Intelligent arc extinguishing and current limiting method and system based on dynamic fault prediction

Abstract

The invention discloses an intelligent arc extinguishing and current limiting method and system based on dynamic fault prediction, and relates to the technical field of power systems, and the method comprises the steps: collecting the data of a power distribution network, and carrying out the denoising and data smoothing processing; current trend prediction is carried out according to the power distribution network data, fault occurrence time and place are predicted, a fault prediction report is generated, a fault point is positioned, and a fault area is rapidly isolated; according to the power distribution network data and the fault prediction report, parameters of the arc suppression coil are dynamically adjusted, feedback control is performed on the parameters of the arc suppression coil according to the arc suppression effect monitored in real time, and rapid arc suppression and current limitation are realized. According to the method, the automation and intelligence level of fault processing is improved, the response time of fault processing is greatly shortened, and the operation reliability and stability of a power grid are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to an intelligent arc extinguishing and current limiting method and system based on dynamic fault prediction. Background Art

[0002] With the continuous development of modern power systems and the expansion of power grids, the operating environment of distribution networks has become increasingly complex, and the frequency of various faults has increased year by year. Traditional distribution network fault detection and processing methods can no longer meet the needs of today's complex power grids. In recent years, intelligent technologies have been increasingly used in distribution networks, including fault prediction technologies based on artificial intelligence and machine learning. These technologies can accurately predict the time and location of faults by analyzing a large amount of historical data, thereby improving the reliability and stability of power grid operations.

[0003] At present, common arc suppression and current limiting methods mainly include arc suppression coils with fixed parameters and static fault current limiting devices. Although these methods can alleviate the impact of faults to a certain extent, it is often difficult to achieve fast and accurate fault handling in the face of complex and changeable power grid environments. The effect of arc suppression coils with fixed parameters is limited under different fault conditions and cannot be dynamically adjusted according to actual conditions. Although static fault current limiting devices can act quickly when a fault occurs, their fixed working mode cannot adapt to various changes in power grid operation, making it difficult to achieve the best current limiting effect.

[0004] Existing technologies have significant deficiencies in fault prediction and processing. First, traditional fault detection methods rely on fixed thresholds and preset fault modes, which makes it difficult to cope with the diverse fault types in distribution networks. Second, existing arc extinguishing and current limiting devices lack real-time feedback and dynamic adjustment mechanisms, and cannot be effectively adjusted according to the actual situation of the fault, resulting in poor fault handling results. In addition, existing technologies usually require manual intervention after a fault occurs, which increases the response time and operational complexity of fault handling. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is that the prior art lacks intelligent fault prediction capability, and the parameters of arc extinguishing and current limiting devices are fixed and cannot be dynamically adjusted according to actual fault conditions.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent arc extinguishing and current limiting method based on dynamic fault prediction, comprising: collecting distribution network data, performing denoising and data smoothing processing; predicting current trends based on distribution network data, predicting the time and location of fault occurrence, generating a fault prediction report, locating the fault point and quickly isolating the fault area; dynamically adjusting the parameters of the arc extinguishing coil based on the distribution network data and the fault prediction report, and performing feedback control on the parameters of the arc extinguishing coil based on the arc extinguishing effect monitored in real time, so as to achieve rapid arc extinguishing and current limiting.

[0008] As a preferred solution of the intelligent arc extinguishing and current limiting method based on dynamic fault prediction described in the present invention, the distribution network data includes the current, voltage, temperature data of the line, the arc extinguishing coil working status data and historical data.

[0009] As a preferred solution of the intelligent arc extinguishing and current limiting method based on dynamic fault prediction described in the present invention, the current trend prediction includes building a combined model of LSTM and GRU to identify and predict the current trend. The structure of the model is divided into an input layer, an LSTM layer, a GRU layer, a weight calculation layer, a weighted average layer and an output layer. The input layer receives the distribution network data and uploads it to the LSTM layer and the GRU layer for calculation to obtain the hidden state output of the LSTM. And the hidden state output of GRU ; Adaptive weight parameters calculated in the weight calculation layer , using sliding windows to calculate time windows The mean square error within is updated by gradient descent , expressed as: , , in, Represents the updated adaptive weight parameters; represents the initial adaptive weight parameter; represents the learning rate; Representation time window The mean square error within ; Indicates the moment; represents the mean square error at time t; At the same time, in the weighted average layer according to the adaptive weight parameter ,Will and Weighted combination, and the combined result is output through the output layer, expressed as: , in, Indicates time Current prediction value; set the current safety range based on historical data , the threshold value of the current change rate and ,and ; Indicates time The adaptive weight parameter of exist When it is within the range, it indicates that the current is normal; when exist When it is out of range, it indicates abnormal current; when the predicted value of the current change rate is When the current change rate is normal; when When the current change rate is abnormal; when When , it indicates that the current change rate reaches the fault range.

[0010] As a preferred solution of the intelligent arc extinguishing and current limiting method based on dynamic fault prediction described in the present invention, wherein: the initial adaptive weight parameter Obtained through grid search during model training, setting the initial adaptive weight parameters The value range is , the initial step length is , the number of cross validation folds is ; For each Value, grid search: Initialization is 0, the training data set is divided into subsets, for each subset , use The rest The combined model is trained using subsets. Verify the model and calculate the mean square error ,Will Add to , calculate the average mean square error of all subsets, expressed as: , in, express The average mean square error of Smallest The value of , zoom out The value range is , the step size is set to , again for each The value is grid searched and calculated , repeat the grid search and shrink The range of steps is up to Achieve target accuracy, output As the initial adaptive weight parameter.

[0011] As a preferred solution of the intelligent arc extinguishing and current limiting method based on dynamic fault prediction described in the present invention, wherein: the fault prediction report includes, when the current is normal and the current change rate is normal, it is judged that the distribution network is in a normal operating state, the existing arc extinguishing coil parameters are maintained and no fault prediction report is generated; when the current is normal and the current change rate is abnormal, it is judged that the distribution network is in an abnormal fluctuation state, the sampling frequency of the distribution network data is increased, the arc extinguishing coil parameters are dynamically adjusted, and if the abnormal fluctuation state lasts for more than a preset time threshold , an early warning signal is issued to remind the staff to monitor manually; when the current is normal and the current change rate reaches the fault range, the distribution network is judged to be in a potential fault state, the arc suppression coil parameters are dynamically adjusted, and the location of the potential fault is reversely located according to the distribution network data source, a fault prediction report is generated and an early warning is issued; when the current is abnormal and the current change rate is normal, the distribution network is judged to be in an abnormal current state, the sampling frequency of the distribution network data is increased, the arc suppression coil parameters are dynamically adjusted to prevent further abnormal current, and an early warning signal is issued to remind the staff to check the load situation to prevent further deterioration; when the current is abnormal and the current change rate is abnormal, the distribution network is judged to be in a complex abnormal state, and the fault detection sensor is started. The sensor scans the complex abnormal area, dynamically adjusts the arc suppression coil parameters and starts the auxiliary protection device to prevent the fault from expanding, generates a fault prediction report and warns, and dispatches staff to conduct on-site confirmation and maintenance; when the current is abnormal and the current change rate reaches the fault range, it is determined that the distribution network is in a fault state, and the arc suppression coil parameters are immediately adjusted to reduce the fault current, and the fault detection sensor is started to locate the location of the fault, and the fault area is quickly isolated to prevent the fault from expanding. After confirming that the fault area has been de-energized and isolated, the arc suppression equipment is stopped, a fault prediction report is generated and warned, and staff are dispatched to repair the fault. After the staff completes the repair and manually confirms it, the isolation measures of the fault area are withdrawn.

[0012] As a preferred solution of the intelligent arc extinguishing and current limiting method based on dynamic fault prediction described in the present invention, the dynamic adjustment of the arc extinguishing coil parameters includes, when the distribution network is in an abnormal fluctuation state, slightly adjusting the inductance to increase the damping characteristics of the system to suppress the fluctuation, which is expressed as: , in, represents the adjusted inductance; Indicates the inductance before adjustment; Indicates the adjustment amount; When the distribution network is in a potential fault state, the connection mode of the arc suppression coil is changed from parallel to series, and the inductance is adjusted to quickly suppress abnormal fluctuations, which is expressed as: , in, represents the adjustment factor; When the distribution network is in an abnormal current state, the arc extinguishing effect is optimized by adjusting the ratio of inductance and resistance, which is expressed as: , in, represents the adjusted resistance; Indicates the resistance before adjustment; The deviation amount indicating the abnormal current; Indicates normal current; When the distribution network is in a complex abnormal state, the inductance is adjusted and the capacitance is increased to form an LC resonant circuit to absorb current fluctuations, which is expressed as: , , in, represents the adjusted capacitance; Indicates the capacitance before adjustment; Indicates the newly added capacitance value; When the distribution network is in a fault state, the connection mode of the arc suppression coil is changed from parallel to series, and the inductance is adjusted to quickly suppress abnormal fluctuations. If there is a backup arc suppression device, it is started to provide additional protection. After the fault area is isolated, the arc suppression work is stopped, which is expressed as: , , in, represents the adjustment factor; Indicates the rate of change of current.

[0013] As a preferred solution of the intelligent arc extinguishing and current limiting method based on dynamic fault prediction described in the present invention, the feedback control includes calculating the error between the actual value and the predicted value after adjusting the arc extinguishing coil parameters, which is expressed as: , in, Indicates time The error of Indicates time The predicted value of Indicates time The actual measured value; when the error increases When the current adjustment range is insufficient, increase , expressed as: , When the error decreases When the current adjustment range is too large, reduce , expressed as: , in, Indicates the new adjustment amount; Represents the adjustment coefficient.

[0014] An intelligent arc extinguishing and current limiting system based on dynamic fault prediction adopting any of the methods described in the present invention, wherein: an acquisition module collects distribution network data, performs denoising and data smoothing processing, and uploads the processed data to a detection module; the detection module constructs a combined model of LSTM and GRU to identify and predict current trends, optimizes the prediction accuracy by dynamically adjusting the weights of a weighted average layer, generates a fault prediction report according to the prediction results, locates the fault point and quickly isolates the fault area; the arc extinguishing module dynamically adjusts the parameters of the arc extinguishing coil according to the distribution network data and the fault prediction report, and performs feedback control on the parameters of the arc extinguishing coil according to the arc extinguishing effect monitored in real time, so as to achieve rapid arc extinguishing and current limiting.

[0015] A computer device comprises: a memory and a processor; the memory stores a computer program, comprising: the steps of implementing any one of the methods of the present invention when the processor executes the computer program.

[0016] A computer-readable storage medium stores a computer program, comprising: when the computer program is executed by a processor, the steps of implementing any one of the methods of the present invention are implemented.

[0017] Beneficial effects of the present invention: The method of the present invention collects distribution network data and performs denoising and data smoothing processing, uses the current trend prediction model to predict the time and location of the fault, generates a fault prediction report, locates the fault point and quickly isolates the fault area. At the same time, according to the real-time monitoring data and the fault prediction report, the parameters of the arc extinguishing coil are dynamically adjusted, and the arc extinguishing effect is monitored in real time using the feedback control mechanism to achieve rapid arc extinguishing and current limiting. It not only improves the automation and intelligence level of fault handling, but also greatly shortens the response time of fault handling, and improves the operational reliability and stability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 An overall flow chart of an intelligent arc extinguishing and current limiting method based on dynamic fault prediction is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned purposes, 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 drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0021] Example 1, reference Figure 1 , as an embodiment of the present invention, provides an intelligent arc extinguishing and current limiting method based on dynamic fault prediction, comprising: S1: Collect distribution network data and perform denoising and data smoothing.

[0022] Furthermore, after the system is started, historical fault data and arc suppression coil working status data are loaded, the sensor network is initialized, and all monitoring devices are ensured to work properly and connected to the control center.

[0023] The loading of historical fault data is the basis for the system to conduct intelligent fault prediction. By analyzing past fault data, the fault prediction model can identify common fault modes and laws, thereby improving the accuracy of fault prediction.

[0024] The working status data of the arc extinguishing coil is used to understand the historical operation status and performance indicators of the equipment, ensuring that the actual working capacity and status of the arc extinguishing coil can be taken into account when predicting faults. It is of great significance for adjusting the parameters of the arc extinguishing coil and optimizing the arc extinguishing effect. When adjusting the arc extinguishing coil according to the fault prediction results, the adjustment amount and basic amount are obtained based on the working status data of the arc extinguishing coil.

[0025] The sensor network is used to monitor current, voltage, temperature and other parameters in real time, and the real-time monitoring data is transmitted to the control center for preliminary processing and storage. The collected data is pre-processed. De-noising is the first step in data pre-processing, which aims to improve the accuracy and reliability of the data.

[0026] Monitoring data such as current, voltage and temperature may be affected by various noises and interferences during the collection process, such as electromagnetic interference, equipment failure, environmental changes, etc. These noises and outliers will affect the accuracy of the fault prediction model. Therefore, denoising must be performed and Kalman filtering must be used to process data online in real time. The dynamic model and measurement model of the system are used to predict and correct the monitoring data.

[0027] Smoothing is the second step of data preprocessing, which aims to eliminate short-term fluctuations in the data, highlight long-term trends, and make the data more stable and coherent. Different weights are given to the data in the window through weighted sliding average. Usually, the data close to the center point has a greater weight, which better preserves the local characteristics of the data and achieves a smoothing effect. The size of the sliding window sets the initial value , the size of the sliding window is adjusted according to the fault prediction report, and if a fault risk or current fluctuation is detected, the sliding window size is reduced To increase the frequency of monitoring.

[0028] S2: Predict current trends based on distribution network data, predict the time and location of faults, generate fault prediction reports, locate fault points and quickly isolate fault areas.

[0029] Furthermore, in practical applications, fault prediction of power systems considers both long-term and short-term data features. LSTM and GRU are two commonly used recurrent neural network (RNN) variants. LSTM is a long short-term memory network that performs well when processing long sequence data and can better retain long-term memory; GRU is a gated recurrent unit that performs well when processing short sequence data and has high computational efficiency.

[0030] Using LSTM or GRU alone may not be able to fully capture all the features in the data. Therefore, combining the advantages of LSTM and GRU can analyze the data more comprehensively and provide more accurate predictions.

[0031] The main part of combining LSTM and GRU is their hidden state output (i.e., their respective final hidden states). In the traditional LSTM and GRU structures, their respective hidden states are used to predict the output of the next step. In the combined neural network, the hidden state outputs of LSTM and GRU are calculated separately, and the two hidden states are weighted averaged according to an adaptive weight parameter to obtain the final prediction result.

[0032] The structure of the combined model of LSTM and GRU is divided into input layer, LSTM layer, GRU layer, weight calculation layer, weighted average layer and output layer. The input layer receives the distribution network data and uploads it to the LSTM layer and GRU layer for calculation to obtain the hidden state output of LSTM. And the hidden state output of GRU .

[0033] Adaptive weight parameters calculated in the weight calculation layer , using sliding windows to calculate time windows The mean square error within is updated by gradient descent , expressed as: , , in, Represents the updated adaptive weight parameters; represents the initial adaptive weight parameter; represents the learning rate; Representation time window The mean square error within ; Indicates the moment; represents the mean square error at time t.

[0034] It should be noted that since the hidden state outputs of LSTM and GRU are both in vector form, they can be combined by weighted averaging without making additional deformation adjustments to the output form and without taking the risk of increased computational complexity and additional errors caused by data deformation. The accuracy of the prediction can be improved through simple weighted combination.

[0035] As time goes by, the environment and operating conditions in the distribution network may change, causing the performance of the fault prediction model to deteriorate. In order to maintain the accuracy and robustness of the model, the initial The weights are calculated during model training, but are not fixed in practice. value, but through real-time monitoring and dynamic adjustment value to optimize the performance of the model.

[0036] At the same time, in the weighted average layer according to the adaptive weight parameter ,Will and Weighted combination, and the combined result is output through the output layer, expressed as: , in, Indicates time Current prediction value; set the current safety range based on historical data , the threshold value of the current change rate and ,and ; Indicates time The adaptive weight parameters.

[0037] when exist When it is within the range, it indicates that the current is normal; when exist Outside the range indicates abnormal current.

[0038] When the predicted value of the current change rate When the current change rate is normal; when When the current change rate is abnormal; when When , it indicates that the current change rate reaches the fault range.

[0039] Furthermore, during the model training process, the optimal parameters are calculated through grid search and cross validation. , set the initial The value range is , the initial step length is , the number of cross validation folds is .

[0040] For each Value, perform a grid search: initialization is 0, the training data set is divided into subsets, for each subset , use The rest The combined model is trained using subsets Verify the model and calculate the mean square error ,Will Add to , calculate the average mean square error of all subsets, expressed as: , in, express The average mean square error of Smallest The value of , zoom out The value range is , the step size is set to , again for each The value is grid searched and calculated , repeat the grid search and shrink The range of steps is up to Achieve target accuracy, output As the initial adaptive weight parameter.

[0041] Narrow based on previous round of search results By refining the step length for fall calculation, a more accurate As the initial adaptive weight parameters, dynamically adjusting the range and step size can reduce unnecessary calculations, improve search efficiency, ensure parameter optimization is accurate to several decimal places, and improve model performance.

[0042] It means to recalculate and correct at certain time intervals or when certain conditions are met. , in order to adapt to environmental changes, for example, grid search and cross-validation can be repeated at regular intervals (such as every month) or when the prediction performance drops to a certain threshold to update .

[0043] Furthermore, a fault prediction report is generated based on the prediction results. When the current is normal and the current change rate is normal, the distribution network is judged to be in normal operation, the existing arc suppression coil parameters are maintained, and no fault prediction report is generated. At this time, the system is in a stable state, ensuring that the system remains stable under normal conditions, without unnecessary adjustments, and avoiding the introduction of new disturbances.

[0044] When the current is normal and the current change rate is abnormal, the distribution network is judged to be in an abnormal fluctuation state, the sampling frequency of the distribution network data is increased, and the arc suppression coil parameters are dynamically adjusted. If the abnormal fluctuation state lasts for more than the preset time threshold , an early warning signal is issued to remind staff to monitor manually.

[0045] When the current is normal and the current change rate reaches the fault range, the distribution network is determined to be in a potential fault state, the arc suppression coil parameters are dynamically adjusted, the location of the potential fault is reversely located based on the distribution network data source, a fault prediction report is generated, and an early warning is issued.

[0046] When the current is abnormal and the current change rate is normal, the distribution network is judged to be in an abnormal current state, the sampling frequency of the distribution network data is increased, the arc suppression coil parameters are dynamically adjusted to prevent further current abnormalities, and an early warning signal is issued to remind staff to check the load conditions to prevent further deterioration.

[0047] When the current is abnormal and the current change rate is abnormal, the distribution network is determined to be in a complex abnormal state, the fault detection sensor is started to scan the complex abnormal area, the arc suppression coil parameters are dynamically adjusted and the auxiliary protection device is started to prevent the fault from expanding, a fault prediction report is generated and an early warning is issued, and staff are dispatched to conduct on-site confirmation and maintenance.

[0048] When the current is abnormal and the current change rate reaches the fault range, the distribution network is determined to be in a fault state, the arc suppression coil parameters are immediately adjusted to reduce the fault current, the fault detection sensor is started to locate the fault location, and the fault area is quickly isolated to prevent the fault from spreading. After confirming that the fault area has been powered off and isolated, the arc suppression equipment is stopped, a fault prediction report is generated and an early warning is issued, and staff are dispatched to repair the fault. After the staff has completed the repair and manually confirmed it, the isolation measures of the fault area are withdrawn.

[0049] S3: Dynamically adjust the parameters of the arc extinguishing coil according to the distribution network data and fault prediction report, and perform feedback control on the parameters of the arc extinguishing coil according to the arc extinguishing effect monitored in real time to achieve rapid arc extinguishing and current limiting.

[0050] Furthermore, the parameters of the arc suppression coil are dynamically adjusted, including, when the distribution network is in an abnormal fluctuation state, increasing the damping characteristics of the system by slightly adjusting the inductance to suppress the fluctuation, which is expressed as: , in, represents the adjusted inductance; Indicates the inductance before adjustment; Indicates the adjustment amount.

[0051] When the distribution network is in a potential fault state, the connection mode of the arc suppression coil is changed from parallel to series, and the inductance is adjusted to quickly suppress abnormal fluctuations, which is expressed as: , in, Represents the adjustment factor.

[0052] When the distribution network is in an abnormal current state, the arc extinguishing effect is optimized by adjusting the ratio of inductance and resistance, which is expressed as: , in, represents the adjusted resistance; represents the resistance before adjustment; The deviation amount indicating the abnormal current; Indicates normal current.

[0053] When the distribution network is in a complex abnormal state, the inductance is adjusted and the capacitance is increased to form an LC resonant circuit to absorb current fluctuations, which is expressed as: , , in, represents the adjusted capacitance; Indicates the capacitance before adjustment; Indicates the newly added capacitance value.

[0054] Normally, the extra capacitor CCC is usually not connected to the circuit to avoid unnecessary current resonance under normal operating conditions. In complex abnormal conditions, the capacitor CCC is connected to the circuit by switching the switch to form an LC resonant circuit. The resonant frequency of the LC resonant circuit is It is expressed as: , Wherein, L represents inductance; C represents capacitance; when the current fluctuation frequency is close to the resonant frequency, the LC resonant circuit can effectively absorb the high-frequency component of the current and reduce the current fluctuation.

[0055] When the distribution network is in a fault state, the connection mode of the arc suppression coil is changed from parallel to series, and the inductance is adjusted to quickly suppress abnormal fluctuations. If there is a backup arc suppression device, it is started to provide additional protection. After the fault area is isolated, the arc suppression work is stopped, which is expressed as: , , in, represents the adjustment factor; Indicates the rate of change of current.

[0056] It should be noted that there are two ways to connect arc suppression coils to circuits: series and parallel. Under normal circumstances, arc suppression coils are usually connected in parallel in the power distribution system. This allows them to quickly share the current and reduce the probability of arcing when a fault current occurs in the system.

[0057] In certain situations, such as when higher inductance is required to limit the rate of fault current, a series connection may be chosen, but this approach will increase the inductance of the system during normal operation, affecting system performance.

[0058] Therefore, when the power grid fails or fluctuates greatly, the arc suppression coils are changed to series connection to provide higher inductance, and then switched to parallel connection after the fluctuations decrease to a normal range to ensure system performance.

[0059] Furthermore, the feedback control includes calculating the error between the actual value and the predicted value after adjusting the arc suppression coil parameters, which is expressed as: , in, Indicates time The error of Indicates time The predicted value of Indicates time The actual measured value of When the error increases When the current adjustment range is insufficient, increase , expressed as: , When the error decreases When the current adjustment range is too large, reduce , expressed as: , in, Indicates the new adjustment amount; Represents the adjustment coefficient.

[0060] On the other hand, this embodiment also provides an intelligent arc extinguishing and current limiting system based on dynamic fault prediction, which includes: an acquisition module, which collects distribution network data, performs denoising and data smoothing, and uploads the processed data to a detection module; a detection module, which constructs a combined model of LSTM and GRU to identify and predict current trends, optimizes the prediction accuracy by dynamically adjusting the weights of the weighted average layer, generates a fault prediction report based on the prediction results, locates the fault point and quickly isolates the fault area; an arc extinguishing module, which dynamically adjusts the parameters of the arc extinguishing coil according to the distribution network data and the fault prediction report, and performs feedback control on the parameters of the arc extinguishing coil according to the arc extinguishing effect monitored in real time, so as to achieve rapid arc extinguishing and current limiting.

[0061] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0062] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0063] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0064] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0065] Example 2, below, is an embodiment of the present invention, which provides an intelligent arc extinguishing and current limiting method based on dynamic fault prediction. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0066] PSCAD / EMTDC is used to establish a simulation model of the distribution network, including monitoring nodes for current, voltage and temperature, and a dynamic adjustment model of the arc suppression coil is built in Simulink.

[0067] Run multiple simulations in the simulation model to generate current, voltage, and temperature data under different working conditions. Use Python to denoise the data generated by the simulation (using Kalman filtering) and smooth the data (using sliding window technology).

[0068] Use the deep learning library in Python (such as TensorFlow or PyTorch) to build a fault prediction model that combines LSTM and GRU, and use the preprocessed simulation data as training data to train the fault prediction model.

[0069] The trained fault prediction model is run, and the output of the hidden layer is weighted and combined using the dynamic weights mentioned in the present invention to predict the current trend and the time and location of the fault. The parameters of the arc extinguishing coil are dynamically adjusted according to the prediction results, and the feedback control algorithm is used to monitor the arc extinguishing effect in real time. The experimental data are shown in the following table.

[0070] Table 1 Experimental data table , It can be seen from the table data that in Experiment 2 and Experiment 5, the fault prediction model accurately predicted the fault time and location. The predicted fault time was 130 seconds and 135 seconds, corresponding to node 5 and node 2 respectively. The actual fault time was very close to the predicted time, with an error within ±5 seconds. The prediction of the fault location was also very accurate, verifying that the fault prediction model combining LSTM and GRU performed well in current trend prediction and fault location.

[0071] The inductance and resistance are dynamically adjusted according to the prediction results. For example, in Experiment 2, the inductance adjustment is 12mH and the resistance adjustment is 0.6Ω. The actual current and voltage are effectively controlled after the fault occurs, the current fluctuation is reduced, the voltage is maintained within the normal range, and the arc extinguishing effect is obvious.

[0072] In Experiment 2, after the fault occurred, the current dropped from 52A to 48A, and the voltage dropped from 225V to 215V, indicating that the dynamic adjustment of the arc suppression coil effectively controlled the impact of the fault. In Experiment 5, after the fault occurred, the current dropped from 51A to 45A, and the voltage dropped from 224V to 210V, and the dynamic adjustment was also effective.

[0073] In summary, the method of the present invention achieves accurate prediction and rapid response to distribution network faults by combining an advanced deep learning fault prediction model with a method for dynamically adjusting arc suppression coil parameters, thereby improving the reliability and safety of the power grid. The experimental data fully verifies the effectiveness and practicality of the present invention under different working conditions.

[0074] 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 arc extinguishing and current limiting method based on dynamic fault prediction, characterized in that: include: Collect distribution network data and perform denoising and data smoothing; Predict current trends based on distribution network data, predict the time and location of faults, generate fault prediction reports, locate fault points and quickly isolate fault areas; According to the distribution network data and fault prediction report, the parameters of the arc extinguishing coil are dynamically adjusted, and according to the arc extinguishing effect monitored in real time, the parameters of the arc extinguishing coil are feedback controlled to achieve rapid arc extinguishing and current limiting.

2. The intelligent arc extinguishing and current limiting method based on dynamic fault prediction according to claim 1, characterized in that: The distribution network data includes line current, voltage, temperature data, arc suppression coil working status data and historical data.

3. The intelligent arc extinguishing and current limiting method based on dynamic fault prediction according to claim 2, characterized in that: The current trend prediction includes building a combined model of LSTM and GRU to identify and predict the current trend. The structure of the model is divided into an input layer, an LSTM layer, a GRU layer, a weight calculation layer, a weighted average layer and an output layer. The input layer receives the distribution network data and uploads it to the LSTM layer and the GRU layer for calculation to obtain the hidden state output of the LSTM. And the hidden state output of GRU ; Calculate adaptive weight parameters in the weight calculation layer , using sliding windows to calculate time windows The mean square error within is updated by gradient descent , expressed as: ， ， in, Represents the updated adaptive weight parameters; represents the initial adaptive weight parameter; represents the learning rate; Representation time window The mean square error within ; Indicates the moment; represents the mean square error at time t; At the same time, in the weighted average layer according to the adaptive weight parameter ,Will and Weighted combination, and the combined result is output through the output layer, expressed as: ， in, Indicates time Current prediction value; set the current safety range based on historical data , the threshold value of the current change rate and ,and ; Indicates time Adaptive weight parameters of ; when exist When it is within the range, it means the current is normal; when exist When it is outside the range, it indicates abnormal current; When the predicted value of the current change rate When , it indicates that the current change rate is normal; when When , it indicates that the current change rate is abnormal; when When , it indicates that the current change rate reaches the fault range.

4. The intelligent arc extinguishing and current limiting method based on dynamic fault prediction according to claim 3, characterized in that: The initial adaptive weight parameters Obtained through grid search during model training, setting the initial adaptive weight parameters The value range is , the initial step length is , the number of cross validation folds is ; For each Value, perform a grid search: initialization is 0, the training data set is divided into subsets, for each subset , use Other The combined model is trained using subsets Verify the model and calculate the mean square error ,Will Add to , calculate the average mean square error of all subsets, expressed as: ， in, express The average mean square error of Smallest The value of , zoom out The value range is , the step size is set to , again for each Perform a grid search on the value and calculate , repeat the grid search and shrink The range of steps is up to Achieve target accuracy, output As the initial adaptive weight parameter.

5. The intelligent arc extinguishing and current limiting method based on dynamic fault prediction according to claim 4, characterized in that: The fault prediction report includes, when the current is normal and the current change rate is normal, it is determined that the distribution network is in a normal operating state, the existing arc suppression coil parameters are maintained and no fault prediction report is generated; When the current is normal and the current change rate is abnormal, the distribution network is judged to be in an abnormal fluctuation state, the sampling frequency of the distribution network data is increased, and the arc suppression coil parameters are dynamically adjusted. If the abnormal fluctuation state lasts for more than the preset time threshold , an early warning signal is issued to remind the staff to monitor manually; When the current is normal and the current change rate reaches the fault range, the distribution network is judged to be in a potential fault state, the arc suppression coil parameters are dynamically adjusted, the location of the potential fault is reversely located according to the distribution network data source, a fault prediction report is generated and an early warning is issued; When the current is abnormal and the current change rate is normal, the distribution network is judged to be in an abnormal current state, the sampling frequency of the distribution network data is increased, the arc suppression coil parameters are dynamically adjusted to prevent further abnormal current, and an early warning signal is issued to remind the staff to check the load situation to prevent further deterioration; When the current is abnormal and the current change rate is abnormal, the distribution network is judged to be in a complex abnormal state, the fault detection sensor is activated to scan the complex abnormal area, the arc suppression coil parameters are dynamically adjusted and the auxiliary protection device is activated to prevent the fault from expanding, a fault prediction report is generated and an early warning is issued, and staff are dispatched to conduct on-site confirmation and maintenance; When the current is abnormal and the current change rate reaches the fault range, the distribution network is determined to be in a fault state, the arc suppression coil parameters are immediately adjusted to reduce the fault current, the fault detection sensor is started to locate the fault location, and the fault area is quickly isolated to prevent the fault from spreading. After confirming that the fault area has been powered off and isolated, the arc suppression equipment is stopped, a fault prediction report is generated and an early warning is issued, and staff are dispatched to repair the fault. After the staff has completed the repair and manually confirmed it, the isolation measures of the fault area are withdrawn.

6. The intelligent arc extinguishing and current limiting method based on dynamic fault prediction according to claim 5, characterized in that: The dynamic adjustment of arc suppression coil parameters includes, when the distribution network is in an abnormal fluctuation state, slightly adjusting the inductance to increase the damping characteristics of the system and suppress the fluctuation, which is expressed as: ， in, represents the adjusted inductance; Indicates the inductance before adjustment; Indicates the adjustment amount; When the distribution network is in a potential fault state, the connection mode of the arc suppression coil is changed from parallel to series, and the inductance is adjusted to quickly suppress abnormal fluctuations, which is expressed as: ， in, represents the adjustment factor; When the distribution network is in an abnormal current state, the arc extinguishing effect is optimized by adjusting the ratio of inductance and resistance, which is expressed as: ， in, represents the adjusted resistance; Indicates the resistance before adjustment; The deviation amount indicating the abnormal current; Indicates normal current; When the distribution network is in a complex abnormal state, the inductance is adjusted and the capacitance is increased to form an LC resonant circuit to absorb current fluctuations, which is expressed as: ， ， in, represents the adjusted capacitance; Indicates the capacitance before adjustment; Indicates the newly added capacitance value; When the distribution network is in a fault state, the connection mode of the arc suppression coil is changed from parallel to series, and the inductance is adjusted to quickly suppress abnormal fluctuations. If there is a backup arc suppression device, it is started to provide additional protection. After the fault area is isolated, the arc suppression work is stopped, which is expressed as: ， ， in, represents the adjustment factor; Indicates the rate of change of current.

7. The intelligent arc extinguishing and current limiting method based on dynamic fault prediction according to claim 6, characterized in that: The feedback control includes calculating the error between the actual value and the predicted value after adjusting the arc suppression coil parameters, which is expressed as: ， in, Indicates time The error of Indicates time The predicted value of Indicates time The actual measured value of When the error increases When the current adjustment is insufficient, increase , expressed as: ， When the error decreases When the current adjustment range is too large, reduce , expressed as: ， in, Indicates the new adjustment amount; Represents the adjustment coefficient.

8. An intelligent arc extinguishing and current limiting system based on dynamic fault prediction using the method as claimed in any one of claims 1 to 7, characterized in that: include, The acquisition module collects distribution network data, performs denoising and data smoothing, and uploads the processed data to the detection module; The detection module builds a combined model of LSTM and GRU to identify and predict current trends, optimizes the prediction accuracy by dynamically adjusting the weights of the weighted average layer, generates a fault prediction report based on the prediction results, locates the fault point, and quickly isolates the fault area; The arc extinguishing module dynamically adjusts the parameters of the arc extinguishing coil according to the distribution network data and fault prediction report, and performs feedback control on the parameters of the arc extinguishing coil according to the arc extinguishing effect monitored in real time to achieve rapid arc extinguishing and current limiting.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the intelligent arc extinguishing and current limiting method based on dynamic fault prediction as described in any one of claims 1-7 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 arc extinguishing and current limiting method based on dynamic fault prediction are implemented as described in any one of claims 1-7.

Images