generator. For the real-time load data of the generator (such as current, voltage, etc.), the Kalman filter can filter out high-frequency interference signals in a noisy environment while retaining the trend information of the data to remove high-frequency interference signals and finally obtain the preprocessed load data.

[0039] S12: Use median filtering technology to remove abnormal values ​​in the environmental data to obtain preprocessed environmental data.

[0040] Specifically, the median filtering technology is used to remove outliers in the environmental data. During the processing, the environmental data within a time window is taken and the median is calculated. The median is used to replace the outliers. That is, a suitable window is selected, the median of the data in the window is calculated, and the median is used to replace the value at the center of the window, thereby smoothing the data stream and obtaining the preprocessed environmental data after processing.

[0041] S13: Perform normalization processing to normalize the preprocessed load data and the preprocessed environmental data to obtain preprocessed data.

[0042] Specifically, normalization processing is implemented to standardize the preprocessed load data and preprocessed environmental data, and the data is scaled to a fixed range, usually [0,1] or [-1,1], so that data from different sources and different dimensions can be compared within a unified range to prevent the accuracy of the model from being affected by different data units. The preprocessed data is obtained after normalization processing.

[0043] In one embodiment, if Figure 3 As shown, in step S20, the pre-processed data is transmitted to a pre-trained load prediction model for comparison and analysis. Before the load prediction result is obtained, the AC / DC generator regulator control method further includes: S201: Acquire historical load data and historical environmental parameters, and generate an input feature set by extracting features from the historical load data and historical environmental parameters.

[0044] Specifically, historical load data and historical environmental parameters of generators in different time periods are collected. These historical data reflect the operating status of generators under different load conditions and the changing patterns affected by the external environment. By extracting features from historical data and using statistical methods, such as calculating the average, maximum, minimum, and standard deviation of load data, or obtaining periodic and trend features through time series analysis, the key features in historical load and environmental data are combined into a feature set. The feature set may include features such as "average load in the last hour" and "temperature change rate in the past day", so as to help the model learn the relationship between load and environment, and finally obtain the input feature set of the prediction model.

[0045] S202: Based on the input feature set, the basic model is trained by combining the long short-term memory network with the neural network model to obtain a load forecasting model.

[0046] Specifically, the generated input feature set is input into the deep learning model for training, and the basic model is trained by combining the long short-term memory network with the neural network model. First, the feature set is input into the LSTM layer, which learns the long-term dependency characteristics of the time series data. Then, the output of the LSTM can be passed to the MLP network for further processing to obtain a richer feature representation. The model is trained by inputting a large amount of historical data to enable it to learn the changing laws of load and environment. In the training process, the back propagation algorithm is used to continuously adjust the weight of the model to reduce the prediction error, and finally the load forecasting model is trained.

[0047] S203: Optimize the parameters of the load forecasting model through cross-validation to obtain a pre-trained load forecasting model.

[0048] Specifically, after the model training is completed, cross-validation is performed to optimize the model parameters. Cross-validation is to divide the data set into several parts, use one part as the test set each time, and the rest as the training set, and repeat the training and validation. During the cross-validation process, the model's hyperparameters are continuously adjusted, such as the number of LSTM layers, the number of neurons, the learning rate, etc., and finally the parameter combination that minimizes the prediction error is selected as the final parameter of the model, and the pre-trained load forecasting model is optimized.

[0049] In one embodiment, if Figure 4 As shown, in step S20, the pre-processed data is transmitted to a pre-trained load forecasting model for comparison and analysis to obtain a load forecasting result, which specifically includes: S21: The time series law of load changes in the preprocessed data is captured through a multi-layer neural network structure to obtain the load change law.

[0050] Specifically, the preprocessed load data is input into the neural network, and the data is organized into a sequence of time steps, such as hourly, daily or weekly load data. The trained multi-layer neural network can extract the time series features in the load data. Suppose we have a set of continuous generator load data (such as current) [8A, 10A, 12A, 11A, 13A, 15A]. Using the multi-layer structure of the LSTM model, the first layer captures short-term changes, such as load fluctuations between every two moments; the second layer further integrates the results of short-term changes and identifies long-term trends, such as the overall increase in load. Through the processing of multi-layer LSTM, the model will "learn" the increasing characteristics of the load at different times, and finally generate a representation of the load change law.

[0051] S22: Calculate the preprocessed data using the weights and parameters within the pre-trained load forecasting model, and obtain the load forecasting result in combination with the load variation law.

[0052] Specifically, the preprocessed load data and environmental data are input in the format required by the model, such as tensor shape, batch size, etc. Through the forward propagation process of the model, the input data is calculated using the loaded weights and parameters to obtain preliminary load forecasting results. The load change law extracted in the first step is combined with the output of the pre-trained model, such as fusing the time series features with the intermediate layer output or final output of the model as the input for the final prediction, or adjusting the prediction results according to the load change law, such as using the weighted average method to combine the outputs of the two, and finally generating a load prediction result.

[0053] In one embodiment, if Figure 5 As shown, in step S30, a preliminary control strategy of the generator is generated according to the load prediction result, which specifically includes: S31: Based on the load prediction result, a load trend graph for the next time period is generated, and mutation points and abnormal fluctuations in the load trend graph for the next time period are marked and recorded.

[0054] Specifically, the load forecasting model is used to obtain the load forecast results for a period of time in the future, such as the next few minutes or hours. These data points are plotted into a trend graph to intuitively display the load changes, and the mutation points and abnormal fluctuations of the load changes are marked in the trend graph, such as the points where the load suddenly rises or falls and the changes are larger than the normal fluctuation range. These points are usually the key nodes of the load adjustment strategy. For example, after drawing the trend graph, it is found that the load gradually increases to a peak value of 25A in the first 30 minutes, and then the load gradually decreases in the next 30 minutes. At this time, the point where the load quickly rises to 25A and the subsequent decrease point can be marked as mutation points.

[0055] S32: Generate a preliminary control strategy for the generator according to the load trend diagram in the next time period. The preliminary control strategy for the generator includes adjusting the output power of the generator, adjusting the excitation current of the generator, and adjusting the frequency output of the generator.

[0056] Specifically, based on the load trend chart in the next time period, a preliminary control strategy for the generator is generated. For example, when the load is predicted to increase, the power output of the generator is increased; when the load is predicted to decrease, the power output is reduced to avoid energy waste; when the load increases, the excitation current is appropriately increased to maintain voltage stability; when the load decreases, the excitation current is reduced to prevent excessive voltage; when the load suddenly changes or fluctuates abnormally, the frequency output of the generator can be appropriately adjusted to stabilize the frequency of the power generation system and ensure the quality of the output power.

[0057] In one embodiment, if Figure 6As shown, in step S40, a virtual model of the generator is constructed using digital twin conditions, the state of the generator under different loads and operations is simulated through a virtual environment, and the parameters of the preliminary control strategy are optimized based on the virtual simulation data to generate an optimization strategy for the generator, which specifically includes: S41: Establishing a virtual model that matches the physical characteristics of the generator, where the physical characteristics of the generator include but are not limited to electrical parameters, mechanical parameters, and thermal parameters.

[0058] Specifically, select suitable simulation software, such as MATLAB / Simulink, ANSYS, PSS / E, etc., to establish a virtual model of the generator, and establish a virtual model that matches the physical characteristics of the generator. The physical characteristics of the generator include but are not limited to electrical parameters, mechanical parameters and thermal parameters. By comparing with the actual generator operation data, adjust the model parameters to ensure that the virtual model can accurately reflect the physical characteristics of the generator, and perform multiple simulation tests to verify the accuracy and stability of the model under different operating conditions.

[0059] S42: In a virtual environment, simulate the operating status of the generator under different loads and working conditions, record the impact of load changes on the voltage, current and temperature of the generator, and use genetic algorithm and particle swarm optimization algorithm to iteratively optimize the parameters of the preliminary control strategy to generate the optimization strategy of the generator.

[0060] Specifically, in a virtual environment, the operating status of the generator under various conditions is simulated by adjusting the load and operating conditions. For example, different load curves can be set to observe the changes in the voltage, current, and temperature of the generator when the load changes, and record the impact of the load change on the electrical and thermal parameters of the virtual generator. For example, as the load increases, the current may increase and the temperature will also rise accordingly. The changing trends of these parameters are analyzed to find possible limit values ​​and abnormal conditions. The optimization results of the genetic algorithm and the particle swarm optimization algorithm are combined to determine the optimal control parameters and generate the final generator optimization control strategy.

[0061] In one embodiment, if Figure 7 As shown, the AC / DC generator regulator control method also includes: S60: Determine 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.

[0062] Specifically, in actual operation, the voltage, current, temperature, power and other parameters of the generator are monitored in real time. According to the real-time parameters, the working status is divided into different levels. For example, a current less than 20A is light load, 20A-40A is normal load, and more than 40A is heavy load; a temperature below 60°C is normal, and above 70°C is overheating, etc., and combined with the load prediction results, the current working status of the generator is determined, such as light load, heavy load, overload, etc.

[0063] S70: According to the working state of the generator, a multi-level protection mechanism is started, and the operation mode of the generator is adjusted using fuzzy logic and adaptive algorithms.

[0064] Specifically, different protection mechanisms are activated in stages according to the real-time status of the generator. For example, when the generator is slightly overloaded, a low-level protection mechanism is activated, such as power reduction operation; when the generator is severely overloaded, a high-level protection mechanism is activated, such as output cutoff or load limitation. Through fuzzy logic and adaptive algorithms, appropriate operating modes are selected according to different status levels, such as stable mode, energy-saving mode, emergency mode, etc., to achieve flexible control.

[0065] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0066] In one embodiment, an AC / DC generator regulator control system is provided, and the AC / DC generator regulator control system corresponds one-to-one to an AC / DC generator regulator control method in the above embodiment. Figure 8 As shown, the AC / DC generator regulator control system includes a data acquisition module, a comparison and analysis module, a preliminary strategy generation module, an optimization strategy module and a regulation module. The detailed description of each functional module is as follows: A data acquisition module is used to acquire real-time load data of the generator and the data of the environment in which it is located, and pre-process the real-time load data of the generator and the data of the environment in which it is located according to a filtering and impurity removal algorithm to obtain pre-processed data; A comparison and analysis module is used to transmit the pre-processed data to a pre-trained load forecasting model for comparison and analysis to obtain a load forecasting result; A preliminary strategy generation module is used to generate a preliminary control strategy of the generator according to the load prediction result; The optimization strategy module is used to build a virtual model of the generator using digital twin conditions, simulate the status of the generator under different loads and operations through a virtual environment, and optimize the parameters of the preliminary control strategy based on the virtual simulation data to generate an optimization strategy for the generator; The regulation module is used to adjust the operating parameters of the generator based on the optimization strategy of the generator and apply adaptive anti-interference control and fuzzy control algorithms to achieve smooth and efficient operation.

[0067] Optionally, the data acquisition module includes: The load filtering submodule is used to apply the Kalman filtering algorithm to perform noise suppression and signal smoothing on the real-time load data of the generator to remove high-frequency interference signals and obtain pre-processed load data; The environmental filtering submodule is used to remove abnormal values ​​in the environmental data using the median filtering technology to obtain pre-processed environmental data; The normalization submodule is used to implement normalization processing, standardize the preprocessed load data and the preprocessed environmental data to obtain preprocessed data.

[0068] Optionally, the AC / DC generator regulator control system further includes: A historical data acquisition module is used to acquire historical load data and historical environmental parameters, and to generate an input feature set by extracting features from the historical load data and historical environmental parameters; The model training module is used to train the basic model based on the input feature set by combining the long short-term memory network with the neural network model to obtain the load forecasting model; The model validation module is used to optimize the parameters of the load forecasting model through cross-validation to obtain a pre-trained load forecasting model.

[0069] The real-time monitoring module is used to determine the working status of the generator by analyzing the real-time voltage, current, temperature and power of the generator and combining the load prediction results; The protection and regulation module is used to start the multi-level protection mechanism according to the working status of the generator, and adjust the operation mode of the generator by using fuzzy logic and adaptive algorithm.

[0070] Optional comparison analysis modules include: The load change acquisition submodule is used to capture the time series law of load changes in the preprocessed data through a multi-layer neural network structure to obtain the load change law; The calculation submodule is used to calculate the preprocessed data using the weights and parameters within the pre-trained load forecasting model, and obtain the load forecasting result in combination with the load change law.

[0071] Optionally, generating a preliminary strategy module includes: A trend chart generation submodule is used to generate a load trend chart for the next time period based on the load forecast results, and to mark and record the mutation points and abnormal fluctuations in the load trend chart for the next time period; A preliminary strategy submodule is obtained, which is used to generate a preliminary control strategy for the generator according to a load trend diagram in the next time period. The preliminary control strategy for the generator includes adjusting the output power of the generator, adjusting the excitation current of the generator, and adjusting the frequency output of the generator.

[0072] Optionally, the optimization strategy module includes: A virtual construction submodule, used to establish a virtual model that matches the physical characteristics of the generator, the physical characteristics of the generator including but not limited to electrical parameters, mechanical parameters and thermal parameters; The strategy optimization submodule is used to simulate the operating status of the generator under different loads and working conditions in a virtual environment, record the impact of load changes on the voltage, current and temperature of the generator, and iteratively optimize the parameters of the preliminary control strategy using genetic algorithms and particle swarm optimization algorithms to generate the optimization strategy of the generator.

[0073] For the specific definition of an AC / DC generator regulator control system, please refer to the definition of an AC / DC generator regulator control method mentioned above, which will not be repeated here. Each module in the above-mentioned AC / DC generator regulator control system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0074] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for controlling an AC / DC generator regulator is implemented.

[0075] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Acquire the real-time load data and the environment data of the generator, and pre-process the real-time load data and the environment data of the generator according to the filtering and impurity removal algorithm to obtain the pre-processed data; The preprocessed data is transmitted to the pre-trained load forecasting model for comparison and analysis to obtain the load forecasting result; Generate a preliminary control strategy for the generator based on the load forecast results; Use digital twin conditions to build a virtual model of the generator, simulate the generator's state under different loads and operations through a virtual environment, and optimize 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, the adaptive anti-interference control and fuzzy control algorithms are used to adjust the operating parameters of the generator to achieve smooth and efficient operation. In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Acquire the real-time load data and the environment data of the generator, and pre-process the real-time load data and the environment data of the generator according to the filtering and impurity removal algorithm to obtain the pre-processed data; The preprocessed data is transmitted to the pre-trained load forecasting model for comparison and analysis to obtain the load forecasting result; Generate a preliminary control strategy for the generator based on the load forecast results; Use digital twin conditions to build a virtual model of the generator, simulate the generator's state under different loads and operations through a virtual environment, and optimize 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, the adaptive anti-interference control and fuzzy control algorithms are used to adjust the operating parameters of the generator to achieve smooth and efficient operation. Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many 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).

[0076] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0077] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for controlling an AC / DC generator regulator, characterized in that: The AC / DC generator regulator control method comprises: Acquire real-time load data and environment data of the generator, and preprocess the real-time load data and environment data of the generator according to a filtering and impurity removal algorithm to obtain preprocessed data; The preprocessed data is transmitted to a pre-trained load forecasting model for comparison and analysis to obtain a load forecasting result; generating a preliminary control strategy for the generator according to the load prediction result; Using digital twin conditions to build a virtual model of the generator, simulating the state of the generator under different loads and operations through a virtual environment, and optimizing the parameters of the preliminary control strategy based on virtual simulation data to generate an optimization strategy for the generator; Based on the optimization strategy of the generator, adaptive anti-interference control and fuzzy control algorithms are applied to adjust the operating parameters of the generator to achieve smooth and efficient operation.

2. The AC / DC generator regulator control method according to claim 1, characterized in that: The real-time load data and the environment data of the generator are obtained, and the real-time load data and the environment data of the generator are preprocessed according to a filtering and impurity removal algorithm to obtain the preprocessed data, including: The Kalman filter algorithm is used to suppress noise and smooth the signal of the real-time load data of the generator to remove high-frequency interference signals and obtain pre-processed load data; The median filtering technology is used to remove abnormal values ​​in the environmental data to obtain pre-processed environmental data; A normalization process is performed to normalize the preprocessed load data and the preprocessed environmental data to obtain the preprocessed data.

3. The AC / DC generator regulator control method according to claim 1, characterized in that: Before transmitting the preprocessed data to a pre-trained load prediction model for comparison and analysis to obtain a load prediction result, the AC / DC generator regulator control method further includes: Acquire historical load data and historical environmental parameters, and generate an input feature set by performing feature extraction on the historical load data and the historical environmental parameters; Based on the input feature set, the basic model is trained by combining the long short-term memory network with the neural network model to obtain a load forecasting model; The parameters of the load forecasting model are optimized through cross-validation to obtain the pre-trained load forecasting model.

4. The AC / DC generator regulator control method according to claim 1, characterized in that: The pre-processed data is transmitted to a pre-trained load forecasting model for comparison and analysis to obtain a load forecasting result, which includes: Capturing the time series law of load changes in the preprocessed data through a multi-layer neural network structure to obtain the load change law; The preprocessed data is calculated using the weights and parameters within the pre-trained load forecasting model, and combined with the load variation law, the load forecasting result is obtained.

5. The AC / DC generator regulator control method according to claim 1, characterized in that: Generating a preliminary control strategy for the generator according to the load prediction result includes: Based on the load forecast result, a load trend graph for the next time period is generated, and mutation points and abnormal fluctuations in the load trend graph for the next time period are marked and recorded; According to the load trend diagram in the next time period, a preliminary control strategy of the generator is generated, and the preliminary control strategy of the generator includes adjusting the output power of the generator, adjusting the excitation current of the generator, and adjusting the frequency output of the generator.

6. The AC / DC generator regulator control method according to claim 1, characterized in that: The virtual model of the generator is constructed by using the digital twin condition, the state of the generator under different loads and operations is simulated through a virtual environment, and the parameters of the preliminary control strategy are optimized based on the virtual simulation data to generate the optimization strategy of the generator, including: Establishing a virtual model that matches the physical characteristics of the generator, the physical characteristics of the generator including but not limited to electrical parameters, mechanical parameters and thermal parameters; In a virtual environment, the operating state of the generator under different loads and working conditions is simulated, the impact of load changes on the voltage, current and temperature of the generator is recorded, and the parameters of the preliminary control strategy are iteratively optimized using a genetic algorithm and a particle swarm optimization algorithm to generate an optimization strategy for the generator.

7. The AC / DC generator regulator control method according to claim 1, characterized in that: The AC / DC generator regulator control method further includes: Determine the working state of the generator by analyzing the real-time voltage, current, temperature and power of the generator in combination with the load prediction result; According to the working state of the generator, a multi-level protection mechanism is started, and the operation mode of the generator is adjusted by using fuzzy logic and adaptive algorithm.

8. An AC / DC generator regulator control system, characterized in that: The AC / DC generator regulator control system comprises: A data acquisition module is used to acquire real-time load data of the generator and data of the environment in which the generator is located, and pre-process the real-time load data of the generator and the data of the environment in which the generator is located according to a filtering and impurity removal algorithm to obtain pre-processed data; A comparison and analysis module, used for transmitting the preprocessed data to a pre-trained load forecasting model for comparison and analysis to obtain a load forecasting result; A preliminary strategy generation module is used to generate a preliminary control strategy for the generator according to the load prediction result; An optimization strategy module, used to construct a virtual model of the generator using digital twin conditions, simulate the state of the generator under different loads and operations through a virtual environment, and optimize the parameters of the preliminary control strategy based on virtual simulation data to generate an optimization strategy for the generator; The regulating module is used to adjust the operating parameters of the generator based on the optimization strategy of the generator and apply adaptive anti-interference control and fuzzy control algorithms to achieve smooth 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: When the processor executes the computer program, the steps of the AC / DC generator regulator control method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the AC / DC generator regulator control method as claimed in any one of claims 1 to 7 are implemented.

Images