Battery monitoring method and system based on battery parameters, electronic equipment and medium

Abstract

The invention provides a battery monitoring method and system based on battery parameters, electronic equipment and a storage medium, and aims to solve the problems of relatively large error between a battery condition model result and an actual result and relatively narrow application range. The method comprises the steps that battery information is collected through a sensor, and the collected battery information is preprocessed; the charging efficiency and the charging health condition of the battery are judged through the preprocessed battery information, the difference value between the voltage of each single battery and the average voltage is calculated, and the single batteries are balanced according to the obtained difference value; the method comprises the following steps: setting a plurality of monitoring points, deploying each monitoring point in each single battery, monitoring the operation state of each single battery, constructing an operation coefficient set of the battery, and monitoring the abnormal risk through analysis of the operation coefficient set. Balancing among the single batteries can be achieved, and the service life of the battery pack is prolonged; the risk condition of the battery is evaluated more comprehensively, and the risk prevention and control capability is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of battery management, and in particular to a battery monitoring method based on battery parameters, a battery monitoring system based on battery parameters, an electronic device, and a computer-readable storage medium. Background Art

[0002] A battery is a device that can continuously provide energy and output current at a constant voltage and frequency. With the advocacy and dissemination of life concepts such as energy conservation, emission reduction, and low-carbon life, many research institutions and power battery companies have invested a lot of manpower and material resources to begin researching battery management systems, and have made some breakthroughs. The top priority of the research is how to detect problematic and exhausted batteries as early as possible, how to make the battery pack work stably and sustainably, and always run under the correct parameter configuration, thereby extending the battery life as much as possible.

[0003] In existing research and analysis, battery conditions are usually analyzed through battery models. Common battery models include electrochemical models, mathematical models, heat exchange models, aging mechanism models, equivalent circuit models, etc. Among them, equivalent circuit models are widely used due to their advantages such as small amount of calculation and high accuracy. The equivalent circuit model mainly uses the DC internal resistance model. The DC internal resistance model includes the electromotive force (E m ) and DC internal resistance (R0) are two parameters that need to be identified. DC internal resistance R0 simulates the current drop, and electromotive force E m Provide open circuit voltage, if i represents charging current, then terminal voltage U = E m +i·R0. The parameters of the DC internal resistance model can be quickly determined through parameter identification, but the DC internal resistance model cannot characterize the polarization effect of the battery, and the simulation results obtained by the model have a large error with the actual results, and the scope of use is narrow. Summary of the invention

[0004] In order to at least solve the problem of large errors between the battery condition model results and the actual results and narrow application range in the prior art. The present disclosure provides a battery monitoring method based on battery parameters, a battery monitoring system based on battery parameters, an electronic device and a computer-readable storage medium, which can achieve balance between each single battery, ensure that the status of each single battery in the battery pack remains consistent, thereby extending the life of the entire battery pack; and through the analysis of the operating coefficient, the abnormal situation of the battery can be discovered in time. When the deviation exceeds the preset threshold, the system can issue an early warning in time. This multi-dimensional monitoring method can more comprehensively evaluate the risk status of the battery and improve the ability of risk prevention and control, so as to give early warning and handle it, thereby improving the safety and reliability of the battery pack.

[0005] In a first aspect, the present disclosure provides a battery monitoring method based on battery parameters, characterized in that the method comprises:

[0006] Collect battery information through sensors and pre-process the collected battery information;

[0007] The charging efficiency and charging health of the battery are determined by the pre-processed battery information, and the difference between the voltage of each single cell and the average voltage is calculated, and the single cells are balanced according to the obtained difference;

[0008] Set up several monitoring points and deploy each monitoring point in each single cell to monitor the operating status of each single cell and build a set of operating coefficients for the battery. By analyzing the set of operating coefficients, monitor abnormal risks.

[0009] Furthermore, the method further comprises:

[0010] Based on the calculation of the operating coefficient, a trend model is established to predict and analyze the battery status data collected in real time to determine the degradation risk of the battery.

[0011] Furthermore, the battery information includes the total voltage V_total of the battery pack, the voltage of each single cell V={V1, V2, V3, ..., Vn}, the battery pack current I, the battery temperature V_W and the external environment temperature V_hw;

[0012] The preprocessing includes calculating the output power of the battery pack, the output power of each single cell, the input power of the battery pack, and the input power of each single cell.

[0013] Furthermore, the calculating of the difference between the voltage of each single cell and the average voltage, and balancing the single cells according to the obtained difference, includes:

[0014] The difference between each cell voltage and the average voltage is calculated using the following formula:

[0015] JY=(Y1+Y2+Y3+...+Yn) / n

[0016] DYc=Yi-JY

[0017] Wherein, Y1, Y2, Y3, ..., Yn represent the voltage value of each single cell, JY represents the average value of the voltage of all single cells, Yi represents the voltage value of any single cell, and DYc represents the voltage difference between the single cell Yi and the average voltage JY;

[0018] A voltage difference threshold is preset, and whether a balancing operation is required is determined according to the calculated voltage difference DYc. When the voltage difference exceeds the preset voltage difference threshold, a balancing operation is performed between the single cells in an active balancing manner.

[0019] Furthermore, the monitoring of the operating status of each single battery and the construction of the operating coefficient set of the battery, and the monitoring of abnormal risks through the analysis of the operating coefficient set, include:

[0020] Set a monitoring cycle, monitor the operating status of the single battery of each monitoring node during the monitoring cycle, obtain the operating temperature Yw and operating charge Yh of the battery respectively, and then summarize and construct a battery operating status set;

[0021] The operating coefficient YX(w,h) of the battery is generated from the operating state set, and the specific method is as follows:

[0022]

[0023] Wherein, i=1, 2, ..., m, m is a positive integer greater than 1 and is the number of monitoring nodes. is the qualified standard value of the operating temperature, is the qualified standard value of the operating charge, Yw i represents the battery operating temperature monitored by the i-th monitoring node, Yh i represents the battery operating charge monitored by the i-th monitoring node, Q1 and Q2 represent the weight coefficients corresponding to the operating temperature and the operating charge respectively, and the weight coefficients are: 0≤Q1≤1, 0≤Q2≤1, and Q1+Q2=1; the weight coefficients are determined by referring to the hierarchical analysis method;

[0024] Continuously obtain the operating coefficients YX(w,h) within several monitoring cycles, and then summarize them to construct a set of operating coefficients of the battery;

[0025] Continuously obtain several groups of battery operation coefficients YX(w,h), and preset the maximum operation threshold Smax and the minimum operation threshold Smin based on historical data and expectations for battery safety management to form a moving threshold range [Smax, Smin];

[0026] After obtaining several operating coefficients YX(w,h) of the battery, the changes in the operating coefficient YX(w,h) are tracked, and the threshold range in the moving state is set according to the changes in the operating coefficient YX(w,h). Based on the relationship between the operating coefficient FYX(w,h) and the threshold range, the battery safety is evaluated and judged.

[0027] Furthermore, the specific calculation formula of the threshold range [Smax, Smin] is as follows:

[0028]

[0029] Where n is the number of YX(w,h), is the mean value of the operating coefficient; YX(w,h) j is a set of operating coefficients in the jth monitoring period.

[0030] Furthermore, the calculation based on the operation coefficient establishes a trend model to predict and analyze the real-time collected battery status data to determine the degradation risk of the battery, including:

[0031] The battery operating temperature T and operating charge C at different time points are collected, and the corresponding battery operating coefficient YX(w,h) is generated according to the battery operating temperature T and the operating charge C, which are marked as {(T1,C1,YX1),(T2,C2,YX2),...,(T n ,C n ,YX n )}, through the maximum and minimum normalization, the operating temperature and operating charge are processed separately to obtain the normalized temperature T norm and the normalized charge C norm ;

[0032] Using vector machine regression algorithm, through f(x) = w T φ(x)+b is used to fit the data, with normalized temperature and charge data as input and operating coefficient as output. These data are used to train the vector machine regression model, and the model performance is evaluated by the mean square error and determination coefficient. The specific calculation formula of the mean square error is as follows:

[0033]

[0034] Among them, k represents the number of test set samples, y test represents the true running coefficient of the test set, The specific calculation formula of the operating coefficient R, which represents the model prediction, is as follows:

[0035]

[0036] in, Represents the mean of the true running coefficient of the test set;

[0037] For the newly input data, normalization is performed to obtain in, Represents the normalized temperature data of the new input, Represents the newly input normalized charge data, using the trained model to predict and obtain the predicted value of the operating coefficient

[0038]

[0039] Among them, w represents the weight vector, b is the bias term of the model, φ(x new ) represents the mapping function, y new Represents the true value of the running coefficient for the new input data, calculates the deviation, and the absolute deviation is The relative deviation is When the deviation exceeds the preset threshold, the battery is judged to be at risk of degradation and an early warning is issued.

[0040] In a second aspect, the present disclosure provides a battery monitoring system based on battery parameters, the system comprising:

[0041] An information collection module, which is configured to collect battery information through sensors and pre-process the collected battery information;

[0042] A balancing management module is configured to determine the charging efficiency and charging health of the battery through the pre-processed battery information, calculate the difference between the voltage of each single cell and the average voltage, and balance the single cells according to the obtained difference;

[0043] The operation status monitoring module is configured to set up a number of monitoring points, deploy each monitoring point in each single cell, monitor the operation status of each single cell and construct a battery operation coefficient set, and monitor abnormal risks through analysis of the operation coefficient set.

[0044] Furthermore, the system also includes:

[0045] The trend prediction module is configured to calculate the operating coefficient and establish a trend model to predict and analyze the battery status data collected in real time to determine the degradation risk of the battery.

[0046] In a third aspect, the present disclosure provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes a battery monitoring method based on battery parameters as described in any one of the first aspects.

[0047] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the battery monitoring method based on battery parameters described in any one of the above-mentioned first aspects is implemented.

[0048] Beneficial effects:

[0049] The present disclosure provides a battery monitoring method based on battery parameters, a battery monitoring system based on battery parameters, an electronic device and a storage medium; by calculating the difference between the voltage of each single cell and the average voltage, and achieving balance between each single cell by active balancing, it can ensure that the status of each single cell in the battery pack remains consistent, thereby extending the life of the entire battery pack; by setting monitoring cycles and monitoring nodes, the operating status of the battery is fully acquired, a battery operating status set is constructed, and an operating coefficient is generated, and abnormal risks are monitored through the analysis of the operating coefficient set. This multi-dimensional monitoring method can more comprehensively evaluate the risk status of the battery, improve the ability to prevent and control risks, thereby providing early warnings and processing, and improving the safety and reliability of the battery pack. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flowchart of a battery monitoring method based on battery parameters provided in the first embodiment of the present disclosure;

[0051] Figure 2 An architecture diagram of a battery monitoring system based on battery parameters provided in Embodiment 2 of the present disclosure;

[0052] Figure 3 A schematic diagram of the working process of a battery monitoring system based on battery parameters provided in the second embodiment of the present disclosure;

[0053] Figure 4 An architecture diagram of a battery monitoring system based on battery parameters provided in Embodiment 3 of the present disclosure;

[0054] Figure 5 This is an architecture diagram of an electronic device provided in Embodiment 4 of the present disclosure. DETAILED DESCRIPTION

[0055] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the present disclosure is further described in detail below in conjunction with the drawings and embodiments. It should be understood that the specific embodiments and drawings described herein are only used to explain the present invention, rather than to limit the present invention.

[0056] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence; and, in the absence of conflict, the embodiments in the present disclosure and the features in the embodiments can be arbitrarily combined with each other.

[0057] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure. The singular forms of "a", "said" and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings.

[0058] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present disclosure, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0059] The following is a detailed description of the technical solution of the present invention and how the technical solution of the present invention solves the problems existing in the prior art with specific embodiments. It is understandable that in the embodiments of the present application, the execution subject can perform some or all of the steps in the embodiments of the present application, and these steps or operations are only examples. The embodiments of the present application can also perform other operations or deformations of various operations. In addition, each step can be performed in a different order presented in the embodiments of the present application, and it is possible not to perform all the operations in the embodiments of the present application. And, the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0060] Figure 1 A flow chart of a battery monitoring method based on battery parameters provided in the first embodiment of the present disclosure is shown as follows: Figure 1 As shown, the method includes:

[0061] Step S101: collecting battery information through sensors and preprocessing the collected battery information;

[0062] Step S102: judging the charging efficiency and charging health of the battery through the pre-processed battery information, and calculating the difference between the voltage of each single cell and the average voltage, and balancing the single cells according to the obtained difference;

[0063] Step S103: set a number of monitoring points, deploy each monitoring point in each single cell, monitor the operating status of each single cell and construct a battery operating coefficient set, and monitor abnormal risks through analysis of the operating coefficient set.

[0064] The purpose of this public embodiment is to detect problematic exhausted batteries as early as possible, so that the battery pack can work stably and permanently and always operate under the correct parameter configuration, thereby extending the service life of the battery as much as possible.

[0065] To achieve this purpose, the embodiment of the present disclosure first collects battery information in the system for battery management through sensors, and the battery information includes voltage data, current data, charge and discharge curve data, temperature data, internal resistance data and battery health status. These data provide key information about battery performance and health status. Data collection, preprocessing and analysis can be performed according to actual conditions, wherein voltage data is the voltage measurement value of the battery. It is a key indicator of battery status because voltage directly reflects the charge state of the battery. By monitoring the voltage data of the battery in real time, the system can adjust the charging voltage to ensure that the battery is charged within a safe range and avoid overcharging or over-discharging, thereby improving battery life and performance. Current data indicates the current flowing into or out of the battery. Understanding the direction and intensity of the current is crucial to controlling the charging and discharging process. Through current data, the system can detect battery charging and discharging anomalies in a timely manner, such as overcurrent or short circuit, so as to take necessary measures to improve the safety and charging efficiency of the battery. The charge and discharge curve data describes the change of the battery voltage over time. These curves provide detailed information about battery performance, including the battery capacity, internal resistance, charging and discharging speed, etc. By analyzing these curves, the system can optimize the charging strategy to improve the battery's energy utilization and reduce energy loss. Temperature data is a measurement of the battery's temperature. The temperature of the battery has an important impact on its performance and life. By monitoring temperature data, the system can prevent the battery from overheating or overcooling and improve the safety and stability of the battery. Internal resistance data represents the internal resistance of the battery. The internal resistance directly affects the charging and discharging efficiency of the battery. By measuring the internal resistance data, the system can detect internal problems of the battery, such as battery aging or damage, so that timely measures can be taken to improve the battery's performance and life. Battery health status data provides an overall health assessment of the battery. This includes information such as the battery's remaining capacity, number of cycles, and health percentage. By understanding the battery's health status, the system can adjust the charging strategy based on actual conditions to maximize the battery's life.

[0066] The collected battery information is preprocessed to obtain relevant data to evaluate the battery performance and provide data and basis for fault diagnosis. After data preprocessing, the battery charging efficiency and charging health status can be judged through the preprocessed battery information.

[0067] The difference between the voltage of each single cell and the average voltage is calculated through the pre-processed battery information data, and the single cells are balanced according to the obtained difference through active balancing, thereby ensuring that the status of each single cell in the battery pack remains consistent and extending the life of the entire battery pack.

[0068] In order to evaluate and judge the safety of the battery, a number of monitoring points are set up and deployed in each single cell. The operating status of each single cell is monitored and a set of battery operating coefficients is constructed. The operating status includes the operating temperature and operating charge of each monitoring point of the battery. Based on the historical data of battery operation and the expectations for battery safety management, the operating system range under the battery safety condition can be set. By analyzing the operating coefficient, it is determined whether it is within the safe range, thereby monitoring abnormal risks.

[0069] The disclosed embodiment collects battery information through sensors, pre-processes the collected battery information, and determines the charging efficiency and charging health of the battery; by calculating the difference between the voltage of each single cell and the average voltage, and achieving balance between each single cell through active balancing, it can ensure that the status of each single cell in the battery pack remains consistent, thereby extending the life of the entire battery pack; by setting monitoring cycles and monitoring nodes, the operating status of the battery is fully acquired, a battery operating status set is constructed, and an operating coefficient is generated, and abnormal risks are monitored through the analysis of the operating coefficient set. This multi-dimensional monitoring method can more comprehensively evaluate the risk status of the battery, improve the ability to prevent and control risks, thereby providing early warnings and processing, and improving the safety and reliability of the battery pack.

[0070] Furthermore, the method further comprises:

[0071] Based on the calculation of the operating coefficient, a trend model is established to predict and analyze the battery status data collected in real time to determine the degradation risk of the battery.

[0072] In order to better ensure the safety of battery use, the embodiment of the present disclosure also establishes a trend model through the operating coefficient to predict and analyze the battery status data collected in real time, judge the degradation risk of the battery condition, build and train a vector machine regression model through the operating coefficient data, collect the operating temperature, operating charge and corresponding operating coefficient at different time points, normalize the operating temperature and operating charge, and use these data to fit the model so that the model can learn the relationship between the operating temperature, operating charge and operating coefficient. By comparing the operating coefficient predicted by the model with the actual operating coefficient under the current condition of the battery, it is determined whether the operating coefficient of the battery is consistent with the previous trend, whether the battery condition has undergone a sudden change, and the degradation risk of the battery can be discovered in advance.

[0073] Furthermore, the battery information includes the total voltage V_total of the battery pack, the voltage of each single cell V={V1, V2, V3, ..., Vn}, the battery pack current I, the battery temperature V_W and the external environment temperature V_hw;

[0074] The preprocessing includes calculating the output power of the battery pack, the output power of each single cell, the input power of the battery pack, and the input power of each single cell.

[0075] After collecting the battery information, the battery information is preprocessed and transmitted to the main console. The specific steps of preprocessing are as follows:

[0076] A1. Calculate the total voltage of the battery pack. The specific calculation formula for the total voltage of the battery pack is as follows:

[0077] V_total=V1+V2+V3+...+Vn

[0078] Calculate the battery pack current. The specific calculation formula for the battery pack current is as follows:

[0079] I=(V_nal-V_ial) / R

[0080] Wherein, V_nal represents the output voltage of the battery pack, V_ial represents the input voltage of the battery pack, and R represents the resistance value of the connection circuit;

[0081] A2. Calculate the output power of the battery pack. The specific calculation formula is as follows:

[0082] S=V_total×I

[0083] Where S represents the output power of the battery pack, V_total represents the total voltage of the battery pack, and I represents the current of the battery pack;

[0084] A3. Calculate the output power of each single battery. The specific calculation formula is as follows:

[0085] VS=Vi×I

[0086] Among them, VS represents the output power of each single battery, and Vi represents the output power of each single battery;

[0087] A4. Calculate the input power of the battery pack. The specific calculation formula is as follows:

[0088] D=I×t×f(V_hw)

[0089] Wherein, D represents the input power of the battery pack, t represents the time, V_hw represents the external ambient temperature, and f(V_hw) represents the correction parameter related to the external ambient temperature of the corresponding current;

[0090] A5. Calculate the input power of each single battery. The specific calculation formula is as follows:

[0091] VD=Vi×t×g(V_hw)

[0092] Wherein, VD represents the input power of each single battery; g(V_hw) represents the correction parameter related to the external ambient temperature of the corresponding voltage; f(V_hw) and g(V_hw) are calculated according to the actual charging status;

[0093] Input power. When current enters the battery pack, the open circuit voltage of the battery will change with temperature. When the ambient temperature is high, the battery may overheat, resulting in an increase in side reactions inside the battery and reduced charging efficiency. For example, when a mobile phone is charged in the summer, the temperature of the phone is high and the charging will slow down. Similarly, in the winter, the temperature of the phone is low and the charging will also slow down. The output power of the battery pack, the output power of the single cell, the input power of the battery pack and the input power of the single cell can help understand the working status of the battery. The input power can be used to understand the energy acquisition of the battery during the charging process, which is used to judge the charging efficiency and the charging health of the battery.

[0094] It should be noted that in this embodiment, the voltage of each single cell is measured by connecting a voltage measurement point between the positive and negative electrodes of each single cell. Each voltage measurement point can be obtained through a voltage sensor chip, and the battery temperature and external ambient temperature are measured by thermistors.

[0095] Through preprocessing, the relevant data can be used to evaluate the performance of the battery and provide data and basis for fault diagnosis.

[0096] Furthermore, the calculating of the difference between the voltage of each single cell and the average voltage, and balancing the single cells according to the obtained difference, includes:

[0097] The difference between each cell voltage and the average voltage is calculated using the following formula:

[0098] JY=(Y1+Y2+Y3+...+Yn) / n

[0099] DYc=Yi-JY

[0100] Wherein, Y1, Y2, Y3, ..., Yn represent the voltage value of each single cell, JY represents the average value of the voltage of all single cells, Yi represents the voltage value of any single cell, and DYc represents the voltage difference between the single cell Yi and the average voltage JY;

[0101] A voltage difference threshold is preset, and whether a balancing operation is required is determined according to the calculated voltage difference DYc. When the voltage difference exceeds the preset voltage difference threshold, a balancing operation is performed between the single cells in an active balancing manner.

[0102] By acquiring the voltage of each single cell that makes up the battery pack, the status of each single cell is monitored. The output power of the battery pack can be calculated through the total voltage and current of the battery pack to analyze the performance of the battery pack. The output power calculation of the single cell is related to the battery pack current. The single cell voltage, the total voltage of the battery pack and the voltage of each single cell are used to evaluate the contribution of each single cell in the entire battery pack energy output process.

[0103] DYc represents the difference between the single cell Yi and the average voltage JY. This difference reflects the degree of deviation of the voltage of the single cell relative to the overall average voltage. A voltage difference threshold is preset. According to the calculated voltage difference, it is determined whether a balancing operation is required. When the voltage difference exceeds the preset voltage difference threshold, a balancing operation is performed. The battery is actively discharged through the converter and the control circuit so that the voltage of each single cell is kept at a similar level.

[0104] It should be noted that a technician in this field collects multiple groups of sample data and sets a corresponding preset proportional coefficient for each group of sample data; substitutes the preset proportional coefficient and the collected sample data into the formula, any two formulas constitute a binary first equation group, and the calculated coefficients are screened and averaged to obtain a preset voltage difference threshold;

[0105] The size of the voltage difference threshold is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the corresponding preset proportional coefficient initially set by technical personnel in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0106] Furthermore, the operation status of each single battery is monitored and a set of battery operation coefficients is constructed. By analyzing the set of operation coefficients, abnormal risks are monitored, including:

[0107] Set a monitoring cycle, monitor the operating status of the single battery of each monitoring node during the monitoring cycle, obtain the operating temperature Yw and operating charge Yh of the battery respectively, and then summarize and construct a battery operating status set;

[0108] The operating coefficient YX(w,h) of the battery is generated from the operating state set, and the specific method is as follows:

[0109]

[0110] Wherein, i=1, 2, ..., m, m is a positive integer greater than 1 and is the number of monitoring nodes. is the qualified standard value of the operating temperature, is the qualified standard value of the operating charge, Yw irepresents the battery operating temperature monitored by the i-th monitoring node, Yh i represents the battery operating charge monitored by the i-th monitoring node, Q1 and Q2 represent the weight coefficients corresponding to the operating temperature and the operating charge respectively, and the weight coefficients are: 0≤Q1≤1, 0≤Q2≤1, and Q1+Q2=1; the weight coefficients are determined by referring to the hierarchical analysis method;

[0111] Continuously obtain the operating coefficients YX(w,h) within several monitoring cycles, and then summarize them to construct a set of operating coefficients of the battery;

[0112] Continuously obtain several groups of battery operation coefficients YX(w,h), and preset the maximum operation threshold Smax and the minimum operation threshold Smin based on historical data and expectations for battery safety management to form a moving threshold range [Smax, Smin];

[0113] After obtaining several operating coefficients YX(w,h) of the battery, the changes in the operating coefficient YX(w,h) are tracked, and the threshold range in the moving state is set according to the changes in the operating coefficient YX(w,h). Based on the relationship between the operating coefficient GYX(w,h) and the threshold range, the battery safety is evaluated and judged.

[0114] By setting several monitoring points, the operating temperature Yw and the operating charge Yh of the battery are obtained. The operating charge Yh is measured by a special power sensor, and the operating coefficient YX(w,h) of the battery is generated according to the operating temperature Yw, the operating charge Yh, the qualified standard value of the operating temperature and the qualified standard value of the operating charge. After the operating state coefficient YX(w,h) of the battery is obtained, the operating coefficient YX(w,h) is used to complete a preliminary evaluation of the current operating state of the battery;

[0115] The threshold range [Smax, Smin] is determined according to the operating coefficient of the battery over a period of time, and is the range within which the operating coefficient of the battery is allowed to fluctuate. If the operating coefficient YX(w, h) of the battery is within the threshold range, it means that the operating condition of the battery does not fluctuate much and the battery condition has not changed. If the operating coefficient YX(w, h) of the battery is not within the threshold range [Smax, Smin], it means that the corresponding battery has an operating abnormality during operation, and there is a greater operating risk.

[0116] Preferably, several groups of operating coefficients can be continuously acquired and trend analysis can be performed to observe the changing trend of the operating coefficient over time. If the operating coefficient shows a gradual downward or upward trend, it may indicate that there is a risk of degradation in battery performance. When there is a problem with battery performance, it means that the battery will fail. Based on historical data and expectations for battery safety management, the maximum operating threshold and the minimum operating threshold are preset, and a moving threshold range is formed. When the operating coefficient exceeds the threshold range, the risk of abnormal battery operation can be discovered in time. At the same time, the possible problems that may occur in the battery in the future can also be predicted based on the changing trend of the threshold range. If the threshold range gradually narrows, it may indicate that the stability of the battery is decreasing and the probability of future failures is increasing.

[0117] Furthermore, the specific calculation formula of the threshold range [Smax, Smin] is as follows:

[0118]

[0119] Where n is the number of YX(w,h), is the mean value of the operating coefficient; YX(w,h) j is a set of operating coefficients in the jth monitoring period.

[0120] By the average value of the operating coefficient over a period of time By determining the threshold range [Smax, Smin], it can be determined whether the battery is similar to the most recent operating condition. If the battery condition changes suddenly, the operating coefficient will also change suddenly and fall outside the threshold range, thereby realizing the evaluation and judgment of the battery safety.

[0121] Furthermore, the calculation based on the operation coefficient establishes a trend model to predict and analyze the real-time collected battery status data to determine the degradation risk of the battery, including:

[0122] The battery operating temperature T and operating charge C at different time points are collected, and the corresponding battery operating coefficient YX(w,h) is generated according to the battery operating temperature T and the operating charge C, which are marked as {(T1,C1,YX1),(T2,C2,YX2),...,(T n ,C n ,YX n )}, through the maximum and minimum normalization, the operating temperature and operating charge are processed separately to obtain the normalized temperature T norm and the normalized charge C norm ;

[0123] Using vector machine regression algorithm, through f(x) = w Tφ(x)+b is used to fit the data, with normalized temperature and charge data as input and operating coefficient as output. These data are used to train the vector machine regression model, and the model performance is evaluated by the mean square error and determination coefficient. The specific calculation formula of the mean square error is as follows:

[0124]

[0125] Among them, k represents the number of test set samples, y test represents the true running coefficient of the test set, The specific calculation formula of the operating coefficient R, which represents the model prediction, is as follows:

[0126]

[0127] in, Represents the mean of the true running coefficient of the test set;

[0128] For the newly input data, normalization is performed to obtain in, Represents the normalized temperature data of the new input, Represents the newly input normalized charge data, using the trained model to predict and obtain the predicted value of the operating coefficient:

[0129]

[0130] Among them, w represents the weight vector, b is the bias term of the model, φ(x new ) represents the mapping function, calculates the deviation, and the absolute deviation is The relative deviation is When the deviation exceeds the preset threshold, the battery is judged to be at risk of degradation and an early warning is issued.

[0131] In the above method, the corresponding battery operation coefficient YX(w,h) can be generated according to the operation temperature T and the operation charge C.

[0132] For the operating temperature T, the normalized temperature is:

[0133]

[0134] Among them, T norm represents the normalized temperature, T min Indicates the minimum temperature, T max Indicates the maximum value of temperature;

[0135] For the running charge C, the normalized charge is:

[0136]

[0137] Among them, C norm represents the normalized charge, C min Represents the minimum value of charge, C max Indicates the maximum value of charge;

[0138] The operating coefficient data is mainly used to build and train the vector machine regression model. By collecting the operating temperature, operating charge and corresponding operating coefficient at different time points, normalizing the operating temperature and operating charge, and using these data to fit the model, the model can learn the relationship between the operating temperature, operating charge and operating coefficient.

[0139] First, the battery operating temperature, operating charge and corresponding operating coefficient data at different time points are collected. At this time, the battery operating condition is normal.

[0140] The operating temperature and the operating charge are normalized to the maximum and minimum values ​​to obtain the normalized temperature and charge.

[0141] The normalized temperature and charge data are used as input and the operating coefficient as output. These data are used to train the vector machine regression model, that is, by optimizing the model's weight vector and bias term, the model output is made close to the actual operating coefficient.

[0142] The coefficient of determination is used to measure the degree of fit of the regression model to the data. Its value is between 0 and 1. The closer it is to 1, the better the model fits the data, that is, the higher the proportion of variance of the operating coefficient that the model can explain. The closer it is to 0, the worse the model fits the data.

[0143] In the specific calculation formula of the determination coefficient R, the numerator represents the sum of squares of the errors between the model predicted value and the true value, reflecting the prediction error of the model; the denominator represents the sum of squares of the errors between the true value and the mean of the true values, reflecting the variance of the operating coefficient itself. The coefficient of determination is obtained by subtracting the ratio of the prediction error to the variance of the dependent variable from 1, which represents the proportion of the variance of the dependent variable that the model can explain.

[0144] Substitute the new input data (such as normalized temperature and charge) into the trained model (vector machine regression model) to obtain the predicted value of the operating coefficient.

[0145] Then, the real operating coefficient corresponding to the input data is obtained;

[0146] Finally, the actual operating coefficient and the predicted value are substituted into the absolute deviation calculation formula, and the absolute and relative values ​​of the difference between the two are calculated to obtain the absolute deviation and relative deviation.

[0147] When the deviation exceeds a preset threshold (including when one or both deviation values ​​exceed the preset threshold), the preset threshold can be set according to actual conditions, indicating that the battery condition is at risk of degradation and an early warning is issued.

[0148] The disclosed embodiment calculates the difference between the voltage of each single cell and the average voltage, and realizes the balance between each single cell by active balancing, which can ensure that the status of each single cell in the battery pack remains consistent, thereby extending the life of the entire battery pack. By analyzing the operating coefficient, the abnormal situation of the battery can be discovered in time. When the deviation exceeds the preset threshold, the system can issue an early warning in time to notify the operation and maintenance personnel to take measures. In addition, the disclosed embodiment can also monitor the risk of the battery. By setting the monitoring cycle and monitoring nodes, the operating temperature and operating charge of the battery are fully obtained, the battery operating state set is constructed, and the operating coefficient is generated. Through the analysis of the operating coefficient, the abnormal risk is monitored; at the same time, based on the calculation of the operating coefficient, a trend model is established to predict and analyze the real-time collected data to determine the degradation risk of the battery. This multi-dimensional monitoring method can more comprehensively evaluate the risk status of the battery, improve the ability of risk prevention and control, thereby early warning and processing, and improve the safety and reliability of the battery pack.

[0149] This second embodiment also provides a battery monitoring system based on battery parameters, the specific architecture is as follows Figure 2 As shown, it specifically includes: information collection module, balance management module, operation status monitoring module and trend prediction module; the monitoring process of the system is as follows Figure 3 As shown;

[0150] Information acquisition module: collects battery information through sensors, including the total voltage of the battery pack, the voltage of each single cell, the current of the battery pack, the battery temperature and the external ambient temperature, and pre-processes the collected battery information;

[0151] Balance management module: by calculating the difference between the voltage of each single cell and the average voltage, the balance between each single cell is achieved through active balancing;

[0152] Operation status monitoring module: Set up several monitoring points, deploy each monitoring point in each single battery, monitor the operation status of each single battery and build a battery operation coefficient set. Through the analysis of the operation coefficient, monitor the abnormal risk;

[0153] Trend prediction module: Based on the calculation of the operating coefficient, a trend model is established to predict and analyze the real-time collected data to determine the degradation risk of the battery.

[0154] In this embodiment, it is necessary to specifically explain the information acquisition module, which uses sensors to collect battery information for the battery management system, including the total voltage V_total of the battery pack, the voltage of each single cell V={V1, V2, V3, ..., Vn}, the current I of the battery pack, the battery temperature V_W, and the external environment temperature V_hw. After the collection, the battery information is preprocessed and transmitted to the main control console. The preprocessing includes calculating the output power of the battery pack, the output power of each single cell, the input power of the battery pack, and the input power of each single cell. The specific steps are as follows:

[0155] A1. Calculate the total voltage of the battery pack. The specific calculation formula for the total voltage of the battery pack is as follows:

[0156] V_total=V1+V2+V3+...+Vn

[0157] Calculate the battery pack current. The specific calculation formula for the battery pack current is as follows:

[0158] I=(V_nal-V_ial) / R

[0159] Wherein, V_nal represents the output voltage of the battery pack, V_ial represents the input voltage of the battery pack, and R represents the resistance value of the connection circuit;

[0160] A2. Calculate the output power of the battery pack. The specific calculation formula is as follows:

[0161] S=V_total×I

[0162] Where S represents the output power of the battery pack, V_total represents the total voltage of the battery pack, and I represents the current of the battery pack;

[0163] A3. Calculate the output power of each single battery. The specific calculation formula is as follows:

[0164] VS=Vi×I

[0165] Among them, VS represents the output power of each single battery, and Vi represents the output power of each single battery;

[0166] A4. Calculate the input power of the battery pack. The specific calculation formula is as follows:

[0167] D=I×V_hw

[0168] Where D represents the input power of the battery pack, and V_hw represents the external ambient temperature;

[0169] A5. Calculate the input power of each single battery. The specific calculation formula is as follows:

[0170] VD=Vi×V_hw

[0171] Among them, VD represents the input power of each single battery;

[0172] It should be noted that the voltage of each single cell in the present invention is measured by connecting a voltage measurement point between the positive and negative electrodes of each single cell. Each voltage measurement point can be obtained through a voltage sensor chip, and the battery temperature and external ambient temperature are measured by thermistors.

[0173] In this embodiment, it is necessary to explain the balancing management module, which calculates the difference between the voltage of each single cell and the average voltage through the real-time voltage data transmitted by the information acquisition module. The specific calculation formula of the difference is as follows:

[0174] JY=(Y1+Y2+Y3+...+Yn) / n

[0175] DYc=Yi-JY

[0176] Among them, Y1, Y2, Y3, ..., Yn represent the voltage values ​​of single cells, JY represents the average value of the voltages of all single cells, Yi represents the voltage value of any single cell, DYc represents the difference between the single cell Yi and the average voltage JY, and this difference reflects the degree of deviation of the voltage of the single cell relative to the overall average voltage. A voltage difference threshold is preset, and whether a balancing operation is required is determined based on the calculated voltage difference. When the voltage difference exceeds the preset voltage difference threshold, a balancing operation is performed, and the battery is actively discharged through the converter and the control circuit, so that the voltages of each single cell are kept at a similar level.

[0177] In this embodiment, it is necessary to specifically explain the operation status monitoring module, which receives the temperature data transmitted by the information acquisition module, sets a number of monitoring points, deploys each monitoring point in each single cell, monitors the operation status of each single cell and constructs a battery operation coefficient set, performs trend analysis on a number of groups of operation coefficients YX (w, h) obtained in the operation coefficient set, and monitors the abnormal operation risk of the battery. The specific steps are as follows:

[0178] Step S1, setting a monitoring cycle, for example, every three minutes or five minutes, and having several monitoring nodes within the monitoring cycle to monitor the operating status of each single battery, respectively obtaining the operating temperature Yw and operating charge Yh of the battery, and then summarizing and constructing a battery operating status set;

[0179] Step S2: Generate the battery operation coefficient YX(w,h) from the operation state set, and the specific method is as follows:

[0180]

[0181] Wherein, i=1, 2, ..., m, m is a positive integer greater than 1 and is the number of monitoring nodes. is the qualified standard value of the operating temperature, is the qualified standard value of the operating charge, Yw i represents the battery operating temperature monitored by the i-th monitoring node, Yh i represents the battery operating charge monitored by the i-th monitoring node, Q1 and Q2 represent the weight coefficients corresponding to the operating temperature and the operating charge respectively, and the weight coefficients are: 0≤Q1≤1, 0≤Q2≤1, and Q1+Q2=1; the weight coefficients are determined by referring to the hierarchical analysis method;

[0182] Continuously obtain the operating coefficients YX(w,h) within several monitoring cycles, and then construct the operating coefficient set of the battery after summarizing. After obtaining the operating state coefficient YX(w,h) of the battery, perform a preliminary evaluation of the current operating state of the battery through the operating coefficient YX(w,h);

[0183] Step S3, continuously obtain several groups of battery operation coefficients YX(w,h), preset the maximum operation threshold Smax and the minimum operation threshold Smin based on historical data and the expected safety management of the battery, and form a moving threshold range [Smax, Smin]. The specific calculation formula is as follows:

[0184]

[0185] Where n is the number of YX(w,h), is the mean value of the operating coefficient;

[0186] If the battery operation coefficient YX(w,h) is not within the threshold range [Smax, Smin], it means that the corresponding battery has an abnormal operation during operation, and there is a greater operation risk;

[0187] After obtaining several operating coefficients YX(w,h) of the battery, the changes in the operating coefficient YX(w,h) are tracked, and the threshold range in the moving state is set according to the changes in the operating coefficient YX(w,h). Based on the relationship between the operating coefficient FYX(w,h) and the threshold range, the battery safety is evaluated and judged.

[0188] In this embodiment, it is necessary to explain the trend prediction module, which collects the battery operating temperature T, operating charge C and corresponding operating coefficient YX data at different time points, marked as {(T1, C1, YX1), (T2, C2, YX2), ..., (T n ,C n ,YXn )}, through the maximum and minimum normalization, the operating temperature and operating charge are processed separately. For the operating temperature T, the normalized temperature is:

[0189]

[0190] Among them, T norm represents the normalized temperature, T min Indicates the minimum temperature, T max Represents the maximum value of temperature, for the running charge C, the normalized charge:

[0191]

[0192] Among them, C norm represents the normalized charge, C min Represents the minimum value of charge, C max Indicates the maximum value of charge;

[0193] Using vector machine regression algorithm, through f(x) = w T φ(x)+b is used to fit the data, and the model performance is evaluated by the mean square error and the coefficient of determination. The specific calculation formula of the mean square error is as follows:

[0194]

[0195] Among them, k represents the number of test set samples, y test represents the true running coefficient of the test set, It represents the operating coefficient predicted by the model. The specific calculation formula of the determination coefficient is as follows:

[0196]

[0197] in, Represents the mean of the true running coefficient of the test set;

[0198] For the newly input data, normalization is performed to obtain in, Represents the normalized temperature data of the new input, Represents the newly input normalized charge data, using the trained model to predict and obtain the predicted value of the operating coefficient:

[0199]

[0200] Among them, w represents the weight vector, b is the bias term of the model, φ(x new ) represents the mapping function, calculates the deviation, and the absolute deviation is The relative deviation is When the deviation exceeds the preset threshold, the battery is judged to be at risk of degradation and an early warning is issued.

[0201] It should be noted that a technician in this field collects multiple groups of sample data and sets a corresponding preset proportional coefficient for each group of sample data; substitutes the preset proportional coefficient and the collected sample data into the formula, any two formulas constitute a binary first equation group, and the calculated coefficients are screened and averaged to obtain a preset voltage difference threshold;

[0202] The size of the voltage difference threshold is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the corresponding preset proportional coefficient initially set by technical personnel in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0203] The third embodiment of the present disclosure also provides a battery monitoring system based on battery parameters, such as Figure 4 As shown, the system comprises:

[0204] An information collection module 11, which is configured to collect battery information through sensors and pre-process the collected battery information;

[0205] The balancing management module 12 is configured to determine the charging efficiency and charging health of the battery through the pre-processed battery information, calculate the difference between the voltage of each single cell and the average voltage, and balance the single cells according to the obtained difference;

[0206] The operation status monitoring module 13 is configured to set a number of monitoring points, each of which is deployed in each single cell, to monitor the operation status of each single cell and to construct an operation coefficient set of the battery, and to monitor abnormal risks through analysis of the operation coefficient set.

[0207] Furthermore, the system also includes:

[0208] The trend prediction module 14 is configured to calculate the operation coefficient and establish a trend model to predict and analyze the battery status data collected in real time to determine the degradation risk of the battery.

[0209] Furthermore,

[0210] The battery information includes the total voltage V_total of the battery pack, the voltage of each single cell V={V1, V2, V3, ..., Vn}, the battery pack current I, the battery temperature V_W and the external environment temperature V_hw;

[0211] The preprocessing includes calculating the output power of the battery pack, the output power of each single cell, the input power of the battery pack, and the input power of each single cell.

[0212] Furthermore, the balance management module 12 is specifically configured as follows:

[0213] The difference between each cell voltage and the average voltage is calculated using the following formula:

[0214] JY=(Y1+Y2+Y3+...+Yn) / n

[0215] DYc=Yi+Y2

[0216] Wherein, Y1, Y2, Y3, ..., Yn represent the voltage value of each single cell, JY represents the average value of the voltage of all single cells, Yi represents the voltage value of any single cell, and DYc represents the voltage difference between the single cell Yi and the average voltage JY;

[0217] A voltage difference threshold is preset, and whether a balancing operation is required is determined according to the calculated voltage difference DYc. When the voltage difference exceeds the preset voltage difference threshold, a balancing operation is performed between the single cells in an active balancing manner.

[0218] Furthermore, the operation status monitoring module 13 is specifically configured as follows:

[0219] Set a monitoring cycle, monitor the operating status of the single battery of each monitoring node during the monitoring cycle, obtain the operating temperature Yw and operating charge Yh of the battery respectively, and then summarize and construct a battery operating status set;

[0220] The operating coefficient YX(w,h) of the battery is generated from the operating state set, and the specific method is as follows:

[0221]

[0222] Wherein, i=1, 2, ..., m, m is a positive integer greater than 1 and is the number of monitoring nodes. is the qualified standard value of the operating temperature, is the qualified standard value of the operating charge, Yw i represents the battery operating temperature monitored by the i-th monitoring node, Yh i represents the battery operating charge monitored by the i-th monitoring node, Q1 and Q2 represent the weight coefficients corresponding to the operating temperature and the operating charge respectively, and the weight coefficients are: 0≤Q1≤1, 0≤Q2≤1, and Q1+Q2=1; the weight coefficients are determined by referring to the hierarchical analysis method;

[0223] Continuously obtain the operating coefficients YX(w,h) within several monitoring cycles, and then summarize them to construct a set of operating coefficients of the battery;

[0224] Continuously obtain several groups of battery operation coefficients YX(w,h), and preset the maximum operation threshold Smax and the minimum operation threshold Smin based on historical data and expectations for battery safety management to form a moving threshold range [Smax, Smin]

[0225] After obtaining several operating coefficients YX(w,h) of the battery, the changes in the operating coefficient YX(w,h) are tracked, and the threshold range in the moving state is set according to the changes in the operating coefficient YX(w,h). Based on the relationship between the operating coefficient FYX(w,h) and the threshold range, the battery safety is evaluated and judged.

[0226] Furthermore, the specific calculation formula of the threshold range [Smax, Smin] is as follows:

[0227]

[0228] Where n is the number of YX(w,h), is the mean value of the operating coefficient; YX(w,h) j is a set of operating coefficients in the jth monitoring period.

[0229] Furthermore, the trend prediction module 14 is specifically configured as follows:

[0230] The battery operating temperature T and operating charge C at different time points are collected, and the corresponding battery operating coefficient YX(w,h) is generated according to the battery operating temperature T and the operating charge C, which are marked as {(T1,C1,YX1),(T2,C2,YX2),...,(T n ,C n ,YX n )}, through the maximum and minimum normalization, the operating temperature and operating charge are processed separately to obtain the normalized temperature T norm and the normalized charge C norm ;

[0231] Using vector machine regression algorithm, through f(x) = w T φ(x)+b is used to fit the data, with normalized temperature and charge data as input and operating coefficient as output. These data are used to train the vector machine regression model, and the model performance is evaluated by the mean square error and determination coefficient. The specific calculation formula of the mean square error is as follows:

[0232]

[0233] Among them, k represents the number of test set samples, y test represents the true running coefficient of the test set, The specific calculation formula of the operating coefficient R, which represents the model prediction, is as follows:

[0234]

[0235] in, Represents the mean of the true running coefficient of the test set;

[0236] For the newly input data, normalization is performed to obtain in, Represents the normalized temperature data of the new input, Represents the newly input normalized charge data, using the trained model to predict and obtain the predicted value of the operating coefficient:

[0237]

[0238] Among them, w represents the weight vector, b is the bias term of the model, φ(x new ) represents the mapping function, calculates the deviation, and the absolute deviation is The relative deviation is When the deviation exceeds the preset threshold, the battery is judged to be at risk of degradation and an early warning is issued.

[0239] The battery monitoring system based on battery parameters of the disclosed embodiment is used to implement the battery monitoring method based on battery parameters in the first and second method embodiments, so the description is relatively simple. For details, please refer to the relevant description in the previous method embodiments, which will not be repeated here.

[0240] In addition, if Figure 5 As shown, the fourth embodiment of the present disclosure further provides an electronic device, including a memory 100 and a processor 200, wherein the memory 100 stores a computer program, and when the processor 200 runs the computer program stored in the memory 100, the processor 200 executes the above-mentioned various possible methods.

[0241] The memory 100 is connected to the processor 200. The memory 100 may be a flash memory, a read-only memory or other memory, and the processor 200 may be a central processing unit or a single-chip microcomputer.

[0242] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to perform the above-mentioned various possible methods.

[0243] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable read only memory), flash memory or other memory technology, CD-ROM (Compact Disc Read-Only Memory), Digital Video Disc (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.

[0244] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present disclosure, but the present disclosure is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and substance of the present disclosure, and these modifications and improvements are also considered to be within the scope of protection of the present disclosure.

Claims

1. A battery monitoring method based on battery parameters, characterized in that: The method comprises: Collect battery information through sensors and pre-process the collected battery information; The charging efficiency and charging health of the battery are determined by the pre-processed battery information, and the difference between the voltage of each single cell and the average voltage is calculated, and the single cells are balanced according to the obtained difference; Set up several monitoring points and deploy each monitoring point in each single cell to monitor the operating status of each single cell and build a set of operating coefficients for the battery. By analyzing the set of operating coefficients, monitor abnormal risks.

2. The method according to claim 1, characterized in that The method further comprises: Based on the calculation of the operating coefficient, a trend model is established to predict and analyze the battery status data collected in real time to determine the degradation risk of the battery.

3. The method according to claim 2, characterized in that The battery information includes the total voltage V_total of the battery pack, the voltage of each single battery V={V1, V2, V3, ..., Vn}, the battery pack current I, the battery temperature V_W and the external environment temperature V_hw; The preprocessing includes calculating the output power of the battery pack, the output power of each single cell, the input power of the battery pack, and the input power of each single cell.

4. The method according to claim 2, characterized in that: The step of calculating the difference between the voltage of each single cell and the average voltage, and balancing the single cells according to the obtained difference, comprises: The difference between each cell voltage and the average voltage is calculated using the following formula: JY=(Y1+Y2+Y3+...+Yn) / n DYc=Yi+Y2 Wherein, Y1, Y2, Y3, ..., Yn represent the voltage value of each single cell, JY represents the average value of the voltage of all single cells, Yi represents the voltage value of any single cell, and DYc represents the voltage difference between the single cell Yi and the average voltage JY; A voltage difference threshold is preset, and whether a balancing operation is required is determined according to the calculated voltage difference DYc. When the voltage difference exceeds the preset voltage difference threshold, a balancing operation is performed between the single cells in an active balancing manner.

5. The method according to claim 2, characterized in that: The monitoring of the operating status of each single battery and the establishment of a battery operating coefficient set, and the monitoring of abnormal risks through analysis of the operating coefficient set, include: Set a monitoring cycle, monitor the operating status of the single battery of each monitoring node during the monitoring cycle, obtain the operating temperature Yw and operating charge Yh of the battery respectively, and then summarize and construct a battery operating status set; The operating coefficient YX(w,h) of the battery is generated from the operating state set, and the specific method is as follows: Wherein, i=1, 2, ..., m, m is a positive integer greater than 1 and is the number of monitoring nodes. is the qualified standard value of the operating temperature, is the qualified standard value of the operating charge, Yw i represents the battery operating temperature monitored by the i-th monitoring node, Yh i represents the battery operating charge monitored by the i-th monitoring node, Q1 and Q2 represent the weight coefficients corresponding to the operating temperature and the operating charge respectively, and the weight coefficients are: 0≤Q1≤1, 0≤Q2≤1, and Q1+Q2=1; the weight coefficients are determined by referring to the hierarchical analysis method; Continuously obtain the operating coefficients YX(w,h) within several monitoring cycles, and then summarize them to construct a set of operating coefficients of the battery; Continuously obtain several groups of battery operation coefficients YX(w,h), and preset the maximum operation threshold Smax and the minimum operation threshold Smin based on historical data and expectations for battery safety management to form a moving threshold range [Smax, Smin]; After obtaining several operating coefficients YW(w,h) of the battery, the changes in the operating coefficient YX(w,h) are tracked, and the threshold range in the moving state is set according to the changes in the operating coefficient YX(w,h). Based on the relationship between the operating coefficient FYX(w,h) and the threshold range, the battery safety is evaluated and judged.

6. The method according to claim 5, characterized in that The specific calculation formula of the threshold range [Smax, Smin] is as follows: Where n is the number of TX(w,h), is the mean value of the operating coefficient; YX(w,h) j is a set of operating coefficients in the jth monitoring period.

7. The method according to any one of claims 2 to 6, characterized in that: The calculation based on the operation coefficient establishes a trend model to predict and analyze the real-time collected battery status data to determine the degradation risk of the battery, including: The battery operating temperature T and operating charge C at different time points are collected, and the corresponding battery operating coefficient YX(w,h) is generated according to the battery operating temperature T and the operating charge C, which are marked as {(T1,C1,YX1),(T2,C2,YX2),...,(T n ,C n ,YX n )}, through the maximum and minimum normalization, the operating temperature and operating charge are processed separately to obtain the normalized temperature T norm and the normalized charge C norm ; Using vector machine regression algorithm, through f(x) = w T φ(x)+b is used to fit the data, with normalized temperature and charge data as input and operating coefficient as output. These data are used to train the vector machine regression model, and the model performance is evaluated by the mean square error and determination coefficient. The specific calculation formula of the mean square error is as follows: Among them, k represents the number of test set samples, y test represents the true running coefficient of the test set, The specific calculation formula of the operating coefficient R, which represents the model prediction, is as follows: in, Represents the mean of the true running coefficient of the test set; For the newly input data, normalization is performed to obtain in, Represents the normalized temperature data of the new input, Represents the newly input normalized charge data, using the trained model to predict and obtain the predicted value of the operating coefficient Among them, w represents the weight vector, b is the bias term of the model, φ(x new ) represents the mapping function, y new Represents the true value of the running coefficient for the new input data, calculates the deviation, and the absolute deviation is The relative deviation is When the deviation exceeds the preset threshold, the battery is judged to be at risk of degradation and an early warning is issued.

8. A battery monitoring system based on battery parameters, characterized in that: The system comprises: An information collection module, which is configured to collect battery information through sensors and pre-process the collected battery information; A balancing management module is configured to determine the charging efficiency and charging health of the battery through the pre-processed battery information, calculate the difference between the voltage of each single cell and the average voltage, and balance the single cells according to the obtained difference; The operation status monitoring module is configured to set up a number of monitoring points, deploy each monitoring point in each single cell, monitor the operation status of each single cell and construct a battery operation coefficient set, and monitor abnormal risks through analysis of the operation coefficient set.

9. The system according to claim 8, characterized in that The system further comprises: The trend prediction module is configured to calculate the operating coefficient and establish a trend model to predict and analyze the battery status data collected in real time to determine the degradation risk of the battery.

10. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor runs the computer program stored in the memory, the processor executes the battery monitoring method based on battery parameters as described in any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the battery monitoring method based on battery parameters as described in any one of claims 1 to 7 is implemented.

Images