Intelligent control method and system based on pole-mounted circuit breaker equipment

Abstract

The invention discloses an intelligent control method and system based on pole-mounted circuit breaker equipment, and relates to the technical field of power grid control, and the method comprises the steps: collecting environmental data of a pole-mounted circuit breaker, employing a Kalman filtering fusion algorithm, outputting a fusion state vector, constructing time series data, employing a photon to calculate an accelerated time series neural network, and obtaining a time series neural network model; and performing complex field mapping and optical phase shift modulation on the extracted features, and predicting a future current value. According to the method, complex field mapping is carried out on features extracted by a time convolution layer, the expression ability of nonlinear features is enhanced, optical phase shift modulation is introduced, phase and amplitude information is further adjusted, the nonlinear modeling ability of time sequence features is improved, and multi-modal data fusion and multi-scale consistency verification of fractal dimensions are combined, so that the time sequence features of the fractal dimension are optimized. Time scale deviation of different data sources is eliminated, and effectiveness and consistency of multi-dimensional feature fusion are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid control, and in particular to an intelligent control method and system based on a pole-mounted circuit breaker device. Background Art

[0002] With the rapid development of power systems, the automation and intelligence of distribution networks have become an important development direction for power grid operation and management. Pole-mounted circuit breakers, as key equipment in distribution networks, are widely used in fault isolation, load control and power protection of medium-voltage distribution systems. Traditional control methods of pole-mounted circuit breakers mainly rely on timed inspections, overcurrent protection and simple remote control, which play a certain role in ensuring the stability of the power grid.

[0003] However, due to the limitations of traditional technical means, the control method of pole-mounted circuit breakers has poor adaptability to complex environmental changes and short-term current disturbances, and it is difficult to meet the needs of modern smart grids for efficient, accurate, and intelligent circuit breaker control. The current prediction methods of traditional circuit breakers are mostly based on simple timing analysis or empirical models, which are difficult to accurately predict future short-term current fluctuations, resulting in a high false triggering rate, affecting power supply stability. Secondly, the existing technology lacks in-depth analysis of current fractal characteristics and cannot accurately characterize the nonlinear characteristics of current fluctuations, which in turn affects the accuracy of circuit breaker control strategies. Moreover, although there are optimization strategies based on machine learning, most methods rely on fixed rules or historical data training, and cannot dynamically adjust the control strategy according to real-time environmental changes, resulting in poor system adaptability. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent control method based on a pole-mounted circuit breaker device to solve the problem that most current prediction methods of traditional circuit breakers are based on simple timing analysis or empirical models, which make it difficult to accurately predict future short-term current fluctuations, resulting in a high false triggering rate and affecting power supply stability. Secondly, the existing technology lacks in-depth analysis of current fractal characteristics and cannot accurately characterize the nonlinear characteristics of current fluctuations, thereby affecting the accuracy of the circuit breaker control strategy. Furthermore, although there are optimization strategies based on machine learning, most methods rely on fixed rules or historical data training, and cannot dynamically adjust the control strategy according to real-time environmental changes, resulting in poor system adaptability.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an intelligent control method based on a pole-mounted circuit breaker device, comprising:

[0008] Collect the environmental data of the pole-mounted circuit breaker, use the Kalman filter fusion algorithm to output the fusion state vector, and construct the time series data. Use the time series neural network accelerated by photon computing to map the extracted features into the complex domain and perform optical phase shift modulation to predict the future current value;

[0009] The predicted current time series is divided into multiple scales, the current fractal dimension is calculated, the nonlinear perturbation model of current fluctuation is established using the fractal Brownian motion algorithm to calculate the current fluctuation value, and the fractal dimension is verified by linear regression calculation for consistency verification, the adjustment factor is calculated and the predicted value is corrected;

[0010] Calculate the current trend correction factor, dimensional anomaly index and magnetic field disturbance index, determine the optimal strategy and calculate the short-term disturbance value through the reinforcement learning algorithm, and perform decision delay verification;

[0011] Monitor circuit breaker status data, calculate thermal anomaly index and issue early warning, analyze current stability value, and perform closing operations.

[0012] As a preferred solution of the intelligent control method based on the pole-mounted circuit breaker device of the present invention, wherein: the collecting of the pole-mounted circuit breaker environmental data, using the Kalman filter fusion algorithm, and outputting the fusion state vector refers to collecting environmental data based on the pole-mounted circuit breaker device through sensors, including temperature data, humidity data, current data and leakage current data;

[0013] The collected environmental data are synchronized using linear interpolation and denoised using adaptive Wiener filtering;

[0014] Using the Kalman filter fusion algorithm, the current state is predicted and the covariance is predicted for the environmental vector composed of environmental data, the Kalman gain is calculated, the state vector is corrected using the measurement data and the covariance matrix is ​​updated, the fused state vector is output, and time series data is constructed;

[0015] The time series neural network accelerated by photon computing is used to build a time series model, including input layer, time convolution layer, photon computing layer and output layer;

[0016] The input layer inputs the normalized fusion state vector data. The temporal convolution layer uses the temporal convolution network (TCN) to extract the time series features. The features extracted by the temporal convolution layer are mapped to the complex domain and optical phase shift modulation is performed. The photon calculation layer is used to finally predict the future current value.

[0017] Use the calibrated training set to train the model, select the cross entropy loss function to calculate the computational loss between the model's predicted output and the actual label, use the chain rule to calculate the loss, perform backpropagation calculations on the gradients of each layer's parameters, use the Adam optimizer to update the parameters, and stop updating if the model's loss no longer decreases significantly during the continuous update process, and output the model parameters;

[0018] Use the newly acquired data to make current data forecasts using a time series model.

[0019] As a preferred solution of the intelligent control method based on the pole-mounted circuit breaker device of the present invention, wherein: the multi-scale division of the predicted current time series and the calculation of the current fractal dimension refer to fractal dimension correction FDA of the predicted current data, forming the predicted current data into sequence data, and setting the scale parameter ;

[0020] Through the multi-scale Box-Counting algorithm at each scale Under this condition, the predicted current time series is gridded, the number of intervals covering the entire current series is counted, the number of scale intervals is calculated according to the box counting method, and the current fractal dimension is calculated by linear regression fitting;

[0021] The current fractal dimension data is counted and the sum of the mean and the standard deviation is calculated as the fractal threshold, and the minimum threshold limit value is determined based on historical data. The maximum value of the minimum threshold limit value and the fractal threshold is used as the dimension threshold. If the calculated current fractal dimension is greater than or equal to the dimension threshold, it is determined that correction is required;

[0022] The fractal Brownian motion algorithm fBM is used to establish a nonlinear perturbation model of current fluctuation, and the current fluctuation value is determined by the Hurst index and disturbance amplitude of the current fluctuation. ;

[0023] Based on current fluctuation value To verify, the multi-scale Box-Counting algorithm is used according to the scale parameter right Perform multi-scale segmentation, calculate the box technique, and calculate the corresponding verification fractal dimension through linear regression ;

[0024] Will verify the fractal dimension and The difference is verified, and the minimum value is determined as the verification threshold based on historical data. If the fractal difference is less than the verification threshold, it means Maintain consistency at multiple scales and pass verification;

[0025] Based on verified Set adjustment factors and revise the forecast values ​​based on the adjustment factors.

[0026] As a preferred solution of the intelligent control method based on the pole-mounted circuit breaker device of the present invention, wherein: the current trend correction factor, the dimension anomaly index and the magnetic field disturbance index are calculated, the optimal strategy is determined by the reinforcement learning algorithm, and the current trend correction factor is defined based on the relative change rate between the corrected current prediction value and the over-prediction value;

[0027] Based on the current fractal dimension and fractal dimension mean The difference between the two determines the dimension anomaly index ;

[0028] Determine the magnetic induction intensity based on finite element simulation FEM, calculate the electromagnetic torque of the circuit breaker at the current time t, and calculate the relative change rate of the electromagnetic torque at different times as the magnetic field disturbance index;

[0029] Use the curriculum learning mechanism to dynamically adjust the difficulty of reinforcement learning tasks based on the current trend correction factor, dimensional anomaly index, and magnetic field disturbance index, and determine the task complexity ;

[0030] based on Q-learning updates performed by the reinforcement learning algorithm as a reward correction term, and dynamically adjust the learning rate;

[0031] The state space is composed of current prediction value, current fractal dimension, magnetic field disturbance index and task complexity, and the action space is composed of the adjustment, closing and maintaining state of the circuit breaker. The Q value table is updated through Q-learning, including the corresponding Q values ​​of different state spaces and action spaces, and the optimal strategy is obtained to determine the state of the circuit breaker under different states.

[0032] As a preferred solution of the intelligent control method based on the pole-mounted circuit breaker device of the present invention, wherein: the short-term disturbance value is calculated, the decision delay verification is performed, and the short-term disturbance is calculated based on the optimal strategy, wherein the disturbance time window is defined and the short-term disturbance is calculated according to the difference of the corrected predicted value;

[0033] The sum of the historical mean and double standard deviation of the short-term disturbance index is used as the delay threshold. If the short-term disturbance index is less than or equal to the delay threshold, it is judged as no delay and the optimal strategy is directly executed. If the short-term disturbance index is greater than the delay threshold, the decision is delayed.

[0034] A time delay is performed based on the decision delay value and the Q value table is updated again through Q-learning to determine the optimal strategy after the delay.

[0035] As a preferred solution of the intelligent control method based on the pole-mounted circuit breaker device of the present invention, wherein: the circuit breaker status data is monitored, the thermal anomaly index is calculated and an early warning is issued, the action implementation based on the optimal strategy is performed, the circuit breaker status data is monitored, the circuit breaker temperature data is collected and the thermal anomaly index is calculated according to the difference between the ambient temperature and the collected temperature;

[0036] Based on the sum of the rated temperature of the circuit breaker and the allowable temperature rise value of the circuit breaker as the temperature threshold, if the thermal anomaly index is greater than or equal to the temperature threshold, the circuit breaker temperature is judged to be abnormal, and an alarm is issued through the early warning device.

[0037] As a preferred solution of the intelligent control method based on the pole-mounted circuit breaker equipment described in the present invention, wherein: the analysis of the current stability value and the closing operation refers to the implementation of the action based on the optimal strategy. If the circuit breaker is in the off state, the mean of the corrected current prediction value in the acquisition window is used as the current stability value, and the sum of the mean and standard deviation of the current stability is used as the current threshold. If the current stability value is less than the current threshold, it is determined that the closing conditions are met and the closing operation is performed.

[0038] In a second aspect, the present invention provides a system based on an intelligent control method of a pole-mounted circuit breaker device, comprising:

[0039] The data acquisition and processing module collects environmental data of the pole-mounted circuit breaker and performs time synchronization and noise reduction on the multi-modal data;

[0040] The time series construction module uses the Kalman filter algorithm to fuse multimodal environmental data and construct multidimensional time series data based on the fused state vector;

[0041] The time series neural network module uses the TCN network accelerated by photon computing to extract multi-scale time series features from the time series of the fusion state vector;

[0042] The nonlinear correction module calculates the current fractal dimension of the predicted current time series and verifies its consistency. Based on the adjustment factor calculated by the fractal dimension, the nonlinear correction is performed on the current prediction value.

[0043] The reinforcement learning adaptive control module calculates the current trend correction factor, dimension anomaly index and magnetic field disturbance index, dynamically adjusts the complexity of the reinforcement learning task, updates the Q value table through Q-learning, dynamically calculates the optimal strategy and performs decision delay verification;

[0044] The intelligent early warning module collects circuit breaker status data for status monitoring and fault early warning.

[0045] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the intelligent control method based on the pole-mounted circuit breaker device as described in the first aspect of the present invention is implemented.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the intelligent control method based on a pole-mounted circuit breaker device as described in the first aspect of the present invention is implemented.

[0047] The beneficial effects of the present invention are as follows: by mapping the features extracted by the time convolution layer into the complex domain, the expression ability of nonlinear features is enhanced; the introduction of optical phase shift modulation further adjusts the phase and amplitude information, and improves the nonlinear modeling ability of time series features; by combining multimodal data fusion with multi-scale consistency verification of fractal dimensions, the time scale deviation of different data sources is eliminated, and the effectiveness and consistency of multi-dimensional feature fusion are improved; by combining the phase adjustment of optical phase shift modulation with the multi-scale self-similarity of fractal dimensions, the nonlinear characteristics of current fluctuations at different frequencies and amplitudes can be fully captured; the nonlinear correction mechanism of the adjustment factor is combined with the efficient calculation of photon calculation, which significantly improves the correction speed and accuracy of the predicted value; the current fluctuation trend and amplitude are dynamically captured by the current trend correction factor; the nonlinear fluctuation and abnormal fluctuation are accurately detected by the dimensional anomaly index of the current fractal dimension, thereby ensuring the safety of the power grid and the stable operation of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0049] Figure 1 This is a flow chart of the intelligent control method based on the pole-mounted circuit breaker device in Example 1.

[0050] Figure 2 This is a schematic diagram of the structure of the intelligent control system based on the pole-mounted circuit breaker device in Example 2. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0054] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides an intelligent control method based on a pole-mounted circuit breaker device, comprising the following steps:

[0055] S1, collects the environmental data of the pole-mounted circuit breaker, uses the Kalman filter fusion algorithm to output the fusion state vector, and constructs the time series data. The time series neural network accelerated by photon computing is used to map the extracted features into the complex domain and perform optical phase shift modulation to predict the future current value;

[0056] Preferably, the environmental data of the pole-mounted circuit breaker is collected, and the Kalman filter fusion algorithm is used to output the fusion state vector, and the time series data is constructed. The time series neural network accelerated by photon computing is used to map the extracted features into the complex domain and perform optical phase shift modulation to predict the future current value. The environmental data is collected based on the pole-mounted circuit breaker equipment through sensors, including temperature data, humidity data, current data and leakage current data;

[0057] The collected environmental data are synchronized using linear interpolation and denoised using adaptive Wiener filtering;

[0058] Using the Kalman filter fusion algorithm, the current state prediction and covariance prediction are performed for the environmental vector composed of environmental data, which is expressed as:

[0059] ;

[0060] ;

[0061] in represents the predicted current state vector at time t+1, represents the state transfer matrix, which represents the transition relationship of the system from time t to time t+1, and is learned based on historical data. Represents the predicted current state vector at time t, which includes the collected temperature data, humidity data, current data, leakage current data, and historical fault data. Represents the control input matrix, including the impact of temperature and humidity changes on current and leakage current, and the impact of current changes on the thermal load of the circuit breaker. represents the control input vector, including the temperature change, humidity change, current change and leakage current change in the environmental data, represents the predicted covariance matrix at time t+1, represents the covariance matrix at time t, represents the process noise covariance matrix, represents the uncertainty of state transition, Represents the transpose calculation of the state transfer matrix;

[0062] Calculate the Kalman gain, use the measurement data to correct the state vector and update the covariance matrix, output the fused state vector, and construct the time series data;

[0063] The time series neural network accelerated by photon computing is used to build a time series model, including input layer, time convolution layer, photon computing layer and output layer;

[0064] The input layer inputs the normalized fusion state vector data, and the temporal convolution layer uses the temporal convolution network TCN to extract the time series features, which can be expressed as:

[0065] ;

[0066] in represents the convolution output of the i-th neuron, M represents the time window size, represents the fusion state vector at the past time point t−j, represents the convolution weight;

[0067] The features extracted by the temporal convolution layer are mapped to the complex domain and optical phase shift modulation is performed, which can be expressed as:

[0068] ;

[0069] ;

[0070] ;

[0071] in represents the input data of the ith neuron after optical phase shift modulation, represents the i-th phase shift angle The optical phase shift factor, represents the phase shift adjustment coefficient, u represents the imaginary unit, and satisfies ;

[0072] Perform photon calculation layer calculations to make a final prediction of future current values, expressed as:

[0073] ;

[0074] ;

[0075] in represents the output of the i-th neuron photon computing layer, N represents the number of neurons in the hidden layer of the neural network, represents the current prediction at time t+Δt, represents the full connection weight, b represents the bias term, represents the photon calculation weight;

[0076] Use the calibrated training set to train the model, select the cross entropy loss function to calculate the computational loss between the model's predicted output and the actual label, use the chain rule to calculate the loss, perform backpropagation calculations on the gradients of each layer's parameters, use the Adam optimizer to update the parameters, and stop updating if the model's loss no longer decreases significantly during the continuous update process, and output the model parameters;

[0077] Use the newly acquired data to make current data forecasts using a time series model.

[0078] Through multi-modal environmental data collection, the environmental factors that affect current fluctuations are fully covered, making the predicted values ​​closer to the actual scenarios and environmental conditions. Through data synchronization and adaptive noise reduction, the effectiveness of multi-dimensional feature fusion is improved.

[0079] Through the Kalman filter fusion algorithm, the uncertainty in the state transfer process is quantified, and the interference of noise on state prediction and covariance estimation is reduced. Through the time series neural network accelerated by photon computing, photon computing transmits data at the speed of light in convolution calculation, realizing ultra-high bandwidth and ultra-low latency convolution operations, and parallel calculation of multiple convolution kernels and time windows, significantly accelerating time convolution operations and feature extraction. Through the long-dependency modeling capability of the time convolution network, the periodicity and trend of current data in long time series can be captured. The combination of convolution kernel sharing and photon computing acceleration improves the accuracy and stability of time series feature extraction.

[0080] The features extracted by the time convolution layer are mapped to the complex domain, and the timing features are converted into complex form, thereby enhancing the expression ability of nonlinear features. The introduction of optical phase shift modulation further adjusts the phase and amplitude information, and improves the nonlinear modeling ability of timing features. The phase modulation and interference principles of photon computing are used to perform matrix operations and complex convolutions in the complex domain while retaining the amplitude and phase information to achieve accurate modeling of nonlinear and periodic fluctuation characteristics. Through the high parallelism and low latency of photon computing, the ability to cope with the dynamic changes of power grid load fluctuations and environmental disturbances is improved, thereby improving the effectiveness of predicting future current values.

[0081] S2, divide the predicted current time series into multiple scales, calculate the current fractal dimension, use the fractal Brownian motion algorithm to establish a nonlinear perturbation model of current fluctuation to calculate the current fluctuation value, and verify the fractal dimension through linear regression calculation to verify the consistency, calculate the adjustment factor and correct the predicted value;

[0082] Preferably, the predicted current time series is divided into multiple scales, the current fractal dimension is calculated, the nonlinear perturbation model of current fluctuation is established using the fractal Brownian motion algorithm to calculate the current fluctuation value, and the fractal dimension is verified by linear regression calculation for consistency verification, the adjustment factor is calculated and the predicted value is corrected, the fractal dimension of the predicted current data is corrected FDA, the predicted current data is composed of sequence data, and the scale parameter is set , set to , and m is determined according to historical data, and the multi-scale Box-Counting algorithm is used at each scale Under this condition, the predicted current time series is gridded, the number of intervals covering the entire current series is counted, and the current fractal dimension is calculated according to the box counting method, which is expressed as:

[0083] ;

[0084] in represents the fractal dimension of the current, Representation scale The number of intervals below;

[0085] The current fractal dimension data is counted and the sum of the mean and the standard deviation is calculated as the fractal threshold, and the minimum threshold limit value is determined based on historical data. The maximum value of the minimum threshold limit value and the fractal threshold is used as the dimension threshold. If the calculated current fractal dimension is greater than or equal to the dimension threshold, it is determined that correction is required;

[0086] The fractal Brownian motion algorithm fBM is used to establish the nonlinear perturbation model of current fluctuation, which is expressed as:

[0087] ;

[0088] in represents the current fluctuation value under the fractal Brownian motion at time t, The Hurst exponent, which represents the current fluctuation at time t, can be set as , Represents the disturbance amplitude value, which is determined by the historical fluctuation standard deviation. represents the random perturbation value of the standard Brownian motion at time t;

[0089] based on To verify, the multi-scale Box-Counting algorithm is used according to the scale parameter right Multi-scale segmentation is performed, and the box technique is calculated, and the corresponding verification fractal dimension is calculated by linear regression, which is expressed as:

[0090] ;

[0091] in Indicates the verification fractal dimension, C is the intercept term in linear regression, which indicates the cardinality of the shape object at the minimum scale and can be calculated by the least squares method;

[0092] Will verify the fractal dimension and The difference is verified, and the minimum value is determined as the verification threshold based on historical data. If the fractal difference is less than the verification threshold, it means Maintain consistency at multiple scales and pass verification;

[0093] Based on verified Set the adjustment factor and modify the predicted value according to the adjustment factor, expressed as:

[0094] ;

[0095] ;

[0096] in represents the adjustment factor, Represents a minimum value to prevent the denominator from being zero. represents the corrected current prediction value at time t+Δt, Indicates the difference between the actual current value and the predicted value.

[0097] Through multi-scale division, the self-similarity and multi-fractal structure of current fluctuations can be fully captured, reflecting the complexity of current fluctuations at different time scales. It is particularly suitable for modeling nonlinear and non-stationary current fluctuations, and improving the prediction accuracy of sudden changes, spikes and periodic fluctuations. Through fractal dimension calculation, the complexity and multi-scale self-similarity of current fluctuations can be described, and the degree of chaos of current fluctuations can be accurately quantified, nonlinear fluctuations and abnormal fluctuations can be accurately identified, and the correction mechanism of predicted values ​​can be triggered to avoid misjudgment of stable fluctuations, effectively reduce redundant calculations of error correction, and improve the accuracy and efficiency of correction calculations. Through fractal Brownian motion (fBM), a nonlinear perturbation model of current fluctuations can be established to dynamically adjust the long-term trend and short-term random fluctuations of current fluctuations. Through fractal dimension consistency verification, the random fluctuations and external noise influences in the nonlinear perturbation model can be eliminated to ensure the reliability and stability of the fBM model. Through the calculation of adjustment factors and correction of predicted values, short-term fluctuations and noise interference can be effectively eliminated, and the robustness and accuracy of the corrected predicted values ​​can be improved.

[0098] By organically combining multimodal data fusion with multiscale consistency verification of fractal dimensions, the time scale deviation of different data sources is eliminated, and the effectiveness and consistency of multidimensional feature fusion are improved. The multiscale time series features extracted by TCN accelerated by photon computing provide high-precision and high-timeliness feature input for multiscale segmentation and self-similarity verification of the Box-Counting algorithm. The complexity and multiscale self-similarity of current fluctuations are quantitatively described by the current fractal dimension, and the performance of multimodal data in nonlinear fluctuation and abnormal fluctuation detection is enhanced. The phase adjustment of optical phase shift modulation is combined with the multiscale self-similarity of fractal dimensions to fully capture the nonlinear characteristics of current fluctuations at different frequencies and amplitudes. The nonlinear correction mechanism of the adjustment factor is combined with the efficient calculation of photon computing to significantly improve the correction speed and accuracy of the predicted value. The dynamic adjustment factor based on fractal dimensions is combined with the phase adjustment and complex domain mapping of the photon computing layer to achieve accurate correction and fast calculation of nonlinear and complex fluctuations.

[0099] S3, calculates the current trend correction factor, dimensional anomaly index and magnetic field disturbance index, determines the optimal strategy and calculates the short-term disturbance value through the reinforcement learning algorithm, and performs decision delay verification;

[0100] Preferably, the current trend correction factor, the dimension anomaly index and the magnetic field disturbance index are calculated, the optimal strategy is determined by the reinforcement learning algorithm, and the current trend correction factor is defined based on the corrected current prediction value, which is expressed as:

[0101] ;

[0102] in represents the current trend correction factor, represents the corrected current prediction value at time ti;

[0103] The dimension anomaly index is calculated based on the current fractal dimension and is expressed as:

[0104] ;

[0105] in represents the dimension anomaly index, represents the mean value of the current fractal dimension;

[0106] Based on the finite element simulation FEM, the magnetic induction intensity is determined, and the electromagnetic torque of the circuit breaker at the current time t is calculated, and the magnetic field disturbance index is calculated, which is expressed as:

[0107] ;

[0108] ;

[0109] in represents the magnetic field disturbance index, and denote the electromagnetic torque of the circuit breaker at time t and time t-1 respectively, represents the current density, represents the magnetic induction intensity, and V represents the action area of ​​the circuit breaker;

[0110] The curriculum learning mechanism is used to dynamically adjust the difficulty of the reinforcement learning task based on the current trend correction factor, dimension anomaly index and magnetic field disturbance index, which is expressed as:

[0111] ;

[0112] ;

[0113] in represents the complexity of the task, T represents the time window of the course learning phase, Indicates the initial time, represents the fixed reward scale parameter, (determined based on historical data), Indicates the task complexity modification reward item;

[0114] based on As a reward correction term, Q-learning is updated through the reinforcement learning algorithm, and the learning rate is dynamically adjusted, expressed as:

[0115] ;

[0116] in represents the dynamic learning rate, represents the initial learning rate;

[0117] The state space is composed of current prediction value, current fractal dimension, magnetic field disturbance index and task complexity, and the action space is composed of the adjustment, closing and maintaining state of the circuit breaker. The Q value table is updated through Q-learning, including the corresponding Q values ​​of different state spaces and action spaces, and the optimal strategy is obtained to determine the state of the circuit breaker under different states.

[0118] The current trend correction factor is used to dynamically capture the current fluctuation trend and amplitude. The dimension anomaly index of the current fractal dimension is used to accurately detect nonlinear fluctuations and abnormal fluctuations. The electromagnetic torque disturbance modeling of finite element simulation (FEM) is used to accurately quantify the intensity and volatility of the electromagnetic disturbance of the circuit breaker. The task complexity adjustment and reward correction of the curriculum learning mechanism are used to effectively improve the scenario adaptability and generalization of the reinforcement learning model. The Q-learning update mechanism of the reinforcement learning algorithm is used to dynamically find the optimal strategy in the state space and action space to achieve refined control of the closing, holding, and adjustment operations of the circuit breaker.

[0119] Furthermore, the short-term disturbance value is calculated, and the decision delay verification is performed. The short-term disturbance is considered based on the optimal strategy, in which the disturbance time window is defined to calculate the short-term disturbance, which is expressed as:

[0120] ;

[0121] in represents the short-term disturbance index, represents the disturbance time window;

[0122] The sum of the historical mean and double standard deviation of the short-term disturbance index is used as the delay threshold. If the short-term disturbance index is less than or equal to the delay threshold, it is judged as no delay and the optimal strategy is directly executed. If the short-term disturbance index is greater than the delay threshold, the decision is delayed, which is expressed as:

[0123] ;

[0124] in represents the decision delay value, represents the delay threshold, Indicates the maximum delay time;

[0125] A time delay is performed based on the decision delay value and the Q value table is updated again through Q-learning to determine the optimal strategy after the delay.

[0126] By calculating the short-term disturbance value through the dynamic changes of current fluctuations within the disturbance time window, it is possible to accurately identify transient fluctuations, short-term pulses and high-frequency noise, significantly improve the response speed and decision-making accuracy of the power grid under transient disturbances and sudden fluctuations, significantly reduce misjudgments and misoperations, and ensure the safety of the power grid and the stable operation of equipment.

[0127] S4, monitor the circuit breaker status data, calculate the thermal anomaly index and issue an early warning, analyze the current stability value, and perform closing operations;

[0128] Preferably, the circuit breaker status data is monitored, the thermal anomaly index is calculated and an early warning is issued, and the action implementation based on the optimal strategy is performed, the circuit breaker status data is monitored, the circuit breaker temperature data is collected and the thermal anomaly index is calculated, which is expressed as:

[0129] ;

[0130] in represents the thermal anomaly index, m represents the total number of acquisition times, represents the circuit breaker temperature at time i, represents the ambient temperature at time i;

[0131] Based on the sum of the rated temperature of the circuit breaker and the allowable temperature rise value of the circuit breaker as the temperature threshold, if the thermal anomaly index is greater than or equal to the temperature threshold, the circuit breaker temperature is judged to be abnormal, and an alarm is issued through the early warning device.

[0132] By accumulating the difference between the circuit breaker temperature and the ambient temperature, the heat accumulation and temperature rise inside the circuit breaker can be accurately reflected, and the abnormal temperature change trend can be captured in real time. Especially when the temperature continues to rise or fluctuates violently, the anomaly can be quickly identified and timely warning can be issued, reducing the dependence on a single temperature threshold. It can accurately identify the abnormal change trend in temperature fluctuations and effectively improve the accuracy and stability of temperature monitoring.

[0133] Furthermore, analyzing the current stability value and performing the closing operation refers to the implementation of the action based on the optimal strategy. If the circuit breaker is in the open state, the mean of the corrected current prediction value in the acquisition window is used as the current stability value, and the sum of the mean and standard deviation of the current stability is used as the current threshold. If the current stability value is less than the current threshold, it is determined that the closing conditions are met and the closing operation is performed.

[0134] By correcting the mean calculation of the current prediction value within the acquisition window, the stable state of the current over a period of time can be accurately reflected, especially when the load fluctuation is small, and the stable state and continuous state of the current can be effectively identified.

[0135] This embodiment also provides a system based on the intelligent control method of the pole-mounted circuit breaker device, comprising:

[0136] The data acquisition and processing module collects environmental data of the pole-mounted circuit breaker and performs time synchronization and noise reduction on the multi-modal data;

[0137] The data fusion and time series construction module uses the Kalman filter algorithm to fuse multimodal environmental data and construct multidimensional time series data based on the fused state vector;

[0138] The time series neural network module uses the TCN network accelerated by photon computing to extract multi-scale time series features from the time series of the fused state vector, maps the time series features into the complex domain and performs optical phase shift modulation to predict the current;

[0139] The nonlinear correction module divides the predicted current time series into multiple scales, calculates the current fractal dimension and verifies its consistency, and performs nonlinear correction on the current prediction value based on the adjustment factor calculated by the fractal dimension;

[0140] The reinforcement learning adaptive control module calculates the current trend correction factor, dimension anomaly index and magnetic field disturbance index, dynamically adjusts the complexity of the reinforcement learning task, updates the Q value table through Q-learning, dynamically calculates the optimal strategy and performs decision delay verification;

[0141] Intelligent early warning module collects circuit breaker status data for status monitoring and fault early warning;

[0142] Communication module, modular integration and edge computing communication, to achieve multi-module linkage and real-time data transmission.

[0143] This embodiment also provides a computer device, which is suitable for the case of an intelligent control method based on a pole-mounted circuit breaker device, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the intelligent control method based on the pole-mounted circuit breaker device proposed in the above embodiment.

[0144] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0145] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the intelligent control method for a pole-mounted circuit breaker device proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a disk or an optical disk.

[0146] In summary, the present invention maps the features extracted by the time convolution layer into the complex domain and converts the time series features into complex form, thereby enhancing the expression ability of nonlinear features. The introduction of optical phase shift modulation further adjusts the phase and amplitude information and improves the nonlinear modeling ability of time series features. The multimodal data fusion is organically combined with the multi-scale consistency verification of the fractal dimension to eliminate the time scale deviation of different data sources and improve the effectiveness and consistency of multi-dimensional feature fusion. The phase adjustment of the optical phase shift modulation is combined with the multi-scale self-similarity of the fractal dimension to fully capture the nonlinear characteristics of current fluctuations at different frequencies and amplitudes. The nonlinear correction mechanism of the adjustment factor is combined with the efficient calculation of photon calculation to significantly improve the correction speed and accuracy of the predicted value. The current fluctuation trend and amplitude are dynamically captured by the current trend correction factor. The dimensional anomaly index of the current fractal dimension is used to accurately detect nonlinear fluctuations and abnormal fluctuations to ensure the safety of the power grid and the stable operation of the equipment.

[0147] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent control method based on a pole-mounted circuit breaker device, characterized in that: include: Collect the environmental data of the pole-mounted circuit breaker, use the Kalman filter fusion algorithm to output the fusion state vector, and construct the time series data. Use the time series neural network accelerated by photon computing to map the extracted features into the complex domain and perform optical phase shift modulation to predict the future current value; The predicted current time series is divided into multiple scales, the current fractal dimension is calculated, the nonlinear perturbation model of current fluctuation is established using the fractal Brownian motion algorithm to calculate the current fluctuation value, and the fractal dimension is verified by linear regression calculation for consistency verification, the adjustment factor is calculated and the predicted value is corrected; Calculate the current trend correction factor, dimensional anomaly index and magnetic field disturbance index, determine the optimal strategy and calculate the short-term disturbance value through the reinforcement learning algorithm, and perform decision delay verification; Monitor circuit breaker status data, calculate thermal anomaly index and issue early warning, analyze current stability value, and perform closing operations.

2. The intelligent control method based on the pole-mounted circuit breaker device according to claim 1, characterized in that: The collecting of the environmental data of the pole-mounted circuit breaker and the output of the fusion state vector using the Kalman filter fusion algorithm refer to collecting environmental data based on the pole-mounted circuit breaker device through sensors, including temperature data, humidity data, current data and leakage current data; The collected environmental data are synchronized using linear interpolation and denoised using adaptive Wiener filtering; Using the Kalman filter fusion algorithm, the current state is predicted and the covariance is predicted for the environmental vector composed of environmental data, the Kalman gain is calculated, the state vector is corrected using the measurement data and the covariance matrix is ​​updated, the fused state vector is output, and time series data is constructed; The time series neural network accelerated by photon computing is used to build a time series model, including input layer, time convolution layer, photon computing layer and output layer; The input layer inputs the normalized fusion state vector data. The temporal convolution layer uses the temporal convolution network (TCN) to extract the time series features. The features extracted by the temporal convolution layer are mapped to the complex domain and optical phase shift modulation is performed. The photon calculation layer is used to finally predict the future current value. Use the calibrated training set to train the model, select the cross entropy loss function to calculate the computational loss between the model's predicted output and the actual label, use the chain rule to calculate the loss, perform backpropagation calculations on the gradients of each layer's parameters, use the Adam optimizer to update the parameters, and stop updating if the model's loss no longer decreases significantly during the continuous update process, and output the model parameters; Use the newly acquired data to make current data forecasts using a time series model.

3. The intelligent control method based on the pole-mounted circuit breaker device according to claim 2, characterized in that: The multi-scale division of the predicted current time series and the calculation of the current fractal dimension refer to fractal dimension correction FDA of the predicted current data, forming the predicted current data into sequence data, and setting the scale parameter ; Through the multi-scale Box-Counting algorithm at each scale Under this condition, the predicted current time series is gridded, the number of intervals covering the entire current series is counted, the number of scale intervals is calculated according to the box counting method, and the current fractal dimension is calculated by linear regression fitting; The current fractal dimension data is counted and the sum of the mean and the standard deviation is calculated as the fractal threshold, and the minimum threshold limit value is determined based on historical data. The maximum value of the minimum threshold limit value and the fractal threshold is used as the dimension threshold. If the calculated current fractal dimension is greater than or equal to the dimension threshold, it is determined that correction is required; The fractal Brownian motion algorithm fBM is used to establish a nonlinear perturbation model of current fluctuation, and the current fluctuation value is determined by the Hurst index and disturbance amplitude of the current fluctuation. ; Based on current fluctuation value To verify, the multi-scale Box-Counting algorithm is used according to the scale parameter right Perform multi-scale segmentation, calculate the box technique, and calculate the corresponding verification fractal dimension through linear regression ; Will verify the fractal dimension and The difference is verified, and the minimum value is determined as the verification threshold based on historical data. If the fractal difference is less than the verification threshold, it means Maintain consistency at multiple scales and pass verification; Based on verified Set adjustment factors and revise the forecast values ​​based on the adjustment factors.

4. The intelligent control method based on the pole-mounted circuit breaker device according to claim 3, characterized in that: The current trend correction factor, dimensional anomaly index and magnetic field disturbance index are calculated, and the optimal strategy is determined by a reinforcement learning algorithm, and the current trend correction factor is defined based on the relative change rate between the corrected current prediction value and the over-prediction value; Based on the current fractal dimension and fractal dimension mean The difference between the two determines the dimension anomaly index ; Determine the magnetic induction intensity based on finite element simulation FEM, calculate the electromagnetic torque of the circuit breaker at the current time t, and calculate the relative change rate of the electromagnetic torque at different times as the magnetic field disturbance index; Use the curriculum learning mechanism to dynamically adjust the difficulty of reinforcement learning tasks based on the current trend correction factor, dimensional anomaly index, and magnetic field disturbance index, and determine the task complexity ; based on Q-learning updates performed by the reinforcement learning algorithm as a reward correction term, and dynamically adjust the learning rate; The state space is composed of current prediction value, current fractal dimension, magnetic field disturbance index and task complexity, and the action space is composed of the adjustment, closing and maintaining state of the circuit breaker. The Q value table is updated through Q-learning, including the corresponding Q values ​​of different state spaces and action spaces, and the optimal strategy is obtained to determine the state of the circuit breaker under different states.

5. The intelligent control method based on the pole-mounted circuit breaker device according to claim 4, characterized in that: The short-term disturbance value is calculated, and the decision delay verification is performed, and the short-term disturbance is calculated based on the optimal strategy, wherein a disturbance time window is defined and the short-term disturbance is calculated based on the difference of the corrected predicted value; The sum of the historical mean and double standard deviation of the short-term disturbance index is used as the delay threshold. If the short-term disturbance index is less than or equal to the delay threshold, it is judged as no delay and the optimal strategy is directly executed. If the short-term disturbance index is greater than the delay threshold, the decision is delayed. A time delay is performed based on the decision delay value and the Q value table is updated again through Q-learning to determine the optimal strategy after the delay.

6. The intelligent control method based on the pole-mounted circuit breaker device according to claim 5, characterized in that: The circuit breaker status data is monitored, the thermal anomaly index is calculated and an early warning is issued, the action implementation based on the optimal strategy is performed, the circuit breaker status data is monitored, the circuit breaker temperature data is collected and the thermal anomaly index is calculated according to the difference between the ambient temperature and the collected temperature; Based on the sum of the rated temperature of the circuit breaker and the allowable temperature rise value of the circuit breaker as the temperature threshold, if the thermal anomaly index is greater than or equal to the temperature threshold, the circuit breaker temperature is judged to be abnormal, and an alarm is issued through the early warning device.

7. The intelligent control method based on the pole-mounted circuit breaker device according to claim 6, characterized in that: The analyzing the current stability value and performing the closing operation refers to the implementation of the action based on the optimal strategy. If the circuit breaker is in the off state, the mean value of the corrected current prediction value in the acquisition window is used as the current stability value, and the sum of the mean value and the standard deviation of the current stability is used as the current threshold. If the current stability value is less than the current threshold, it is determined that the closing conditions are met and the closing operation is performed.

8. A system based on an intelligent control method for a pole-mounted circuit breaker device, based on the intelligent control method for a pole-mounted circuit breaker device according to any one of claims 1 to 7, characterized in that: include, The data acquisition and processing module collects environmental data of the pole-mounted circuit breaker and performs time synchronization and noise reduction on the multi-modal data; The time series construction module uses the Kalman filter algorithm to fuse multimodal environmental data and construct multidimensional time series data based on the fused state vector; The time series neural network module uses the TCN network accelerated by photon computing to extract multi-scale time series features from the time series of the fusion state vector; The nonlinear correction module calculates the current fractal dimension of the predicted current time series and verifies its consistency. Based on the adjustment factor calculated by the fractal dimension, the nonlinear correction is performed on the current prediction value. The reinforcement learning adaptive control module calculates the current trend correction factor, dimension anomaly index and magnetic field disturbance index, dynamically adjusts the complexity of the reinforcement learning task, updates the Q value table through Q-learning, dynamically calculates the optimal strategy and performs decision delay verification; The intelligent early warning module collects circuit breaker status data for status monitoring and fault early warning.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent control method based on the pole-mounted circuit breaker device according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent control method based on a pole-mounted circuit breaker device according to any one of claims 1 to 7 are implemented.

Images