Electronic equipment surge protection control method and system based on overcurrent and overvoltage detection

Abstract

The invention relates to the technical field of surge protection, and discloses an electronic equipment surge protection control method and system based on overcurrent and overvoltage detection. Firstly, an initial electronic equipment current and voltage data set is obtained, an initial bidirectional long-short-term memory neural network model is obtained through training, and an error function is established; secondly, taking the error function as a fitness function, optimizing parameters in the initial bidirectional long-short-term memory neural network model by using an improved snow ablation optimization algorithm, and constructing a final bidirectional long-short-term memory neural network model; inputting an initial current and voltage data set of the electronic equipment to obtain an overcurrent and overvoltage data set of the electronic equipment, and then performing data correction; and finally, setting a safety threshold value, and obtaining a surge protection result of the electronic equipment through comparison, thereby realizing surge protection control of the electronic equipment. By processing and analyzing the current and voltage data of the electronic equipment, the purpose of surge protection control of the electronic equipment is achieved, and the method is objective and accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of surge protection, and in particular to an electronic equipment surge protection control method and system based on overcurrent and overvoltage detection. Background Art

[0002] Traditional surge protection control methods for electronic equipment are difficult to control in real time due to the different sensitivities of different electronic devices, which can easily cause damage to the electronic equipment. At the same time, technologies such as artificial intelligence are not used, and surge voltages require manual monitoring, which not only wastes manpower and material resources, but is also slow in processing surge-related data. When there are potential risks, protective measures cannot be taken in advance to ensure good surge protection effects. Summary of the invention

[0003] In view of the problems in the related art, the present invention provides an electronic device surge protection control method and system based on overcurrent and overvoltage detection to overcome the above-mentioned technical problems existing in the existing related art.

[0004] In order to solve the above technical problems, the present invention is achieved through the following technical solutions: The present invention is a surge protection control method for electronic equipment based on overcurrent and overvoltage detection, comprising the following steps: S1. Acquire the current and voltage of the electronic device to obtain an initial current and voltage data set of the electronic device, train to obtain an initial bidirectional long short-term memory neural network model and a current and voltage error set, and establish an error function according to the current and voltage error set; S2, using the error function as a fitness function, using an improved snow melting optimization algorithm to optimize the parameters in the initial bidirectional long short-term memory neural network model to obtain optimized parameters, and using the optimized parameters to construct a final bidirectional long short-term memory neural network model; S3, inputting the initial electronic equipment current and voltage data set, outputting the current and voltage abnormality identification result, obtaining the electronic equipment overcurrent and overvoltage data set, and then performing data correction to obtain the electronic equipment surge data set; S4. Dynamically set a safety threshold according to the electronic device surge data set, obtain the electronic device surge protection result by comparing the safety threshold, and then add the electronic device circuit protection device to realize the electronic device surge protection control.

[0005] The invention obtains an initial set of electronic device current and voltage data, and trains a bidirectional long short-term memory neural network to obtain an initial bidirectional long short-term memory neural network model, and establishes an error function after calculating the current and voltage errors; compared with other neural networks, it can better handle the timing differences between normal data and abnormal data, where abnormal data is overcurrent and overvoltage data, which is suitable for processing timing data and has good detection effects; secondly, the error function is used as a fitness function, and an improved snow melting optimization algorithm is used to optimize the parameters in the model to obtain the optimized parameters and construct the final bidirectional long short-term memory neural network model; this method optimizes the weights in the model, speeds up the convergence speed of the neural network, and reduces the training time. The improved snow melting optimization algorithm is used to simulate The sublimation and melting phenomenon of simulated snow, combined with heat transfer and condensation strategies, improves the shortcomings of the original population mechanism compared to traditional optimization algorithms, accelerates the convergence speed of the algorithm, and greatly improves the optimization efficiency; combined with the initial electronic equipment current and voltage data set, the electronic equipment overcurrent and overvoltage data set is obtained, and then the data is corrected to obtain the electronic equipment surge data set; this method uses the abnormal data identified by the neural network model as the overcurrent and overvoltage data, the method is simple, and then two data corrections are performed to eliminate equipment collection errors and perform voltage correction to increase data reliability and accuracy; finally, the safety threshold is obtained according to the electronic equipment surge data set, and the electronic equipment circuit protection device is added by comparing the safety threshold to realize electronic equipment surge protection control.

[0006] Preferably, the S1 comprises the following steps: S11, using a current sensor and a voltage sensor to collect current and voltage at different positions of the electronic device, obtain the current data and voltage data of the electronic device, and record the data collection time to obtain the collection time series ,in Indicates m The initial electronic device current and voltage data set is obtained by combining the acquisition time series, the electronic device current data and the electronic device voltage data. ,in Indicates m The current data of the electronic equipment collected at each collection time point, Indicates m The voltage data of the electronic equipment collected at each collection time point; S12, training the bidirectional long short-term memory neural network to obtain an initial bidirectional long short-term memory neural network model and a current and voltage error set, the specific steps are as follows: S121, setting the bidirectional long short-term memory neural network to include a forward long short-term memory neural network and a reverse long short-term memory neural network, dividing the data set to be tested according to the time series, inputting the data set into the bidirectional long short-term memory neural network, and outputting the output value of the forward long short-term memory neural network and the output value of the reverse long short-term memory neural network respectively by setting the forward weight and bias as well as the reverse weight and bias, and merging the output values ​​to obtain the output value of the bidirectional long short-term memory neural network; S122, reacquire a new electronic device current and voltage data set, regard the new electronic device current and voltage data set as a sample data set, and set a collection time point for the sample data set. , the collection time point and collection time point The corresponding electronic device current data and electronic device voltage data are input into the bidirectional long short-term memory neural network, and the acquisition time point is output The corresponding electronic device current output value and electronic device voltage output value, and calculate the acquisition time point The current and voltage errors are obtained by continuously inputting the sample data set until the bidirectional long short-term memory neural network converges, and obtaining the initial bidirectional long short-term memory neural network model and the current and voltage error set; S13. Settings and They represent the first i The current error and i A voltage error is generated, and the current error function and voltage error function are established. The formula is as follows: , ; in, represents the current error function, represents the voltage error function, n Indicates the number of errors; The average of the current error function and the voltage error function is used as the error function.

[0007] The invention obtains an initial bidirectional long short-term memory neural network model by training a bidirectional long short-term memory neural network. Compared with other neural networks, it can better handle the timing differences between normal data and abnormal data. The abnormal data is overcurrent and overvoltage data, which is suitable for processing timing data and has good detection effect. The current and voltage errors are then calculated to establish an error function, which is convenient for subsequent optimization.

[0008] Preferably, S2 comprises the following steps: S21, during the iteration process of the initial bidirectional long short-term memory neural network model, the error function is used as the fitness function, and the parameters in the initial bidirectional long short-term memory neural network model are optimized using the improved snow melting optimization algorithm, the parameters are weights, and the optimized parameters are obtained. The specific steps are as follows: S211. The initial bidirectional long short-term memory neural network model is regarded as a search space in the iterative process. There is a snow population in the search space. The snow individuals in the snow population represent parameters. The dimension of the snow population is j ; The snow population is converted into water vapor at high temperature to obtain a water vapor population. The water vapor individuals in the water vapor population move in Brownian motion, and the heat transfer strategy is used to replace the Brownian motion; set the current number of iterations to b , the thermal attenuation factor is , and Respectively represent random numbers between the interval [0, 1], when When it is less than the thermal attenuation factor, the b The iteration c The individual positions of water vapor are recorded as ; Calculate the b The fitness function values ​​corresponding to the water vapor individuals in the water vapor population at the iteration are sorted in descending order, and a water vapor individual is randomly selected from the water vapor individuals corresponding to the top five fitness function values, and is recorded as At this time, the water vapor population moves to the water vapor individuals with higher fitness function values, which affects the position of the water vapor individuals. Update, the calculation formula is as follows: ; The water vapor individuals in the water vapor population transfer heat to each other, b The iteration c The fitness function value corresponding to the water vapor individual and the b The difference in fitness function values ​​corresponding to other water vapor individuals at the iteration is recorded as ; Set the b The iteration c -1 water vapor individual position is , No. b The iteration c +1 water vapor individual position is , at this time the individual position of water vapor ; S212, compare the fitness function values ​​corresponding to the current water vapor individual positions, find the current optimal fitness function value, and obtain the current optimal parameters at the current optimal fitness function value; the snow population is converted into liquid water at low temperature, and the condensation strategy is used to replace the snow melting process, and the maximum number of iterations is set toB , condensation parameters ;No. b The average position of water vapor individuals at the iteration is recorded as , No. b The optimal position of the water vapor individual at the iteration is recorded as , represents a random number between the interval [-1, 1]. At this time, the individual positions of water vapor are again To update, ; No. b The iteration is over, the entire process of this iteration of the water vapor population is completed, the next generation of water vapor population is generated, and the next iteration is entered. The parameters are continuously updated until the current number of iterations reaches the maximum number of iterations, then the iteration is stopped to obtain the final water vapor population, and the individual water vapor position corresponding to the best fitness function value is regarded as the optimized parameter; S22. During the iteration process of the initial bidirectional long short-term memory neural network model, the optimized parameters are used as the weights of the initial bidirectional long short-term memory neural network model according to the improved snow melting optimization algorithm optimization process to construct the final bidirectional long short-term memory neural network model.

[0009] This invention uses the error function as the fitness function and an improved snow melting optimization algorithm to optimize the parameters in the model, obtains the optimized parameters, optimizes the weights in the model, speeds up the convergence of the neural network, and reduces the training time. The improved snow melting optimization algorithm simulates the sublimation and melting of snow, combines heat transfer and condensation strategies, and improves the shortcomings of the original population mechanism compared to the traditional optimization algorithm, accelerates the convergence speed of the algorithm, and greatly improves the optimization efficiency.

[0010] Preferably, S3 comprises the following steps: S31, setting a collection time point for the initial electronic device current and voltage data set , the collection time point and collection time point The corresponding electronic device current data and electronic device voltage data are input into the final bidirectional long short-term memory neural network model, and the current and voltage anomaly recognition result is output. The current and voltage anomaly recognition result is the acquisition time point The corresponding electronic device current output value and electronic device voltage output value are recorded in sequence to obtain the electronic device current and voltage output value set; A current threshold and a voltage threshold are set, and at the same acquisition time point, the electronic device current and voltage output value set and the initial electronic device current and voltage data set are compared; when the difference between the electronic device current output value in the electronic device current and voltage output value set and the electronic device current data in the initial electronic device current and voltage data set is greater than the current threshold, the corresponding electronic device current data is recorded as electronic device overcurrent data; when the difference between the electronic device voltage output value in the electronic device current and voltage output value set and the electronic device voltage data in the initial electronic device current and voltage data set is greater than the voltage threshold, the corresponding electronic device voltage data is recorded as electronic device overvoltage data, and the electronic device overcurrent and overvoltage data set is formed; S32, performing data correction on the electronic device overcurrent and overvoltage data set to obtain an electronic device surge data set, the specific steps are as follows: S321, performing a first data correction on the electronic device overcurrent and overvoltage data set, counting the collection time points of the electronic device overcurrent data in the electronic device overcurrent and overvoltage data set, and the collection time points of the electronic device overvoltage data in the electronic device overcurrent and overvoltage data set, and when the collection time points of the electronic device overcurrent data and the electronic device overvoltage data are different, deleting the electronic device overcurrent data corresponding to the collection time points of the electronic device overcurrent data, and deleting the electronic device overvoltage data corresponding to the collection time points of the electronic device overvoltage data, to obtain a preliminarily processed electronic device overcurrent and overvoltage data set; S322, performing a second data correction on the preliminarily processed electronic device overcurrent and overvoltage data set, setting sample points on the electronic device, selecting any sample points as the first sample point and the second sample point, respectively, the current direction is from the first sample point to the second sample point; setting the active voltage from the first sample point to the second sample point as , the reactive voltage from the first sample point to the second sample point is , the voltage at the first sample point is , the voltage at the first sample point ; Calculate the voltage at all sample points in turn, set the sample point threshold, and when the difference between the voltage at the sample point and the electronic device overvoltage data in the initially processed electronic device overcurrent and overvoltage data set is greater than the sample point threshold, delete the corresponding electronic device overvoltage data and electronic device overcurrent data; complete data correction, regard the electronic device overcurrent and overvoltage data as surge data, and obtain the electronic device surge data set.

[0011] The invention obtains the electronic equipment overcurrent and overvoltage data set by comparing thresholds, and uses the abnormal data identified by the neural network model as the overcurrent and overvoltage data. The method is simple, and then two data corrections are performed to eliminate the equipment collection errors in space and time and perform voltage correction, thereby increasing data reliability and accuracy and obtaining the electronic equipment surge data set.

[0012] Preferably, S4 comprises the following steps: S41, the electronic device surge data set includes the collection time point and the electronic device overcurrent and overvoltage data, recorded as ,in Indicates g The collection time points, Indicates g The overcurrent data of electronic equipment collected at each collection time point, Indicates g The electronic device overvoltage data collected at each collection time point; calculating the average value of the electronic device overcurrent data and the average value of the electronic device overvoltage data, and using the average value of the electronic device overcurrent data and the average value of the electronic device overvoltage data as a safety threshold; S42. Current is passed through the electronic device again, and the current and voltage are collected in real time. When the current and voltage collected in real time are greater than the safety threshold, a surge occurs in the electronic device, an alarm is sounded, and a surge protection result of the electronic device is obtained. The power supply is automatically cut off or switched to a safe mode, and a circuit protection device is added to the circuit to implement surge protection control of the electronic device.

[0013] The present invention also discloses a system of an electronic device surge protection control method based on overcurrent and overvoltage detection, which specifically includes: an error detection module, a model parameter optimization module, an abnormality identification and data correction module and a surge protection control module; The error detection module is used to construct a neural network model to obtain current and voltage errors and establish an error function; The model parameter optimization module is used to optimize the parameters in the neural network model using an optimization algorithm; The abnormality identification and data correction module is used to identify the overcurrent and overvoltage data set in the current and voltage data set of the electronic equipment, and then perform data correction; The surge protection control module is used to compare the safety threshold to obtain the electronic equipment surge protection result, so as to realize the electronic equipment surge protection control.

[0014] The present invention has the following beneficial effects: 1. The invention obtains an initial bidirectional long short-term memory neural network model by training a bidirectional long short-term memory neural network. Compared with other neural networks, it can better handle the timing differences between normal data and abnormal data, where abnormal data is overcurrent and overvoltage data, which is suitable for processing timing data and has good detection effect. The current and voltage errors are then calculated to establish an error function, which is convenient for subsequent optimization.

[0015] 2. The invention uses the error function as the fitness function and the improved snow melting optimization algorithm to optimize the parameters in the model, obtains the optimized parameters, optimizes the weights in the model, accelerates the convergence speed of the neural network, and reduces the training time. The improved snow melting optimization algorithm simulates the sublimation and melting of snow and combines heat transfer and condensation strategies. Compared with the traditional optimization algorithm, it improves the shortcomings of the original population mechanism, accelerates the convergence speed of the algorithm, and greatly improves the optimization efficiency.

[0016] 3. The invention obtains the overcurrent and overvoltage data set of the electronic equipment by comparing the threshold values, and uses the abnormal data identified by the neural network model as the overcurrent and overvoltage data. The method is simple, and then two data corrections are performed to eliminate the equipment collection errors in space and time and perform voltage correction, thereby increasing data reliability and accuracy, and obtaining the electronic equipment surge data set.

[0017] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0019] Figure 1 A schematic diagram of the flow of surge protection control of electronic equipment by an electronic equipment surge protection control system based on overcurrent and overvoltage detection provided by the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0022] Example 1 Please refer to Figure 1The present invention provides an electronic device surge protection control method based on overcurrent and overvoltage detection, comprising the following steps: S1. Acquire the current and voltage of the electronic device to obtain an initial current and voltage data set of the electronic device, train to obtain an initial bidirectional long short-term memory neural network model and a current and voltage error set, and establish an error function according to the current and voltage error set; The S1 comprises the following steps: S11, using a current sensor and a voltage sensor to collect current and voltage at different positions of the electronic device, obtain the current data and voltage data of the electronic device, and record the data collection time to obtain the collection time series ,in Indicates m The initial electronic device current and voltage data set is obtained by combining the acquisition time series, the electronic device current data and the electronic device voltage data. ,in Indicates m The current data of the electronic equipment collected at each collection time point, Indicates m The voltage data of the electronic equipment collected at each collection time point; S12, training the bidirectional long short-term memory neural network to obtain an initial bidirectional long short-term memory neural network model and a current and voltage error set, the specific steps are as follows: S121, setting the bidirectional long short-term memory neural network to include a forward long short-term memory neural network and a reverse long short-term memory neural network, dividing the data set to be tested according to the time series, inputting the data set into the bidirectional long short-term memory neural network, and outputting the output value of the forward long short-term memory neural network and the output value of the reverse long short-term memory neural network respectively by setting the forward weight and bias as well as the reverse weight and bias, and merging the output values ​​to obtain the output value of the bidirectional long short-term memory neural network; S122, reacquire a new electronic device current and voltage data set, regard the new electronic device current and voltage data set as a sample data set, and set a collection time point for the sample data set. , the collection time point and collection time point The corresponding electronic device current data and electronic device voltage data are input into the bidirectional long short-term memory neural network, and the acquisition time point is output The corresponding electronic device current output value and electronic device voltage output value, and calculate the acquisition time point The current and voltage errors are obtained by continuously inputting the sample data set until the bidirectional long short-term memory neural network converges, and obtaining the initial bidirectional long short-term memory neural network model and the current and voltage error set; S13. Settings and They represent the first i The current error and i A voltage error is generated, and the current error function and voltage error function are established. The formula is as follows: , ; in, represents the current error function, represents the voltage error function, n Indicates the number of errors; Taking the mean of the current error function and the voltage error function as the error function; S2, using the error function as a fitness function, using an improved snow melting optimization algorithm to optimize the parameters in the initial bidirectional long short-term memory neural network model to obtain optimized parameters, and using the optimized parameters to construct a final bidirectional long short-term memory neural network model; The S2 comprises the following steps: S21, during the iteration process of the initial bidirectional long short-term memory neural network model, the error function is used as the fitness function, and the parameters in the initial bidirectional long short-term memory neural network model are optimized using the improved snow melting optimization algorithm, the parameters are weights, and the optimized parameters are obtained. The specific steps are as follows: S211. The initial bidirectional long short-term memory neural network model is regarded as a search space in the iterative process. There is a snow population in the search space. The snow individuals in the snow population represent parameters. The dimension of the snow population is j ; The snow population is converted into water vapor at high temperature to obtain a water vapor population. The water vapor individuals in the water vapor population move in Brownian motion, and the heat transfer strategy is used to replace the Brownian motion; set the current number of iterations to b The thermal attenuation factor is , and Respectively represent random numbers between the interval [0, 1], when When it is less than the thermal attenuation factor, the b The first iteration c The individual positions of water vapor are recorded as ; Calculate the b The fitness function values ​​corresponding to the water vapor individuals in the water vapor population at the iteration are sorted in descending order, and a water vapor individual is randomly selected from the water vapor individuals corresponding to the top five fitness function values, and is recorded as At this time, the water vapor population moves to the water vapor individuals with higher fitness function values, which affects the position of the water vapor individuals. Update, the calculation formula is as follows: ; The water vapor individuals in the water vapor population transfer heat to each other, b The first iteration c The fitness function value corresponding to the water vapor individual and the b The difference in fitness function values ​​corresponding to other water vapor individuals at the iteration is recorded as ; Set the b The first iteration c -1 water vapor individual position is , No. b The first iteration c +1 water vapor individual position is , at this time the individual position of water vapor ; S212, compare the fitness function values ​​corresponding to the current water vapor individual positions, find the current optimal fitness function value, and obtain the current optimal parameters at the current optimal fitness function value; the snow population is converted into liquid water at low temperature, and the condensation strategy is used to replace the snow melting process, and the maximum number of iterations is set to B , condensation parameters ;No. b The average position of water vapor individuals at the iteration is recorded as , No. b The optimal position of the water vapor individual at the iteration is recorded as , represents a random number between the interval [-1, 1]. At this time, the individual positions of water vapor are again To update, ; No. b The iteration is over, the entire process of this iteration of the water vapor population is completed, the next generation of water vapor population is generated, and the next iteration is entered. The parameters are continuously updated until the current number of iterations reaches the maximum number of iterations, then the iteration is stopped to obtain the final water vapor population, and the individual water vapor position corresponding to the best fitness function value is regarded as the optimized parameter; S22, during the iteration process of the initial bidirectional long short-term memory neural network model, according to the optimization process of the improved snow melting optimization algorithm, the optimized parameters are used as the weights of the initial bidirectional long short-term memory neural network model to construct a final bidirectional long short-term memory neural network model; S3, inputting the initial electronic equipment current and voltage data set, outputting the current and voltage abnormality identification result, obtaining the electronic equipment overcurrent and overvoltage data set, and then performing data correction to obtain the electronic equipment surge data set; The S3 comprises the following steps: S31, setting a collection time point for the initial electronic device current and voltage data set , the collection time point and collection time point The corresponding electronic device current data and electronic device voltage data are input into the final bidirectional long short-term memory neural network model, and the current and voltage anomaly recognition result is output. The current and voltage anomaly recognition result is the acquisition time point The corresponding electronic device current output value and electronic device voltage output value are recorded in sequence to obtain the electronic device current and voltage output value set; A current threshold and a voltage threshold are set, and at the same acquisition time point, the electronic device current and voltage output value set and the initial electronic device current and voltage data set are compared; when the difference between the electronic device current output value in the electronic device current and voltage output value set and the electronic device current data in the initial electronic device current and voltage data set is greater than the current threshold, the corresponding electronic device current data is recorded as electronic device overcurrent data; when the difference between the electronic device voltage output value in the electronic device current and voltage output value set and the electronic device voltage data in the initial electronic device current and voltage data set is greater than the voltage threshold, the corresponding electronic device voltage data is recorded as electronic device overvoltage data, and the electronic device overcurrent and overvoltage data set is formed; S32, performing data correction on the electronic device overcurrent and overvoltage data set to obtain an electronic device surge data set, the specific steps are as follows: S321, performing a first data correction on the electronic device overcurrent and overvoltage data set, counting the collection time points of the electronic device overcurrent data in the electronic device overcurrent and overvoltage data set, and the collection time points of the electronic device overvoltage data in the electronic device overcurrent and overvoltage data set, and when the collection time points of the electronic device overcurrent data and the electronic device overvoltage data are different, deleting the electronic device overcurrent data corresponding to the collection time points of the electronic device overcurrent data, and deleting the electronic device overvoltage data corresponding to the collection time points of the electronic device overvoltage data, to obtain a preliminarily processed electronic device overcurrent and overvoltage data set; S322, performing a second data correction on the preliminarily processed electronic device overcurrent and overvoltage data set, setting sample points on the electronic device, selecting any sample points as the first sample point and the second sample point, respectively, the current direction is from the first sample point to the second sample point; setting the active voltage from the first sample point to the second sample point as , the reactive voltage from the first sample point to the second sample point is , the voltage at the first sample point is , the voltage at the first sample point ; Calculate the voltage at all sample points in sequence, set the sample point threshold, and when the difference between the voltage at the sample point and the electronic device overvoltage data in the initially processed electronic device overcurrent and overvoltage data set is greater than the sample point threshold, delete the corresponding electronic device overvoltage data and electronic device overcurrent data; complete data correction, regard the electronic device overcurrent and overvoltage data as surge data, and obtain the electronic device surge data set; S4, dynamically setting a safety threshold according to the electronic device surge data set, obtaining an electronic device surge protection result by comparing the safety threshold, and then adding an electronic device circuit protection device to implement electronic device surge protection control; The S4 comprises the following steps: S41, the electronic device surge data set includes the collection time point and the electronic device overcurrent and overvoltage data, recorded as ,in Indicates g The collection time points, Indicates g The overcurrent data of electronic equipment collected at each collection time point, Indicates g The electronic device overvoltage data collected at each collection time point; calculating the average value of the electronic device overcurrent data and the average value of the electronic device overvoltage data, and using the average value of the electronic device overcurrent data and the average value of the electronic device overvoltage data as a safety threshold; S42. Current is passed through the electronic device again, and the current and voltage are collected in real time. When the current and voltage collected in real time are greater than the safety threshold, a surge occurs in the electronic device, an alarm is sounded, and a surge protection result of the electronic device is obtained. The power supply is automatically cut off or switched to a safe mode, and a circuit protection device is added to the circuit to implement surge protection control of the electronic device.

[0023] Example 2 The present invention also discloses a system of an electronic device surge protection control method based on overcurrent and overvoltage detection, which specifically includes: an error detection module, a model parameter optimization module, an abnormality identification and data correction module and a surge protection control module; The error detection module is used to construct a neural network model to obtain current and voltage errors and establish an error function; The model parameter optimization module is used to optimize the parameters in the neural network model using an optimization algorithm; The abnormality identification and data correction module is used to identify the overcurrent and overvoltage data set in the current and voltage data set of the electronic equipment, and then perform data correction; The surge protection control module is used to compare the safety threshold to obtain the electronic equipment surge protection result, so as to realize the electronic equipment surge protection control.

[0024] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0025] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. An electronic equipment surge protection control method based on overcurrent and overvoltage detection, characterized in that: The steps include: S1. Acquire the current and voltage of the electronic device to obtain an initial current and voltage data set of the electronic device, train to obtain an initial bidirectional long short-term memory neural network model and a current and voltage error set, and establish an error function according to the current and voltage error set; S2, using the error function as a fitness function, optimizing the parameters in the initial bidirectional long short-term memory neural network model to obtain optimized parameters, and using the optimized parameters to construct a final bidirectional long short-term memory neural network model; S3, inputting the initial electronic equipment current and voltage data set, outputting the current and voltage abnormality identification result, obtaining the electronic equipment overcurrent and overvoltage data set, and then performing data correction to obtain the electronic equipment surge data set; S4. Dynamically set a safety threshold according to the electronic device surge data set, obtain the electronic device surge protection result by comparing the safety threshold, and then add the electronic device circuit protection device to realize the electronic device surge protection control.

2. The electronic device surge protection control method based on overcurrent and overvoltage detection according to claim 1 is characterized in that: The S1 comprises the following steps: S11, collecting the current and voltage of the electronic device to obtain the electronic device current data and the electronic device voltage data, and recording the data collection time to obtain a collection time series to form an initial electronic device current and voltage data set; S12, training a bidirectional long short-term memory neural network to obtain an initial bidirectional long short-term memory neural network model and a current and voltage error set; S13, obtaining a current error function and a voltage error function according to the current and voltage error set, The average of the current error function and the voltage error function is used as the error function.

3. The electronic equipment surge protection control method based on overcurrent and overvoltage detection according to claim 2 is characterized in that: The S12 comprises the following steps: S121, setting the bidirectional long short-term memory neural network to include a forward long short-term memory neural network and a reverse long short-term memory neural network, dividing the data set to be tested according to the time series, inputting the data set into the bidirectional long short-term memory neural network, and outputting the output value of the forward long short-term memory neural network and the output value of the reverse long short-term memory neural network respectively by setting the forward weight and bias as well as the reverse weight and bias, and merging the output values ​​to obtain the output value of the bidirectional long short-term memory neural network; S122, reacquire a new electronic device current and voltage data set, regard the new electronic device current and voltage data set as a sample data set, and set a collection time point for the sample data set. , the collection time point and collection time point The corresponding electronic device current data and electronic device voltage data are input into the bidirectional long short-term memory neural network, and the acquisition time point is output The corresponding electronic device current output value and electronic device voltage output value, and calculate the acquisition time point The current and voltage errors are obtained by continuously inputting the sample data set until the bidirectional long short-term memory neural network converges, and obtaining the initial bidirectional long short-term memory neural network model and the current and voltage error set.

4. The electronic device surge protection control method based on overcurrent and overvoltage detection according to claim 3 is characterized in that: The S2 comprises the following steps: S21, during the iteration process of the initial bidirectional long short-term memory neural network model, the error function is used as a fitness function, and the parameters in the initial bidirectional long short-term memory neural network model are optimized using an improved snow melting optimization algorithm, wherein the parameters are weights, to obtain optimized parameters; S22. During the iteration process of the initial bidirectional long short-term memory neural network model, the optimized parameters are used as the weights of the initial bidirectional long short-term memory neural network model according to the improved snow melting optimization algorithm optimization process to construct the final bidirectional long short-term memory neural network model.

5. The electronic equipment surge protection control method based on overcurrent and overvoltage detection according to claim 4 is characterized in that: The S21 comprises the following steps: S211. The initial bidirectional long short-term memory neural network model is regarded as a search space in the iterative process. There is a snow population in the search space. The snow individuals in the snow population represent parameters. The dimension of the snow population is j ; The snow population is converted into water vapor at high temperature to obtain a water vapor population. The water vapor individuals in the water vapor population move in Brownian motion, and the heat transfer strategy is used to replace the Brownian motion; set the current number of iterations to b The thermal attenuation factor is , and Respectively represent random numbers between the interval [0, 1], when When it is less than the thermal attenuation factor, the b The iteration c The individual positions of water vapor are recorded as ; Calculate the b The fitness function values ​​corresponding to the water vapor individuals in the water vapor population at the iteration are sorted in descending order, and a water vapor individual is randomly selected from the water vapor individuals corresponding to the top five fitness function values, and is recorded as At this time, the water vapor population moves to the water vapor individuals with higher fitness function values, which affects the position of the water vapor individuals. Update, the calculation formula is as follows: ； The water vapor individuals in the water vapor population transfer heat to each other, b The first iteration c The fitness function value corresponding to the water vapor individual and the b The difference in fitness function values ​​corresponding to other water vapor individuals at the iteration is recorded as ; Set the b The first iteration c -1 water vapor individual position is , No. b The first iteration c +1 water vapor individual position is , at this time the individual position of water vapor ; S212, compare the fitness function values ​​corresponding to the current water vapor individual positions, find the current optimal fitness function value, and obtain the current optimal parameters at the current optimal fitness function value; the snow population is converted into liquid water at low temperature, and the condensation strategy is used to replace the snow melting process, and the maximum number of iterations is set to B , condensation parameters ; No. b The average position of water vapor individuals at the iteration is recorded as , No. b The optimal position of the water vapor individual at the iteration is recorded as , represents a random number between the interval [-1, 1]. At this time, the individual positions of water vapor are again To update, ; No. b The iteration is over, and the entire iteration process of the water vapor population is completed. The next generation of water vapor population is generated, and the next iteration is entered. The parameters are continuously updated until the current number of iterations reaches the maximum number of iterations. The iteration is stopped to obtain the final water vapor population, and the individual position of water vapor corresponding to the best fitness function value is regarded as the optimized parameter.

6. The electronic equipment surge protection control method based on overcurrent and overvoltage detection according to claim 5 is characterized in that: The S3 comprises the following steps: S31, the initial electronic device current and voltage data set is input into the final bidirectional long short-term memory neural network model, and the current and voltage anomaly recognition result is output to obtain the electronic device current and voltage output value set; Setting a current threshold and a voltage threshold, comparing the electronic device current and voltage output value set with the current threshold and the voltage threshold respectively, finding the electronic device overcurrent data and the electronic device overvoltage data, Form an over-current and over-voltage data set for electronic equipment; S32: Perform data correction on the electronic device overcurrent and overvoltage data set to obtain an electronic device surge data set.

7. The electronic equipment surge protection control method based on overcurrent and overvoltage detection according to claim 6 is characterized in that: The S32 comprises the following steps: S321, performing a first data correction on the electronic device overcurrent and overvoltage data set, and screening the electronic device overcurrent and overvoltage data set to obtain a preliminarily processed data set by comparing the collection time points of the electronic device overcurrent and overvoltage data set; S322, performing a second data correction on the electronic device overcurrent and overvoltage data set that has been preliminarily processed, setting sample points on the electronic device, correcting the voltage at the sample points, treating the electronic device overcurrent and overvoltage data as surge data, and obtaining the electronic device surge data set.

8. The electronic equipment surge protection control method based on overcurrent and overvoltage detection according to claim 7 is characterized in that: The S4 comprises the following steps: S41, for the electronic device surge data set, taking the average value of the electronic device overcurrent data and the average value of the electronic device overvoltage data as a safety threshold; S42. Current is passed through the electronic device again, and the current and voltage are collected in real time. When the current and voltage collected in real time are greater than the safety threshold, a surge occurs in the electronic device, an alarm is sounded, and a surge protection result of the electronic device is obtained. The power supply is automatically cut off or switched to a safe mode, and a circuit protection device is added to the circuit to implement surge protection control of the electronic device.

9. A system for implementing the electronic device surge protection control method based on overcurrent and overvoltage detection as claimed in any one of claims 1 to 8, characterized in that: Specifically include: Error detection module, model parameter optimization module, anomaly identification and data correction module and surge protection control module; The error detection module is used to construct a neural network model to obtain current and voltage errors and establish an error function; The model parameter optimization module is used to optimize the parameters in the neural network model using an optimization algorithm; The abnormality identification and data correction module is used to identify the overcurrent and overvoltage data set in the current and voltage data set of the electronic equipment, and then perform data correction; The surge protection control module is used to compare the safety threshold to obtain the electronic equipment surge protection result, so as to realize the electronic equipment surge protection control.

Images