Intelligent operation and maintenance system and method based on BMS

Abstract

The invention discloses an intelligent operation and maintenance system and method based on a BMS (Battery Management System), relates to the technical field of intelligent operation and maintenance, and solves the technical problem that the service life of a battery is shortened because the battery is always in an abnormal state due to the fact that information transmission is not timely when the battery is abnormal and then is processed in the prior art. The method comprises the following steps: collecting real-time data of a plurality of batteries, and preprocessing the real-time data to obtain processed data; detecting the operation states of the plurality of batteries; acquiring processing data of the plurality of batteries in a set time period, integrating the processing data into a state data set, predicting operation states of the plurality of batteries, and adjusting acquisition frequencies of the plurality of batteries; calculating risk coefficients of the plurality of batteries according to the use data; determining risk levels of the plurality of batteries based on the risk coefficients; determining operation and maintenance periods of the plurality of batteries according to the risk levels; overhauling the plurality of batteries based on the operation and maintenance period; and the service life of the battery is prolonged.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent operation and maintenance, and relates to the intelligent operation and maintenance technology of BMS, and specifically to an intelligent operation and maintenance system and method based on BMS. Background Art

[0002] BMS is a battery management system. In the fields of electric vehicles and energy storage systems, BMS is used to monitor, control and manage each battery unit in the battery pack. Its main functions include battery parameter monitoring, battery status estimation, online diagnosis and early warning, charge and discharge control, thermal management, etc., to ensure the safe, reliable and efficient operation of the battery. The intelligent operation and maintenance of BMS can monitor the voltage, current, temperature and other key parameters of the battery in real time, and issue an alarm in time when an abnormal situation is detected. It helps operation and maintenance personnel to promptly discover and deal with potential safety hazards, thereby effectively avoiding safety accidents caused by battery failure. Intelligent operation and maintenance can prevent harmful phenomena such as overcharging and over-discharging by accurately controlling the battery charging and discharging process. At the same time, it can also balance the battery to ensure that the performance difference between each single cell in the battery pack is minimized, which helps to extend the battery life and reduce the frequency and cost of battery replacement.

[0003] The prior art (invention patent application with publication number CN116430248A) discloses an Internet-based BMS operation and maintenance management system, which includes a control center, which is communicatively connected to a data storage module, an information acquisition module, a data processing module and an information feedback module; the data storage module is used to store battery information and operation and maintenance logs, the information acquisition module is used to collect various status information of the battery, the data processing module is used to analyze the charge state and health state of the battery, and the information feedback module is used to alarm and notify the charge state and health state of the battery; the prior art can handle battery abnormalities in a timely manner by alarming and notifying the charge state and health state of the battery; however, when the battery is abnormal and then handles the abnormality, there may be a situation where information transmission is not timely, resulting in the battery being in an abnormal state all the time, resulting in a reduction in the battery life.

[0004] The present invention provides an intelligent operation and maintenance system and method based on BMS to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an intelligent operation and maintenance system and method based on BMS, which is used to solve the technical problem that the prior art can handle the battery abnormality in time by alarming and notifying the charge state and health state of the battery; however, when the battery is abnormal and then handles the abnormality, there may be a situation where information transmission is not timely, resulting in the battery being in an abnormal state all the time, resulting in a reduced battery service life.

[0006] To achieve the above-mentioned object, the first aspect of the present invention provides an intelligent operation and maintenance system based on BMS, comprising: a processing control module, and a data acquisition module and an intelligent operation and maintenance module connected thereto;

[0007] Data acquisition module: used to collect real-time data of several batteries through data sensors, and pre-process the real-time data to obtain processed data;

[0008] Processing control module: used to detect the operating status of several batteries according to the processing data; obtain the processing data of several batteries within a set time period, and integrate the processing data into a status data set; predict the operating status of several batteries based on the status data set; adjust the collection frequency of several batteries according to the prediction results;

[0009] Intelligent operation and maintenance module: used to obtain usage data of several batteries, calculate risk coefficients of several batteries based on the usage data; determine risk levels of several batteries based on the risk coefficients; determine operation and maintenance cycles of several batteries based on the risk levels; and inspect and repair several batteries based on the operation and maintenance cycles.

[0010] Preferably, the preprocessing of the real-time data to obtain processed data includes:

[0011] Retrieve real-time data; real-time data includes collection time, battery number, real-time current, real-time voltage and real-time temperature;

[0012] Determine whether the real-time data includes sub-data of all data types; if yes, keep the corresponding real-time data; if no, complete the missing sub-data of the data type;

[0013] Determine whether the collection time and battery number in the real-time data are consistent; if yes, verify the real-time data and remove duplicate or erroneous data; if no, retain the corresponding real-time data;

[0014] The retained real-time data and the supplemented real-time data are marked as processed data.

[0015] It should be noted that the data type of the processed data is consistent with the data type of the real-time data, and the sub-data of the real-time data includes the collection time, battery number, real-time current, real-time voltage or real-time temperature.

[0016] The present invention analyzes the collected real-time data, and when there are missing sub-data in the real-time data, the real-time data is supplemented; when there are repeated or erroneous data in the real-time data, the real-time data is eliminated; the integrity of the real-time data can be ensured, and invalid data can be eliminated, which is conducive to improving the data processing rate.

[0017] Preferably, the detecting the operating status of a plurality of batteries according to the processed data comprises:

[0018] Retrieving processing data of a number of batteries, obtaining a standard range corresponding to sub-data of the processing data; comparing the sub-data of the processing data with the corresponding standard range;

[0019] Determine whether the sub-data of the processed data is within the standard range; if yes, continue to detect the operating status of several batteries; if not, generate an abnormal warning signal and notify the corresponding operation and maintenance personnel.

[0020] It should be noted that when comparing the sub-data of the processed data with the standard range, it is not necessary to consider the acquisition time and the battery number; the real-time voltage, real-time current and real-time temperature are compared with the corresponding standard range.

[0021] The present invention analyzes the processing data of several batteries, compares the sub-data of the processing data with the corresponding standard range, and notifies the corresponding operation and maintenance personnel when the processing data exceeds the standard range; this is helpful to ensure that the batteries are in a normal operating state.

[0022] Preferably, the predicting the operating states of a plurality of batteries based on the state data set includes:

[0023] Retrieving state data sets corresponding to a number of batteries, and marking the state data sets as state prediction sequences corresponding to the number of batteries;

[0024] The state prediction model is called, and the state prediction sequence is input into the state prediction model to obtain the predicted state of the corresponding battery; wherein the state prediction model is constructed based on an artificial intelligence model.

[0025] The present invention predicts the operating status of a number of batteries using a state prediction model based on the state data sets corresponding to the batteries; when the batteries are not abnormal, it can increase the attention paid to batteries that may have abnormalities, laying a foundation for the subsequent adjustment of the acquisition frequency; and is conducive to extending the life of the batteries.

[0026] Preferably, the state prediction model is constructed based on an artificial intelligence model, including:

[0027] Acquire a standard data set; wherein the standard data set includes standard input data consistent with the content attributes of the state input sequence; and standard output data consistent with the content attributes of the predicted state;

[0028] Divide the standard data set into a training set, a validation set, and a test set; use the training set to train the artificial intelligence model; use the validation set to adjust the internal parameters of the artificial intelligence model; use the test set to test the trained artificial intelligence model to obtain the test parameters of the artificial intelligence model;

[0029] Obtain the parameter threshold and compare the test parameter with the parameter threshold; determine whether the test parameter is greater than the corresponding parameter threshold; if yes, mark the artificial intelligence model as a state prediction model; if no, rebuild the artificial intelligence model.

[0030] It should be noted that the test parameters include accuracy, F1 score, recall rate and stability, and the parameter thresholds are set according to actual experience; the ratio of dividing the standard data set into training set, validation set and test set is set according to actual conditions.

[0031] Preferably, the adjusting the collection frequency of the plurality of batteries according to the prediction result includes:

[0032] Retrieve the predicted status; wherein the predicted status includes normal or abnormal;

[0033] Determine whether the predicted state is normal; if yes, maintain the original collection frequency to continue to collect real-time data of several batteries; if no, adjust the collection frequency of several batteries according to the frequency adjustment library.

[0034] The present invention adjusts the acquisition frequency of a plurality of batteries according to the prediction results; when it is predicted that a battery will be abnormal, the attention paid to the battery is increased, and the abnormal state of the battery is discovered in time, which is conducive to timely processing the abnormality of the battery and extending the service life of the battery.

[0035] Preferably, the step of calculating the risk factors of a plurality of batteries according to the usage data comprises:

[0036] Retrieve the usage data of several batteries, and mark the service life, abnormal number and abnormal level in the usage data as SN, YC and YD respectively;

[0037] The risk level of several batteries is calculated by the formula FX=α×ln(SN+1)+β×YC+γ×exp(YD); wherein α, β and γ are proportional coefficients greater than 0.

[0038] It should be noted that when an abnormal situation occurs in the battery, the risk factor of the battery is calculated and the operation and maintenance cycle is adjusted; the abnormality level is the abnormality level corresponding to the latest abnormality of the battery.

[0039] The present invention calculates the risk coefficient of a corresponding battery based on the usage data of a plurality of batteries, and can evaluate the risk of the battery when an abnormality occurs in the battery, thus laying a foundation for subsequently determining the risk level of the battery.

[0040] Preferably, the step of determining the risk levels of a plurality of batteries based on the risk coefficient includes:

[0041] Retrieving risk coefficients of several batteries to obtain a risk threshold; comparing the risk coefficient with the risk threshold; wherein the risk threshold includes a primary threshold and a secondary threshold;

[0042] Determine whether the risk factor is less than the first-level threshold; if yes, mark the risk level as low; if no, compare the risk factor with the second-level threshold;

[0043] Determine whether the risk factor is greater than the secondary threshold; if yes, mark the risk level as high; if no, mark the risk level as medium.

[0044] The present invention determines the risk level of corresponding batteries according to the risk coefficients of several batteries, can evaluate the risk of abnormal batteries, lays a foundation for subsequent adjustment of the operation and maintenance cycle, and is conducive to ensuring the normal operation of the batteries.

[0045] Preferably, determining the operation and maintenance cycles of a plurality of batteries according to the risk level includes:

[0046] Retrieve the risk levels of several batteries and obtain the level operation and maintenance table;

[0047] Match the risk levels of several batteries with the level operation and maintenance table to obtain the operation and maintenance cycle of the corresponding batteries.

[0048] The present invention determines the operation and maintenance cycle of the corresponding battery according to the risk level of the battery, which can increase the frequency of battery operation and maintenance, reduce the number of battery abnormalities, and help extend the service life of the battery.

[0049] A second aspect of the present invention provides an intelligent operation and maintenance method based on BMS, comprising:

[0050] Step S1: collecting real-time data of a number of batteries through a data sensor, and pre-processing the real-time data to obtain processed data;

[0051] Step S2: detecting the operating status of the plurality of batteries according to the processed data; obtaining the processed data of the plurality of batteries within a set time period, and integrating the processed data into a status data set; predicting the operating status of the plurality of batteries based on the status data set; and adjusting the acquisition frequency of the plurality of batteries according to the prediction result;

[0052] Step S3: Obtain usage data of a number of batteries, and calculate risk coefficients of the number of batteries based on the usage data; determine risk levels of the number of batteries based on the risk coefficients; determine operation and maintenance cycles of the number of batteries based on the risk levels; and inspect and repair the number of batteries based on the operation and maintenance cycles.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] 1. The present invention analyzes the collected real-time data, and when there are missing sub-data in the real-time data, the real-time data is supplemented; when there are repeated or erroneous data in the real-time data, the real-time data is eliminated; the integrity of the real-time data can be ensured, and invalid data can be eliminated, which is beneficial to improving the data processing rate; the processing data of several batteries are analyzed, and the sub-data of the processing data are compared with the corresponding standard range. When the processing data exceeds the standard range, the corresponding operation and maintenance personnel are notified; it is beneficial to ensure that the battery is in a normal operating state; the operating state of several batteries is predicted by using a state prediction model according to the state data sets corresponding to several batteries; when several batteries are not abnormal, the attention to batteries that may have abnormalities can be increased, laying a foundation for the subsequent adjustment of the collection frequency; it is beneficial to extend the life of the battery.

[0055] 2. The present invention adjusts the collection frequency of a plurality of batteries according to the prediction results; when it is predicted that a battery will have an abnormality, the attention paid to the battery is increased, and the abnormal state of the battery is discovered in time, which is conducive to timely processing the abnormality of the battery and extending the service life of the battery; the risk coefficient of the corresponding battery is calculated according to the usage data of the plurality of batteries, and the risk of the battery can be evaluated when the battery has an abnormality, laying a foundation for the subsequent determination of the risk level of the battery; the risk level of the corresponding battery is determined according to the risk coefficient of the plurality of batteries, and the risk of the abnormal battery can be evaluated, laying a foundation for the subsequent adjustment of the operation and maintenance cycle, which is conducive to ensuring the normal operation of the battery; the operation and maintenance cycle of the corresponding battery is determined according to the risk level of the battery, which can increase the frequency of battery operation and maintenance, reduce the number of battery abnormalities, and is conducive to extending the service life of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] 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.

[0057] Figure 1 It is a schematic diagram of specific steps of the system of the present invention;

[0058] Figure 2 A schematic diagram of the battery status detection and prediction steps of the present invention;

[0059] Figure 3 A schematic diagram of the steps for determining the battery collection frequency and operation and maintenance cycle of the present invention;

[0060] Figure 4 It is a schematic diagram of the specific steps of the method of the present invention. DETAILED DESCRIPTION

[0061] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0062] See also Figure 1 , the first aspect of the present invention provides an intelligent operation and maintenance system based on BMS, including: a processing control module, and a data acquisition module and an intelligent operation and maintenance module connected thereto;

[0063] Data acquisition module: used to collect real-time data of several batteries through data sensors, and pre-process the real-time data to obtain processed data;

[0064] Processing control module: used to detect the operating status of several batteries according to the processing data; obtain the processing data of several batteries within a set time period, and integrate the processing data into a status data set; predict the operating status of several batteries based on the status data set; adjust the collection frequency of several batteries according to the prediction results;

[0065] Intelligent operation and maintenance module: used to obtain usage data of several batteries, calculate risk coefficients of several batteries based on the usage data; determine risk levels of several batteries based on the risk coefficients; determine operation and maintenance cycles of several batteries based on the risk levels; and inspect and repair several batteries based on the operation and maintenance cycles.

[0066] See also Figure 2, collect real-time data of several batteries through data sensors, where the real-time data includes collection time, battery number, real-time current, real-time voltage and real-time temperature; determine whether the real-time data includes sub-data of all data types; if yes, retain the corresponding real-time data; if no, complete the missing sub-data of the data type; determine whether the collection time and battery number in the real-time data are consistent; if yes, verify the real-time data and remove duplicate or erroneous data; if no, retain the corresponding real-time data; mark the retained real-time data and the completed real-time data as processed data.

[0067] For example: assuming that there are three sets of real-time data obtained, the data types of the three sets of real-time data are analyzed. The second set of real-time data lacks real-time temperature data, so the real-time temperature is supplemented; the collection time and battery number of the first set of real-time data and the third set of real-time data are consistent, so the third set of real-time data is eliminated after verification; the first set of real-time data and the completed second set of real-time data are marked as processed data.

[0068] Obtain the standard range corresponding to the sub-data of the processed data; compare the sub-data of the processed data with the corresponding standard range; determine whether the sub-data of the processed data is within the standard range; if yes, continue to detect the operating status of several batteries; if not, generate an abnormal warning signal and notify the corresponding operation and maintenance personnel.

[0069] It should be noted that before analyzing the processed data, the battery usage status is detected, and the battery standard range is determined based on the battery usage status; the battery standard range is set according to the battery model; wherein the usage status includes charging, discharging and unused.

[0070] For example: assuming that two sets of collected processing data are analyzed, if the sub-data of the first set of processing data is within the standard range, the operating status of the battery is continuously detected; if the real-time voltage in the second set of processing data exceeds the standard range, an abnormal warning signal is generated and the on-site operation and maintenance personnel are notified to handle the abnormality.

[0071] Obtain processing data of several batteries within a set time period, and integrate the processing data into a state data set; mark several state data sets as state prediction sequences corresponding to several batteries; call a state prediction model, input the state prediction sequence into the state prediction model, and obtain the predicted state of the corresponding battery; wherein the state prediction model is constructed based on an artificial intelligence model.

[0072] For example: suppose that the operating status of battery A and battery B is predicted, and the processing data of battery A and battery B within 20 minutes are obtained respectively, the processed data are integrated into a status data set, the status data set is marked as the corresponding status prediction sequence, the status prediction model is called, and the status prediction sequence is input into the status prediction model, and the corresponding battery prediction status is obtained as battery A is normal and battery B is abnormal.

[0073] It is worth noting that the state prediction model is built based on artificial intelligence models, including:

[0074] Acquire a standard data set; wherein the standard data set includes standard input data consistent with the content attributes of the state input sequence; and standard output data consistent with the content attributes of the predicted state;

[0075] Divide the standard data set into a training set, a validation set, and a test set; use the training set to train the artificial intelligence model; use the validation set to adjust the internal parameters of the artificial intelligence model; use the test set to test the trained artificial intelligence model to obtain the test parameters of the artificial intelligence model;

[0076] Obtain the parameter threshold and compare the test parameter with the parameter threshold; determine whether the test parameter is greater than the corresponding parameter threshold; if yes, mark the artificial intelligence model as a state prediction model; if no, rebuild the artificial intelligence model.

[0077] See also Figure 3 , retrieve the prediction status; wherein the prediction status includes normal or abnormal; determine whether the prediction status is normal; if yes, maintain the original collection frequency to continue to collect real-time data of several batteries; if no, adjust the collection frequency of several batteries according to the frequency adjustment library.

[0078] For example: Assuming that the predicted status of battery A and battery B is obtained, the predicted status of battery B is abnormal, and the collection frequency of battery B is changed from once every 5 minutes to once every 3 minutes; the predicted status of battery A is normal, then the original collection frequency of once every 5 minutes is maintained to collect the real-time data of battery A.

[0079] Obtain usage data of several batteries, and mark the service life, abnormal number and abnormal level in the usage data as SN, YC and YD respectively; calculate the risk level of several batteries by formula FX=α×ln(SN+1)+β×YC+γ×exp(YD); wherein α, β and γ are proportional coefficients greater than 0;

[0080] Obtain a risk threshold; compare the risk coefficient with the risk threshold; wherein the risk threshold includes a primary threshold and a secondary threshold; determine whether the risk coefficient is less than the primary threshold; if so, mark the risk level as low; if not, compare the risk coefficient with the secondary threshold; determine whether the risk coefficient is greater than the secondary threshold; if so, mark the risk level as high; if not, mark the risk level as medium; retrieve the risk levels of several batteries and obtain a graded operation and maintenance table; match the risk levels of several batteries with the graded operation and maintenance table to obtain the operation and maintenance cycles of the corresponding batteries.

[0081] It should be noted that α, β and γ are set according to actual experience, and the setting range is (0,100]; the risk threshold is adjusted according to the settings of α, β and γ, and is set according to experience; the highest level of abnormality is set to 1, and the abnormality level is determined according to the type of abnormality.

[0082] For example, suppose that the risks of battery B, battery E, and battery G are evaluated, and α, β, and γ are set to 10, 1, and 10 respectively; the specific steps are as follows:

[0083] Battery B: Service life SN = 3; number of abnormalities YC = 8; abnormality level YD = 0.87; the risk factor is FX = 45.73; greater than the first-level threshold of 35; less than the second-level threshold of 55; the risk level is classified as medium, and the operation and maintenance cycle is once every 10 days;

[0084] Battery F: Service life SN = 5; Abnormal number YC = 10; Abnormal level YD = 0.63; then the risk factor is FX = 46.67; greater than the first-level threshold of 35; less than the second-level threshold of 55; then the risk level is classified as medium, and the operation and maintenance cycle is once every 10 days

[0085] Battery G: Service life SN = 2; number of abnormalities YC = 2; abnormality level YD = 0.76; the risk factor is FX = 34.37; if it is less than the first-level threshold of 35, the risk level is classified as low, and the operation and maintenance cycle is once every 15 days.

[0086] See also Figure 4 The first aspect of the present invention provides an intelligent operation and maintenance method based on BMS, including:

[0087] Step S1: collecting real-time data of a number of batteries through a data sensor, and pre-processing the real-time data to obtain processed data;

[0088] Step S2: detecting the operating status of the plurality of batteries according to the processed data; obtaining the processed data of the plurality of batteries within a set time period, and integrating the processed data into a status data set; predicting the operating status of the plurality of batteries based on the status data set; and adjusting the acquisition frequency of the plurality of batteries according to the prediction result;

[0089] Step S3: Obtain usage data of a number of batteries, and calculate risk coefficients of the number of batteries based on the usage data; determine risk levels of the number of batteries based on the risk coefficients; determine operation and maintenance cycles of the number of batteries based on the risk levels; and inspect and repair the number of batteries based on the operation and maintenance cycles.

[0090] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0091] Working principle of the present invention: The present invention collects real-time data of several batteries through data sensors, pre-processes the real-time data to obtain processed data; detects the operating status of several batteries according to the processed data; obtains the processed data of several batteries within a set time period, and integrates the processed data into a status data set; predicts the operating status of several batteries based on the status data set; adjusts the collection frequency of several batteries according to the prediction result; obtains the usage data of several batteries, and calculates the risk coefficient of several batteries according to the usage data; determines the risk level of several batteries based on the risk coefficient; determines the operation and maintenance cycle of several batteries according to the risk level; and inspects several batteries based on the operation and maintenance cycle.

[0092] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent operation and maintenance system based on BMS, comprising: Processing control module, and the data acquisition module and intelligent operation and maintenance module connected thereto; characterized in that: Data acquisition module: used to collect real-time data of several batteries through data sensors, and pre-process the real-time data to obtain processed data; Processing control module: used to detect the operating status of several batteries according to the processing data; obtain the processing data of several batteries within a set time period, and integrate the processing data into a status data set; predict the operating status of several batteries based on the status data set; adjust the collection frequency of several batteries according to the prediction results; Intelligent operation and maintenance module: used to obtain usage data of several batteries, calculate risk coefficients of several batteries based on the usage data; determine risk levels of several batteries based on the risk coefficients; determine operation and maintenance cycles of several batteries based on the risk levels; and inspect and repair several batteries based on the operation and maintenance cycles.

2. According to claim 1, the intelligent operation and maintenance system based on BMS is characterized in that: The preprocessing of the real-time data to obtain processed data includes: Retrieve real-time data; real-time data includes collection time, battery number, real-time current, real-time voltage and real-time temperature; Determine whether the real-time data includes sub-data of all data types; if yes, keep the corresponding real-time data; if no, complete the missing sub-data of the data type; Determine whether the collection time and battery number in the real-time data are consistent; if yes, verify the real-time data and remove duplicate or erroneous data; if no, retain the corresponding real-time data; The retained real-time data and the supplemented real-time data are marked as processed data.

3. According to claim 1, the intelligent operation and maintenance system based on BMS is characterized in that: The detecting the operating status of the plurality of batteries according to the processed data comprises: Retrieving processing data of a number of batteries, obtaining a standard range corresponding to sub-data of the processing data; comparing the sub-data of the processing data with the corresponding standard range; Determine whether the sub-data of the processed data is within the standard range; if yes, continue to detect the operating status of several batteries; if not, generate an abnormal warning signal and notify the corresponding operation and maintenance personnel.

4. According to claim 1, the intelligent operation and maintenance system based on BMS is characterized in that: The predicting of the operating states of the plurality of batteries based on the state data set includes: Retrieving state data sets corresponding to a number of batteries, and marking the state data sets as state prediction sequences corresponding to the number of batteries; The state prediction model is called, and the state prediction sequence is input into the state prediction model to obtain the predicted state of the corresponding battery; wherein the state prediction model is constructed based on an artificial intelligence model.

5. According to claim 4, the intelligent operation and maintenance system based on BMS is characterized in that: The state prediction model is constructed based on an artificial intelligence model, including: Acquire a standard data set; wherein the standard data set includes standard input data consistent with the content attributes of the state input sequence; and standard output data consistent with the content attributes of the predicted state; Divide the standard data set into a training set, a validation set, and a test set; use the training set to train the artificial intelligence model; use the validation set to adjust the internal parameters of the artificial intelligence model; use the test set to test the trained artificial intelligence model to obtain the test parameters of the artificial intelligence model; Obtain the parameter threshold and compare the test parameter with the parameter threshold; determine whether the test parameter is greater than the corresponding parameter threshold; if yes, mark the artificial intelligence model as a state prediction model; if no, rebuild the artificial intelligence model.

6. The intelligent operation and maintenance system based on BMS according to claim 1, characterized in that: The adjusting the collection frequencies of the plurality of batteries according to the prediction results includes: Retrieve the predicted status; wherein the predicted status includes normal or abnormal; Determine whether the predicted state is normal; if yes, maintain the original collection frequency to continue to collect real-time data of several batteries; if no, adjust the collection frequency of several batteries according to the frequency adjustment library.

7. The intelligent operation and maintenance system based on BMS according to claim 1 is characterized in that: The method of calculating the risk factors of several batteries according to the usage data includes: Retrieve the usage data of several batteries, and mark the service life, abnormal number and abnormal level in the usage data as SN, YC and YD respectively; The risk level of several batteries is calculated by the formula FX=α×ln(SN+1)+β×YC+γ×exp(YD); wherein α, β and γ are proportional coefficients greater than 0.

8. The intelligent operation and maintenance system based on BMS according to claim 7 is characterized in that: The risk level of the plurality of batteries is determined based on the risk factor, including: Retrieving risk coefficients of several batteries to obtain a risk threshold; comparing the risk coefficient with the risk threshold; wherein the risk threshold includes a primary threshold and a secondary threshold; Determine whether the risk factor is less than the first-level threshold; if yes, mark the risk level as low; if no, compare the risk factor with the second-level threshold; Determine whether the risk factor is greater than the secondary threshold; if yes, mark the risk level as high; if no, mark the risk level as medium.

9. The intelligent operation and maintenance system based on BMS according to claim 1, characterized in that: Determining the operation and maintenance cycles of several batteries according to the risk level includes: Retrieve the risk levels of several batteries and obtain the level operation and maintenance table; Match the risk levels of several batteries with the level operation and maintenance table to obtain the operation and maintenance cycle of the corresponding batteries.

10. An intelligent operation and maintenance method based on BMS, applied to an intelligent operation and maintenance system based on BMS according to any one of claims 1 to 9, characterized in that: include: Step S1: collecting real-time data of a number of batteries through a data sensor, and pre-processing the real-time data to obtain processed data; Step S2: detecting the operating status of the plurality of batteries according to the processed data; obtaining the processed data of the plurality of batteries within a set time period, and integrating the processed data into a status data set; predicting the operating status of the plurality of batteries based on the status data set; and adjusting the acquisition frequency of the plurality of batteries according to the prediction result; Step S3: Obtain usage data of a number of batteries, and calculate risk coefficients of the number of batteries based on the usage data; determine risk levels of the number of batteries based on the risk coefficients; determine operation and maintenance cycles of the number of batteries based on the risk levels; and inspect and repair the number of batteries based on the operation and maintenance cycles.

Images