Storage battery intelligent monitoring system

Abstract

The invention discloses an intelligent storage battery monitoring system, and relates to the technical field of storage battery monitoring. Historical data of a storage battery is collected, a sample set is constructed based on the collected historical data of the storage battery, the historical data of the storage battery in the sample set is processed through a data processing method, and after processing is completed, the storage battery is monitored. Analyzing the processed historical data of the storage battery through a data analysis method to obtain analyzed historical data of the storage battery, training the analyzed historical data of the storage battery through a genetic algorithm, and determining a normal working range of the storage battery; and finally, the battery data monitored in real time is intelligently judged based on the determined normal working range of the storage battery, and the storage battery is controlled based on a judgment result, so that the accuracy of intelligent monitoring of the storage battery is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery monitoring, and in particular to an intelligent battery monitoring system. Background Art

[0002] The existing online battery monitoring technology mainly monitors the discharge voltage and internal resistance of the battery. Although it has certain monitoring and alarm functions, it has certain limitations; the data monitoring is not comprehensive, resulting in deviations in the judgment of battery performance.

[0003] Prior art, such as an invention patent application with announcement number: CN116381497A, discloses a vehicle battery monitoring system, and the method thereof includes: a first detection module, the first detection module includes a positive probe assembly and a negative probe assembly, and is used to detect the voltage and current of the battery; a second detection module, the second detection module includes at least one temperature sensor, and is used to detect the temperature of the battery; a processing module, the processing module is used to determine the status information of the battery according to the voltage, the current and the temperature, and determine the recommended information for the battery based on the status information, the status information includes the actual operating status and life status of the battery, and the recommended information is used to guide the user to use the battery; a display module, the display module is used to display the status information and the recommended information.

[0004] It can be seen from the above scheme that the current battery monitoring system mainly monitors the discharge voltage, current and temperature of the battery, but because the battery status is calculated based on the current data, environmental factors are ignored, and single data is prone to misjudgment, which has great limitations. The present invention integrates multiple sets of recent battery data to estimate the battery status, and judges the battery status data collected in real time, thereby improving the accuracy of battery status monitoring. Summary of the invention

[0005] The purpose of the present invention is to provide a battery intelligent monitoring system, which solves the problem in the background technology that data monitoring is incomplete, resulting in deviations in the judgment of battery performance.

[0006] In order to solve the technical problem that the above data monitoring is not comprehensive, resulting in deviation in the judgment of battery performance, the present invention adopts the following technical solution: The present invention provides a battery intelligent monitoring method, which specifically includes the following steps: S1. Collecting battery historical data, and building a sample set based on the collected battery historical data; S2. Processing the battery historical data in the sample set by a data processing method to obtain processed battery historical data; S3, analyzing the processed battery historical data by a data analysis method to obtain analyzed battery historical data; S31, calculating the battery capacity of the battery based on the processed battery historical data; S32, analyzing the charging process and discharging process of the battery based on the processed battery historical data, and outputting the charging parameters and discharging parameters of the battery after analysis; S33, summarizing the calculated battery capacity, charging parameters, and discharging parameters to obtain analyzed battery history data; S4, training the analyzed battery historical data to determine the normal working range of the battery; S5. Collect battery data in real time, make intelligent judgments on the real-time monitored battery data based on the determined normal working range of the battery, and control the battery based on the judgment results.

[0007] The present invention collects battery historical data, builds a sample set based on the collected battery historical data, processes the battery historical data in the sample set through a data processing method, analyzes the processed battery historical data through a data analysis method after the processing, obtains analyzed battery historical data, and trains the analyzed battery historical data through a genetic algorithm to determine the normal working range of the battery; finally, based on the determined normal working range of the battery, intelligent judgment is made on the battery data monitored in real time, and the battery is controlled based on the judgment result, thereby improving the accuracy of intelligent monitoring of the battery.

[0008] Preferably, the collecting of battery historical data and constructing a sample set based on the collected battery historical data comprises the following steps: The historical data of the battery includes the battery number, battery charging stage data and battery discharging stage data; The battery charging stage data includes: battery charging voltage, battery charging current and battery charging stage temperature; The battery discharge stage data includes: battery discharge voltage, battery discharge current and battery discharge stage temperature.

[0009] Preferably, the method of processing the battery historical data in the sample set by a data processing method to obtain the processed battery historical data comprises the following steps: The battery historical data in the sample set is processed by the data standardization method as follows: ; in, Indicates the minimum value of the battery historical data in the sample set, Indicates the maximum value of the battery historical data in the sample set, Indicates the sample set Battery history data, Indicates the standardized battery history data.

[0010] The present invention processes the battery historical data in the sample set through a data standardization method, and improves the reliability of the battery historical data in the sample set through the data standardization method, thereby ensuring the accuracy of the battery intelligent monitoring.

[0011] Preferably, the calculating the battery capacity of the battery based on the processed battery historical data comprises the following steps: Summarize the battery charging stage data in the last 10 groups of processed battery history data; The charging process from the time when the battery is plugged in to the time when the charger is unplugged after the battery is fully charged is considered as one charging process, and the charging process data generated during this period are considered as the same set of charging data; A charging time threshold is set. When the time interval between two sets of charging data is less than the charging time threshold, the two sets of charging data are aggregated into one set of charging data. Calculate the total battery capacity based on the collected charging data; The total battery capacity is calculated as follows: ; in, It represents the current value collected every minute, and T represents the total charging time.

[0012] Preferably, analyzing the charging process and discharging process of the battery based on the processed battery historical data and outputting the charging parameters and discharging parameters of the battery after analysis includes the following steps: S321, analyzing the charging process of the battery; S322. Analyze the discharge process of the battery.

[0013] Preferably, the analyzing the charging process of the battery comprises the following steps: Constructing a battery charging current curve, a battery charging voltage curve, and a battery charging temperature curve based on the processed battery historical data; The formula for constructing the battery charging current curve is as follows; Summarize the charging current data of the last 10 sets of battery charging stage data, and perform fitting analysis on the selected data by Gaussian fitting; The Gaussian fitting expression is as follows: ; Where n represents the order of Gaussian fitting, represents the height of curve i, represents the coordinates of the center position of curve i on the x-axis, represents the width of curve i, represents the battery charging current curve after fitting; The formula for constructing the battery charging voltage curve is as follows: Set the resistance R during charging process to be constant; ; in, Represents the constructed battery charging voltage curve; The formula for constructing the battery charging temperature curve is as follows: ; in, represents the constructed battery charging temperature curve, The weight of the relationship between temperature, current and voltage during battery charging. Indicates the initial temperature.

[0014] Preferably, the analyzing the discharge process of the battery comprises the following steps: Constructing a battery discharge current curve, a battery discharge voltage curve, and a battery discharge temperature curve based on the processed battery historical data; The formula for constructing the battery discharge current curve is as follows; Summarize the discharge current data of the last 10 sets of battery discharge stage data, and perform fitting analysis on the selected data by Gaussian fitting; The Gaussian fitting expression is as follows: ; Where n represents the order of Gaussian fitting, represents the height of curve i, represents the coordinates of the center position of curve i on the x-axis, represents the width of curve i, represents the fitted battery current curve; The formula for constructing the battery voltage curve is as follows: Set the internal resistance of the battery during discharge Constant; ; in, represents the constructed battery discharge voltage curve; The formula for constructing the battery charging temperature curve is as follows: ; in, represents the constructed battery discharge temperature curve, is the weight of the relationship between temperature, current and voltage during battery discharge, Indicates the initial temperature.

[0015] The present invention summarizes the battery charging stage data and the battery discharging stage data in the most recent 10 groups of processed battery historical data, and constructs voltage, current and temperature curves through Gaussian fitting and the relationship between voltage, current and temperature; at the same time, the total battery capacity is calculated based on the collected charging data, providing a quantitative result for battery monitoring and improving the effectiveness of battery intelligent monitoring.

[0016] Preferably, the training of the analyzed battery historical data to determine the normal working range of the battery includes the following steps: S41, initializing the analyzed battery historical data, performing chromosome encoding on the analyzed battery historical data based on a hybrid genetic algorithm, and constructing a population set; Set each set of chromosome encoding to represent a set of battery history data, set the population size, and the maximum number of iterations .

[0017] S42, setting a fitness function of the battery historical data based on the constructed population set size; Set the fitness function: ; in, A fitness function representing the battery's historical data; S43, genetic operator selection operation; Assume the probability of chromosome encoding being selected to be ; ; in, is the population size, is the fitness encoded by the kth chromosome, Represents the kth chromosome code in the population set.

[0018] S44, chromosome crossover operation; A crossover point is randomly selected from the chromosome codes in the population set, and the chromosome code segments between the crossover points are exchanged to form a new chromosome code, thereby forming a new population; Remove duplicate chromosome codes in order and ensure that the length of chromosome codes is consistent to form daughter chromosomes; S45, chromosome mutation operation; The mutation process is to replace the gene fragment of the parent chromosome to produce a chromosome code different from the parent; based on the set mutation probability Mutate the parent chromosome code, thereby producing a new generation of daughter chromosomes; The fitness of all offspring chromosomes is calculated. If the offspring is better than the parent, the parent chromosome code is replaced. Otherwise, if the parent is better, it means that the mutation has failed, and the parent is selected to continue the iteration operation.

[0019] S46, output the optimal solution to the problem; Set the iteration threshold Y, set the iteration If the chromosome codes output after the last iteration remain unchanged or when the hybrid genetic algorithm reaches the set maximum number of iterations, the hybrid genetic algorithm is terminated and the multiple sets of chromosome codes output for the last time are used as the normal working range of the battery.

[0020] The present invention uses a genetic algorithm to set genetic chromosome coding and continuously iterate to respectively determine the normal operating range of the battery charging stage and the discharging stage, thereby improving the intelligence of battery monitoring.

[0021] Preferably, the real-time collection of battery data, intelligent judgment of the real-time monitored battery data based on the determined normal working range of the battery, and control of the battery based on the judgment result include the following steps: Thresholds of various parameters of the battery are set based on the determined normal operating range of the battery, and when the threshold set by the battery data collected in real time is reached, the operation of the battery is stopped immediately.

[0022] The present invention sets the thresholds of various battery parameters based on the determined normal working range of the battery, monitors the battery status parameters in real time, and compares the real-time monitored battery status parameters with the set thresholds, thereby improving the accuracy of battery status monitoring and judgment.

[0023] In order to solve the above technical problems, the present invention also adopts the following technical solution: the battery intelligent monitoring system is used to implement a battery intelligent monitoring method, and the system includes: a data collection module, a data processing module, a data analysis module, a data training module and a real-time monitoring control module; The data collection module is used to collect battery historical data and battery real-time monitoring data; The data processing module is used to process the collected battery historical data and battery real-time monitoring data; The data analysis module is used to analyze the processed battery historical data to obtain the analyzed battery historical data; The data training module is used to train the historical data of the analyzed battery to determine the normal working range of the battery; The real-time monitoring and control module is used to monitor and control the battery according to the determined normal working range of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art 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 paying creative work.

[0025] Figure 1 The figure is a flow chart of the intelligent battery monitoring method of the present invention. DETAILED DESCRIPTION

[0026] 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.

[0027] In a specific embodiment of the present invention, Reference Figure 1 As shown, the present invention provides a battery intelligent monitoring method, comprising the following steps: S1. Collecting battery historical data, and building a sample set based on the collected battery historical data; S2. Processing the battery historical data in the sample set by a data processing method to obtain processed battery historical data; S3, analyzing the processed battery historical data by a data analysis method to obtain analyzed battery historical data; S31, calculating the battery capacity of the battery based on the processed battery historical data; S32, analyzing the charging process and discharging process of the battery based on the processed battery historical data, and outputting the charging parameters and discharging parameters of the battery after analysis; S33, summarizing the calculated battery capacity, charging parameters, and discharging parameters to obtain analyzed battery history data; S4, training the analyzed battery historical data to determine the normal working range of the battery; S5. Collect battery data in real time, make intelligent judgments on the real-time monitored battery data based on the determined normal working range of the battery, and control the battery based on the judgment results.

[0028] Further, refer to Figure 1 As shown, collecting battery historical data and constructing a sample set based on the collected battery historical data includes the following steps: The historical data of the battery includes the battery number, battery charging stage data and battery discharging stage data; The battery charging stage data includes: battery charging voltage, battery charging current and battery charging stage temperature; The battery discharge stage data includes: battery discharge voltage, battery discharge current and battery discharge stage temperature; Further, refer to Figure 1 As shown, the battery historical data in the sample set is processed by the data processing method to obtain the processed battery historical data, including the following steps: The battery historical data in the sample set is processed by the data standardization method as follows: ; in, Indicates the minimum value of the battery historical data in the sample set, Indicates the maximum value of the battery historical data in the sample set, Indicates the sample set Battery history data, Indicates the standardized battery history data; Further, refer to Figure 1 As shown, calculating the battery capacity of the battery based on the processed battery history data includes the following steps: Summarize the battery charging stage data in the last 10 groups of processed battery history data; The charging process from the time when the battery is plugged in to the time when the charger is unplugged after the battery is fully charged is considered as one charging process, and the charging process data generated during this period are considered as the same set of charging data; Furthermore, a charging time threshold is set, and when it is monitored that the time interval between two sets of charging data is less than the charging time threshold, the two sets of charging data are aggregated into one set of charging data; Further, calculating the total capacity of the battery based on the collected charging data; The total battery capacity is calculated as follows: ; in, It represents the current value collected every minute, and T represents the total charging time; Further, refer to Figure 1 As shown, analyzing the charging process and discharging process of the battery based on the processed battery history data and outputting the charging parameters and discharging parameters of the battery after analysis includes the following steps: S321, analyzing the charging process of the battery; Constructing a battery charging current curve, a battery charging voltage curve, and a battery charging temperature curve based on the processed battery historical data; The formula for constructing the battery charging current curve is as follows; Summarize the charging current data of the last 10 sets of battery charging stage data, and perform fitting analysis on the selected data by Gaussian fitting; The Gaussian fitting expression is as follows: ; Where n represents the order of Gaussian fitting, represents the height of curve i, represents the coordinates of the center position of curve i on the x-axis, represents the width of curve i, represents the battery charging current curve after fitting; The formula for constructing the battery charging voltage curve is as follows: Set the resistance R during charging process to be constant; ; in, Represents the constructed battery charging voltage curve; The formula for constructing the battery charging temperature curve is as follows: ; in, represents the constructed battery charging temperature curve, The weight of the relationship between temperature, current and voltage during battery charging. represents the initial temperature; S322, analyzing the discharge process of the battery; Constructing a battery discharge current curve, a battery discharge voltage curve, and a battery discharge temperature curve based on the processed battery historical data; The formula for constructing the battery discharge current curve is as follows; Summarize the discharge current data of the last 10 sets of battery discharge stage data, and perform fitting analysis on the selected data by Gaussian fitting; The Gaussian fitting expression is as follows: ; Where n represents the order of Gaussian fitting, represents the height of curve i, represents the coordinates of the center position of curve i on the x-axis, represents the width of curve i, represents the fitted battery current curve; The formula for constructing the battery voltage curve is as follows: Set the internal resistance of the battery during discharge Constant; ; in, represents the constructed battery discharge voltage curve; The formula for constructing the battery charging temperature curve is as follows: ; in, represents the constructed battery discharge temperature curve, is the weight of the relationship between temperature, current and voltage during battery discharge, represents the initial temperature; Further, refer to Figure 1 As shown, training the analyzed battery historical data to determine the normal working range of the battery includes the following steps: S41, initializing the analyzed battery historical data, performing chromosome encoding on the analyzed battery historical data based on a hybrid genetic algorithm, and constructing a population set; Set each set of chromosome encoding to represent a set of battery history data, set the population size, and the maximum number of iterations .

[0029] S42, setting a fitness function of the battery historical data based on the constructed population set size; Set the fitness function: ; in, A fitness function representing the battery's historical data; S43, genetic operator selection operation; Assume the probability of chromosome encoding being selected to be ; ; in, is the population size, is the fitness encoded by the kth chromosome, Represents the kth chromosome code in the population set.

[0030] S44, chromosome crossover operation; A crossover point is randomly selected from the chromosome codes in the population set, and the chromosome code segments between the crossover points are exchanged to form a new chromosome code, thereby forming a new population; Remove duplicate chromosome codes in order and ensure that the length of chromosome codes is consistent to form daughter chromosomes; S45, chromosome mutation operation; The mutation process is to replace the gene fragment of the parent chromosome to produce a chromosome code different from the parent; based on the set mutation probability Mutate the parent chromosome code, thereby producing a new generation of daughter chromosomes; The fitness of all offspring chromosomes is calculated. If the offspring is better than the parent, the parent chromosome code is replaced. Otherwise, if the parent is better, it means that the mutation has failed, and the parent is selected to continue the iteration operation.

[0031] S46, output the optimal solution to the problem; Set the iteration threshold Y, set the iteration When the chromosome codes output after the last iteration remain unchanged or when the hybrid genetic algorithm reaches the set maximum number of iterations, the hybrid genetic algorithm is terminated, and the multiple sets of chromosome codes output for the last time are used as the normal working range of the battery; Further, refer to Figure 1 As shown, real-time collection of battery data, intelligent judgment of the real-time monitored battery data based on the determined normal working range of the battery, and control of the battery based on the judgment result include the following steps: The thresholds of various parameters of the battery are set based on the determined normal operating range of the battery, and when the thresholds set by the real-time collected battery data are reached, the battery operation is stopped immediately; In a specific embodiment, the battery intelligent monitoring system is used to implement a battery intelligent monitoring method, and the system includes: a data collection module, a data processing module, a data analysis module, a data training module and a real-time monitoring control module; The data collection module is used to collect battery historical data and battery real-time monitoring data; The data processing module is used to process the collected battery historical data and battery real-time monitoring data; The data analysis module is used to analyze the processed battery historical data to obtain the analyzed battery historical data; The data training module is used to train the historical data of the analyzed battery to determine the normal working range of the battery; The real-time monitoring and control module is used to monitor and control the battery according to the determined normal working range of the battery.

[0032] It should be noted that the above content is merely an example and explanation of the concept of the present invention. The technical personnel in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A battery intelligent monitoring system, characterized in that: The following steps are involved: S1. Collecting battery historical data, and building a sample set based on the collected battery historical data; S2. Processing the battery historical data in the sample set by a data processing method to obtain processed battery historical data; S3, analyzing the processed battery historical data by a data analysis method to obtain analyzed battery historical data; S31, calculating the battery capacity of the battery based on the processed battery historical data; S32, analyzing the charging process and discharging process of the battery based on the processed battery historical data, and outputting the charging parameters and discharging parameters of the battery after analysis; S33, summarizing the calculated battery capacity, charging parameters, and discharging parameters to obtain analyzed battery history data; S4, training the analyzed battery historical data to determine the normal working range of the battery; S5. Collect battery data in real time, make intelligent judgments on the real-time monitored battery data based on the determined normal working range of the battery, and control the battery based on the judgment results.

2. A battery intelligent monitoring system according to claim 1, characterized in that: The collecting of battery historical data and constructing a sample set based on the collected battery historical data comprises the following steps: The historical data of the battery includes the battery number, battery charging stage data and battery discharging stage data; The battery charging stage data includes: battery charging voltage, battery charging current and battery charging stage temperature; The battery discharge stage data includes: battery discharge voltage, battery discharge current and battery discharge stage temperature.

3. A battery intelligent monitoring system according to claim 1, characterized in that: The method of processing the battery historical data in the sample set by the data processing method to obtain the processed battery historical data comprises the following steps: The battery historical data in the sample set is processed by the data standardization method as follows: ； in, Indicates the minimum value of the battery historical data in the sample set, Indicates the maximum value of the battery historical data in the sample set, Indicates the sample set Battery history data, Indicates the standardized battery history data.

4. A battery intelligent monitoring system according to claim 1, characterized in that: The method of calculating the battery capacity of the battery based on the processed battery historical data comprises the following steps: Summarize the battery charging stage data in the last 10 groups of processed battery history data; The charging process from the time when the battery is plugged in to the time when the charger is unplugged after the battery is fully charged is considered as one charging process, and the charging process data generated during this period are considered as the same set of charging data; A charging time threshold is set. When the time interval between two sets of charging data is less than the charging time threshold, the two sets of charging data are aggregated into one set of charging data. Calculate the total battery capacity based on the collected charging data; The total battery capacity is calculated as follows: ； in, It represents the current value collected every minute, and T represents the total charging time.

5. The battery intelligent monitoring system according to claim 1, characterized in that: The method of analyzing the charging process and discharging process of the battery based on the processed battery historical data and outputting the charging parameters and discharging parameters of the battery after analysis comprises the following steps: S321, analyzing the charging process of the battery; S322. Analyze the discharge process of the battery.

6. A battery intelligent monitoring system according to claim 5, characterized in that: The charging process of the described analysis battery comprises the following steps: Constructing a battery charging current curve, a battery charging voltage curve, and a battery charging temperature curve based on the processed battery historical data; The formula for constructing the battery charging current curve is as follows; Summarize the charging current data of the last 10 sets of battery charging stage data, and perform fitting analysis on the selected data by Gaussian fitting; The Gaussian fitting expression is as follows: ； Where n represents the order of Gaussian fitting, represents the height of curve i, represents the coordinates of the center position of curve i on the x-axis, represents the width of curve i, represents the fitted battery charging current curve; The formula for constructing the battery charging voltage curve is as follows: Set the resistance R during charging process to be constant; ； in, Represents the constructed battery charging voltage curve; The formula for constructing the battery charging temperature curve is as follows: ； in, represents the constructed battery charging temperature curve, The weight of the relationship between temperature, current and voltage during battery charging. Indicates the initial temperature.

7. The battery intelligent monitoring system according to claim 5, characterized in that: The discharge process of the battery is analyzed and comprises the following steps: Constructing a battery discharge current curve, a battery discharge voltage curve, and a battery discharge temperature curve based on the processed battery historical data; The formula for constructing the battery discharge current curve is as follows; Summarize the discharge current data of the last 10 sets of battery discharge stage data, and perform fitting analysis on the selected data by Gaussian fitting; The Gaussian fitting expression is as follows: ； Where n represents the order of Gaussian fitting, represents the height of curve i, represents the coordinates of the center position of curve i on the x-axis, represents the width of curve i, represents the fitted battery current curve; The formula for constructing the battery voltage curve is as follows: Set the internal resistance of the battery during discharge Constant; ； in, represents the constructed battery discharge voltage curve; The formula for constructing the battery charging temperature curve is as follows: ； in, represents the constructed battery discharge temperature curve, is the weight of the relationship between temperature, current and voltage during battery discharge, Indicates the initial temperature.

8. The battery intelligent monitoring system according to claim 1, characterized in that: The training of the analyzed battery historical data to determine the normal working range of the battery includes the following steps: S41, initializing the analyzed battery historical data, performing chromosome encoding on the analyzed battery historical data based on a hybrid genetic algorithm, and constructing a population set; Set each set of chromosome encoding to represent a set of battery history data, set the population size, and the maximum number of iterations ; S42, setting a fitness function of the battery historical data based on the constructed population set size; Set the fitness function: ； in, A fitness function representing the battery's historical data; S43, genetic operator selection operation; Assume the probability of chromosome encoding being selected to be , ; in, is the population size, is the fitness encoded by the kth chromosome, Represents the kth chromosome code in the population set; S44, chromosome crossover operation; A crossover point is randomly selected from the chromosome codes in the population set, and the chromosome code segments between the crossover points are exchanged to form a new chromosome code, thereby forming a new population; Remove duplicate chromosome codes in order and ensure that the length of chromosome codes is consistent to form daughter chromosomes; S45, chromosome mutation operation; The mutation process is to replace the gene fragment of the parent chromosome to produce a chromosome code different from the parent; based on the set mutation probability Mutate the parent chromosome code, thereby producing a new generation of daughter chromosomes; The fitness of all offspring chromosomes is calculated. If the offspring is better than the parent, the parent chromosome code is replaced. Otherwise, if the parent is better, it means that the mutation has failed, and the parent is selected to continue the iteration operation. S46, output the optimal solution to the problem; Set the iteration threshold Y, set the iteration If the chromosome codes output after the last iteration remain unchanged or when the hybrid genetic algorithm reaches the set maximum number of iterations, the hybrid genetic algorithm is terminated and the multiple sets of chromosome codes output for the last time are used as the normal working range of the battery.

9. The battery intelligent monitoring system according to claim 1, characterized in that: The real-time collection of battery data, intelligent judgment of the real-time monitored battery data based on the determined normal working range of the battery, and control of the battery based on the judgment result include the following steps: Thresholds of various parameters of the battery are set based on the determined normal operating range of the battery, and when the threshold set by the battery data collected in real time is reached, the operation of the battery is stopped immediately.

10. A battery intelligent monitoring system implementing any one of claims 1 to 9, characterized in that: include: Data collection module, data processing module, data analysis module, data training module and real-time monitoring and control module; The data collection module is used to collect battery historical data and battery real-time monitoring data; The data processing module is used to process the collected battery historical data and battery real-time monitoring data; The data analysis module is used to analyze the processed battery historical data to obtain the analyzed battery historical data; The data training module is used to train the historical data of the analyzed battery to determine the normal working range of the battery; The real-time monitoring and control module is used to monitor and control the battery according to the determined normal working range of the battery.

Images