Power battery safety early warning method and system based on slope change rate

Abstract

The invention relates to the technical field of power battery monitoring, and discloses a power battery safety early warning method and system based on a slope change rate, and the method comprises the steps: determining the statistical feature and relative feature information of voltage list data in charging segment data; performing grid division processing on a preset SOC interval, and calculating a slope matrix and a slope growth rate matrix of the vehicle in at least one grid based on the statistical feature and relative feature information; training a preset model by adopting the training data, and determining a target early warning model; and performing safety early warning on the power battery of the to-be-detected vehicle by adopting the target early warning model, and determining a safety early warning result of the to-be-detected vehicle. According to the method provided by the embodiment of the invention, by screening the charging fragment data in the preset SOC interval and extracting the statistical feature and relative feature information of the voltage, the calculation complexity can be reduced, so that the calculation delay time is shortened, and the safety detection efficiency is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of power battery monitoring, and in particular to a power battery safety early warning method and system based on slope change rate. Background Art

[0002] With the widespread use of new energy vehicles, fires and spontaneous combustion of new energy vehicles occur from time to time, a large part of which occurs during the charging process of new energy vehicles. How to provide early safety warnings for new energy vehicle power batteries has become the key to solving this safety problem.

[0003] In the related technologies, knowledge-based fault diagnosis methods, model-based fault diagnosis methods and data-driven fault diagnosis methods are often used to perform safety detection on power batteries. However, the related technologies may have problems such as long calculation delay time and low safety detection efficiency. Therefore, how to reduce the calculation delay time and improve the efficiency of safety detection has become a problem that needs to be solved. Summary of the invention

[0004] In view of this, the present disclosure provides a power battery safety warning method and system based on slope change rate to solve the problem of how to reduce calculation delay time and improve the efficiency of safety detection.

[0005] On the one hand, the present disclosure provides a power battery safety warning method based on slope change rate, the method comprising: screening out charging segment data in a preset SOC range from original message data of the vehicle, and determining statistical features and relative feature information of voltage list data in the charging segment data; the vehicle comprises a faulty vehicle and a normal vehicle; based on a preset grid size, performing grid division processing on a preset SOC range, and based on statistical features and relative feature information, calculating a slope matrix and a slope growth rate matrix of the vehicle in at least one grid; combining the slope growth rate matrix of the vehicle and a fault condition label as training data, using the training data to train a preset model, and determining a target warning model; using the target warning model to perform safety warning on the power battery of the vehicle to be detected, and determining a safety warning result of the vehicle to be detected.

[0006] On the other hand, the present disclosure also provides a power battery safety warning system based on slope change rate, the system includes a data processing module, a feature calculation module, a model training module and a model prediction module, wherein: the data processing module is used to filter out charging segment data in a preset SOC range from the original message data of the vehicle, and determine the statistical characteristics and relative characteristic information of the voltage list data in the charging segment data; the vehicle includes a faulty vehicle and a normal vehicle; the feature calculation module is used to perform grid division processing on the preset SOC range based on a preset grid size, and calculate the slope matrix and slope growth rate matrix of the vehicle in at least one grid based on the statistical characteristics and relative characteristic information; the model training module is used to combine the slope growth rate matrix of the vehicle and the fault condition label into training data, use the training data to train the preset model, and determine the target warning model; the model prediction module is used to use the target warning model to perform safety warning on the power battery of the vehicle to be detected, and determine the safety warning result of the vehicle to be detected.

[0007] On the other hand, the present disclosure further provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to implement the above-mentioned power battery safety warning method based on slope change rate.

[0008] On the other hand, the present disclosure further provides a computer program product, including computer instructions, which are used to enable a computer to execute the above-mentioned power battery safety early warning method based on slope change rate.

[0009] Through the power battery safety warning method and system based on slope change rate of the above-mentioned embodiments of the present invention, by screening the charging segment data in the preset SOC range and extracting the statistical characteristics and relative characteristic information of the voltage, the complexity of the calculation can be reduced, thereby reducing the calculation delay time and improving the efficiency of safety detection.

[0010] In addition, through the slope matrix and the slope growth rate matrix, the method can refine the trend of voltage change during battery charging, thereby improving the accuracy of fault warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0012] Figure 1 is a flow chart of a power battery safety early warning method based on slope change rate provided in an embodiment of the present disclosure;

[0013] Figure 2 is a specific flow chart of a power battery safety early warning method based on slope change rate provided in an embodiment of the present disclosure;

[0014] Figure 3 is a structural schematic diagram of a power battery safety warning system based on slope change rate provided in an embodiment of the present disclosure;

[0015] Figure 4 It is another structural schematic diagram of the power battery safety warning system based on slope change rate provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0016] With the advancement of energy conservation and emission reduction policies, new energy vehicles have been rapidly popularized and the market has shown explosive growth. New energy vehicles play an important role in alleviating the pollution caused by traditional fuel vehicles and reducing dependence on fossil energy, and are the key to achieving sustainable development. However, with the widespread application of new energy vehicles, the phenomenon of smoke, fire, and even spontaneous combustion during charging has gradually increased, and a large part of the faults occur during the charging process.

[0017] Therefore, safety warning for new energy vehicle power batteries has become an important issue. Solving this problem will help reduce the failure rate, increase battery life, and protect life and property safety. The health and safety of the power battery system are mainly reflected in voltage, internal resistance, capacity and temperature, among which battery voltage is the most direct form of expression.

[0018] In the related technologies, power battery fault diagnosis technology can be divided into three categories: knowledge-based fault diagnosis method, model-based fault diagnosis method and data-driven fault diagnosis method. Although these methods have certain advantages, they still have some obvious shortcomings:

[0019] 1. Knowledge-based fault diagnosis methods require in-depth understanding of complex battery failure mechanisms, making it difficult to establish an accurate diagnostic model, resulting in low accuracy of fault diagnosis.

[0020] 2. Model-based fault diagnosis methods rely heavily on high-precision models and modeling techniques, and it is difficult to preset appropriate fault thresholds, resulting in insufficient adaptability of fault diagnosis.

[0021] 3. Data-driven fault diagnosis method: There are problems such as difficulty in fault location and long calculation delay.

[0022] To solve the above problems, various embodiments of the present disclosure provide a power battery safety warning method based on slope change rate, the method comprising: screening out charging segment data in a preset SOC range from the original message data of the vehicle, and determining the statistical characteristics and relative characteristic information of the voltage list data in the charging segment data; the vehicle comprises a faulty vehicle and a normal vehicle; based on a preset grid size, a preset SOC range is grid-divided, and based on the statistical characteristics and relative characteristic information, a slope matrix and a slope growth rate matrix of the vehicle in at least one grid are calculated; the slope growth rate matrix of the vehicle and a fault condition label are combined into training data, a preset model is trained using the training data, and a target warning model is determined; using the target warning model, a safety warning is performed on the power battery of the vehicle to be detected, and a safety warning result of the vehicle to be detected is determined.

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0024] Please refer to Figure 1 , Figure 1 : is a flow chart of a power battery safety warning method based on slope change rate provided by an embodiment of the present disclosure. The flow of the method may include the following steps:

[0025] Step S101 , screening out charging segment data in a preset SOC range from original message data of the vehicle, and determining statistical characteristics and relative characteristic information of voltage list data in the charging segment data.

[0026] In this embodiment, the vehicle includes a faulty vehicle and a normal vehicle, wherein the faulty vehicle may refer to a vehicle with a problem in the dynamic battery.

[0027] The original message data of the vehicle may refer to the preliminary collected data of the vehicle, and the original message data may include but is not limited to: operating status information, sensor information, and control information.

[0028] The battery state of charge (SOC) interval can be the battery power percentage; the preset SOC interval can be a preset power percentage interval. According to the exploration of vehicle sample data, when the SOC is between [40-60], the trend consistency of each parking charging segment data is better, which is more conducive to the construction and extraction of subsequent features and maintains good feature data quality. Here, the preset SOC interval can be set according to actual needs and is not limited here.

[0029] In a possible implementation, data with a charging status identifier of 1 is filtered out from the original message data to determine the original charging segment data;

[0030] The charging segment data with the battery SOC between [40-60] is filtered out from the original charging segment data.

[0031] Furthermore, the statistical characteristics of the voltage list data in the charging segment data can be key indicators for describing the overall distribution, variation range and central tendency of the voltage list data. The relative characteristic information can be data comparing the statistical characteristics with the reference value to reflect the degree of deviation and uneven distribution in the voltage data.

[0032] Step S102 , based on a preset grid size, a preset SOC interval is grid-divided, and based on statistical characteristics and relative characteristic information, a slope matrix and a slope growth rate matrix of the vehicle in at least one grid are calculated.

[0033] In this embodiment, a grid may refer to a number of equally spaced small intervals as a basic unit for analysis and feature extraction; the interval between the grids is the preset grid size. The preset SOC interval is divided into a number of small intervals according to the preset gateway size.

[0034] As an example, assuming that the preset SOC interval S=[40,60] and the preset grid size s=5, S can be divided into 4 grids, namely [40,45), [45,50), [50,55), and [40,60].

[0035] Furthermore, the slope matrix may be a two-dimensional matrix for describing the voltage characteristic variation trend of each vehicle in each SOC grid in different charging segments, and the slope growth rate matrix may be used to describe the slope variation trend between different charging segments.

[0036] Step S103, combining the slope growth rate matrix of the vehicle and the fault condition label as training data, using the training data to train a preset model, and determining a target warning model.

[0037] In this embodiment, the fault condition label can be represented by 1 or 0, wherein 1 can indicate that there is a fault in the vehicle, and 0 can indicate that there is no fault in the vehicle.

[0038] The preset model may be an existing or future model, which is not specifically limited here. For example, the preset model may adopt a support vector machine (SVM) model.

[0039] Here, the SVM model can map low-dimensional nonlinear problems to high-dimensional space through kernel functions, find a linearly separated hyperplane in the high-dimensional space, and thus solve the nonlinear classification problem. However, the data scale in the disclosed embodiment is limited, which is suitable for small sample learning, and the features constructed by the slope matrix and the slope growth rate matrix in the disclosed embodiment have certain nonlinear and high-dimensional characteristics. Therefore, the SVM model is suitable for the disclosed embodiment.

[0040] Step S104, using the target warning model to perform a safety warning on the power battery of the vehicle to be detected, and determining the safety warning result of the vehicle to be detected.

[0041] In this embodiment, the slope growth rate matrix corresponding to the power battery of the vehicle to be detected is determined, and the slope growth rate matrix of the vehicle to be detected is input into the target warning model to obtain the safety warning result corresponding to the vehicle to be detected.

[0042] Specifically, when the output result of the vehicle to be detected is 1, the safety warning result of the vehicle to be detected is that there is a fault, and fault-related information is output; when the output result of the vehicle to be detected is 0, the safety warning result of the vehicle to be detected is that there is no fault, and relevant prompt information is output.

[0043] As an example, fault-related information may include, but is not limited to: the last frame time of the charging segment, SOC, current, and temperature; the related prompt information may be "So far, everything is normal with the vehicle."

[0044] In the power battery safety warning method and system based on slope change rate of the above embodiment of the present disclosure, by screening the charging segment data in the preset SOC interval and extracting the statistical characteristics and relative characteristic information of the voltage, the complexity of the calculation can be reduced, thereby reducing the delay time of the calculation and improving the efficiency of safety detection. Through the slope matrix and the slope growth rate matrix, the method can refine the trend of voltage change during battery charging, thereby improving the accuracy of fault warning.

[0045] In a possible implementation of the above step S101, the charging segment data in the preset SOC range is screened out from the original message data of the vehicle, including:

[0046] Acquire original message data of the vehicle, and extract at least one original charging segment data of the vehicle from the original message data based on the charging status field;

[0047] Based on the preset SOC interval, at least one charging segment data in the preset SOC interval is extracted from at least one original charging segment data, and the at least one charging segment data is pre-processed.

[0048] In this embodiment, original message data of a normal vehicle and a faulty vehicle are obtained, and based on the charging status field whose value is 1, at least one original charging segment data corresponding to the normal vehicle and the faulty vehicle is extracted from the original message data.

[0049] In a possible implementation, based on a preset SOC interval, extracting at least one charging segment data in the preset SOC interval from at least one original charging segment data, and preprocessing the at least one charging segment data may include:

[0050] At least one charging segment data between [40-60] is extracted from at least one original charging segment data, and the at least one charging segment data is pre-processed.

[0051] The preprocessing may include: cleaning the monomer voltage list to delete invalid data; detecting whether there are abnormal values ​​in the monomer voltage list, and deleting the entire frame of data when there are abnormal values.

[0052] Here, the format of the single cell voltage list may be [v1_v2_..._vn-1_vn], indicating the voltage value of the nth single cell, where n may be the number of cells.

[0053] Furthermore, invalid data may include: a null value or an unfilled cell voltage value, a voltage value that is not a floating point number or an integer or non-integer value. Abnormal values ​​may include a cell voltage value that is greater than 5V or 0V.

[0054] In the power battery safety warning method and system based on slope change rate of the above embodiment of the present disclosure, the charging segment data is extracted through the charging status field, which can effectively filter the original message data, accurately locate the charging status of the vehicle, and avoid invalid or charging-irrelevant data interfering with the analysis. Data cleaning is performed in the extracted charging segment data to ensure the integrity and accuracy of the data and avoid the influence of noise data on subsequent modeling and feature extraction. By limiting the SOC interval, unnecessary large-scale data processing is reduced, the computational complexity is reduced, and the efficiency of model training and prediction is improved.

[0055] In a possible implementation of the above embodiment, determining the statistical characteristics and relative characteristic information of the voltage list data in the charging segment data is implemented based on the following steps:

[0056] Perform feature extraction on at least one charging segment data to obtain original matrix data of the vehicle; the original matrix data at least includes a voltage list;

[0057] Based on the voltage list in the original matrix data, determining statistical characteristics of the vehicle, the statistical characteristics including at least one of the following: maximum single cell voltage, minimum single cell voltage, average voltage value, extreme positive deviation, and extreme negative deviation;

[0058] Based on the statistical characteristics, relative characteristic information of the vehicle is determined, where the relative characteristic information includes at least one of the following: a relative extreme positive deviation and a relative extreme negative deviation.

[0059] In this embodiment, feature extraction is performed on at least one charging segment data to obtain original matrix data of the vehicle; the original matrix data includes at least a voltage list, which may include:

[0060] Feature extraction is performed on at least one charging segment data to obtain original matrix data of the vehicle as shown in the following formula.

[0061] Here, the formula of the original matrix data can be D=[Time, U, I, V, T].

[0062] Among them, Time in the matrix can represent the data acquisition time, that is, the timestamp; U can represent the total voltage; I represents the total current; V represents the voltage list, and the format in the data can be [1:v1_v2_……_vn-1_vn], vi represents the voltage value of the i-th monomer, and n represents the number of monomers. In the subsequent feature construction, they need to be converted into a list form; T represents the temperature list data, and the format in the data is [1:t1_t2_……_tm-1_tm], tj represents the detection temperature value of the j-th temperature probe, and m represents the number of temperature probes.

[0063] In one possible implementation, the maximum cell voltage can be expressed as V max =max(v 1 ,v 2 ,...,v n ) calculation; the minimum single cell voltage can be calculated using the formula V min =min(v 1 ,v 2 ,...,v n ) is calculated; the average voltage value is calculated using the formula Calculation; extreme positive deviations can be calculated using the formula Calculation; extreme negative deviations can be calculated using the formula calculate.

[0064] Among them, the extreme positive deviation can indicate the difference between the voltage value of the single cell with the highest voltage in the single cell battery and the average voltage value of all single cells, that is, the degree of deviation of the single cell with the highest voltage from the average voltage, reflecting the single cell in the battery that may have the risk of overcharging. The extreme negative deviation can indicate the difference between the voltage value of the single cell with the lowest voltage in the single cell battery and the average voltage value of all single cells, that is, the degree of deviation of the single cell with the lowest voltage from the average voltage, reflecting the single cell in the battery that may have the risk of overdischarging.

[0065] In one possible implementation, Indicates a relatively extreme positive deviation, which can be expressed as Indicates a relatively extreme negative deviation.

[0066] Among them, the relative extreme positive deviation can reflect the degree of deviation of the single cell voltage with the highest voltage in the single cell relative to the average voltage of all single cells, that is, it directly reflects the possible overcharge risk in the battery in the form of percentage. The relative extreme negative deviation can reflect the degree of deviation of the single cell voltage with the lowest voltage in the single cell relative to the average voltage of all single cells, that is, it directly reflects the possible over-discharge risk in the battery in the form of percentage.

[0067] In the power battery safety warning method and system based on the slope change rate of the above embodiment of the present disclosure, by extracting the maximum and minimum single cell voltages, the abnormal single cells in the battery pack can be quickly located, and the judgment of whether there is a risk of overcharging or over-discharging can be assisted, so as to accurately identify the voltage distribution state of the power battery. The consistency of the single cell voltage in the battery pack can be quantified through the extreme deviation and its relative deviation, so as to predict the possible failure trend. Through the comprehensive analysis of statistical characteristics and relative characteristic information, the small abnormal fluctuations of the power battery can be accurately captured, avoiding the situations that may be missed by traditional methods, and improving the accuracy of fault identification.

[0068] In a possible implementation of the above step S102, based on the statistical features and the relative feature information, the slope matrix and the slope growth rate matrix of the vehicle in at least one grid are calculated, which is implemented based on the following steps:

[0069] Based on the statistical characteristics, determining a relative extreme negative deviation of a start frame of a target grid and a relative extreme negative deviation of an end frame of the target grid in the target charging segment data;

[0070] calculating a slope value of a target grid in the target charging segment data based on a relative extreme negative deviation of a start frame and a relative extreme negative deviation of an end frame, and constructing a slope matrix of the vehicle based on the slope value of each gateway in the at least one gateway;

[0071] Based on the slope matrix, construct the vehicle's slope growth rate matrix.

[0072] In this embodiment, based on the statistical features, determining the relative extreme negative deviation of the start frame of the target grid and the relative extreme negative deviation of the end frame of the target grid in the target charging segment data may include:

[0073] The extreme relative negative deviation of the starting frame of the target grid is determined as The extreme relative negative deviation of the end frame of the target grid is recorded as

[0074] Here, the target grid may be the qth grid in the pth charging segment.

[0075] Further, based on the relative extreme negative deviation of the start frame and the relative extreme negative deviation of the end frame, calculating the slope value of the target grid in the target charging segment data may include:

[0076] The slope calculation formula is used to determine the slope of the qth grid in the pth charging segment as the target grid.

[0077] The slope calculation formula is as follows:

[0078]

[0079] Here, s may refer to a preset grid size.

[0080] Furthermore, based on the slope value of each gateway in at least one gateway, a slope matrix of the vehicle is constructed, which can be shown as follows:

[0081]

[0082] Where p can represent the pth charging segment, q can represent the qth grid divided, and r p,q The slope of the qth grid in the pth charging segment can be represented by .

[0083] In a possible implementation, the number W of charging segments for each vehicle may be further limited, and the initial value of W may be set to 5, that is, the number of charging segment data for each vehicle is not less than 5. The size of W here may be specifically set according to actual needs and is not limited.

[0084] Furthermore, we can use the formula represents the slope growth rate of the qth grid in the pth charging segment. The constructed slope growth rate matrix can be shown as follows:

[0085]

[0086] In the power battery safety warning method and system based on slope change rate of the above embodiment of the present disclosure, by constructing a slope matrix and a slope growth rate matrix in a unified format, standardized input data is provided for a machine learning model (such as SVM), thereby improving the efficiency of fault identification. The combined use of the slope matrix and the slope growth rate matrix combines the static characteristics of battery performance with the dynamic characteristics, providing a richer information dimension for fault diagnosis and improving the accuracy of identification.

[0087] In a possible implementation of the above step S103, the slope growth rate matrix of the vehicle and the fault condition label are combined as training data, and the training data is used to train a preset model to determine a target warning model, including:

[0088] Setting a first label for the slope growth rate matrix of the faulty vehicle and setting a second label for the slope growth rate matrix of the normal vehicle;

[0089] The slope growth rate matrix of the faulty vehicle and the slope growth rate matrix of the normal vehicle are vertically spliced ​​as input values ​​in the training data, and the first label and the second label are used as output values ​​in the training data;

[0090] The training data is used to train the support vector machine model to determine the target warning model corresponding to the minimum objective function.

[0091] In this embodiment,

[0092] The step of setting a first label for the slope growth rate matrix of the faulty vehicle and setting a second label for the slope growth rate matrix of the normal vehicle may include:

[0093] , set the slope growth rate matrix of the faulty vehicle to 1, and set the slope growth rate matrix of the normal vehicle to 0.

[0094] Furthermore, by introducing the kernel function during the training process of the SVM model, the linear inseparable problem can be mapped to a high-dimensional space, thereby obtaining the optimal separation plane. At this time, the solution to the optimal separation plane is transformed into the following objective function and constraints:

[0095]

[0096] Among them, b is the deviation, C is the penalty factor, and the slack variable τ i ≥0, i∈[1,n]; y i is the y-axis coordinate point; x i is the x-axis coordinate point. Determine the SVM model with the minimum objective function as the target warning model.

[0097] In the power battery safety warning method and system based on slope change rate of the above embodiment of the present disclosure, by marking the features of faulty vehicles and normal vehicles with different labels, the model can effectively identify the feature distribution of vehicles of different categories, which is helpful for accurate classification. By vertically splicing the slope growth rate matrices of multiple vehicles, the diversity of training data is expanded, covering the feature differences of different vehicles and different charging states, and improving the generalization ability and adaptability of the model. By training the SVM model, finding the parameter combination that minimizes the objective function, and constructing an optimal fault warning system, early detection and warning of power battery failures can be achieved.

[0098] In a specific embodiment, please refer to Figure 2 , Figure 2 : is a specific flow chart of a power battery safety warning method based on slope change rate provided by an embodiment of the present disclosure, and the flow may include the following steps:

[0099] Step S201, processing the original message data to determine statistical features and relative feature information;

[0100] Step S202, determining a slope matrix based on statistical features and relative feature information;

[0101] Step S203, determining a slope growth rate matrix based on the slope matrix;

[0102] Step S204, combining the slope growth rate matrix and the fault condition label into training data;

[0103] Step S205, using the training data to train the preset model to determine the target early warning model;

[0104] Step S206: Use the target warning model to issue a safety warning to the predicted vehicle.

[0105] In one embodiment, a power battery safety warning system 300 based on slope change rate is provided, and the power battery safety warning system 300 based on slope change rate corresponds to the power battery safety warning method based on slope change rate in the above embodiment. Figure 3 As shown, the system includes a data processing module 301, a feature calculation module 302, a model training module 303 and a model prediction module 304, wherein each functional module is described in detail as follows:

[0106] The data processing module 301 is used to filter out charging segment data in a preset SOC interval from the original message data of the vehicle, and determine the statistical characteristics and relative characteristic information of the voltage list data in the charging segment data; the vehicle includes a faulty vehicle and a normal vehicle;

[0107] A feature calculation module 302, configured to perform grid division processing on a preset SOC interval based on a preset grid size, and calculate a slope matrix and a slope growth rate matrix of the vehicle in at least one grid based on statistical features and relative feature information;

[0108] The model training module 303 is used to combine the slope growth rate matrix of the vehicle and the fault condition label into training data, use the training data to train the preset model, and determine the target warning model;

[0109] The model prediction module 304 is used to use the target warning model to perform safety warning on the power battery of the vehicle to be detected and determine the safety warning result of the vehicle to be detected.

[0110] In one embodiment, the data processing module 301 is used to obtain original message data of the vehicle, and extract at least one original charging segment data of the vehicle from the original message data based on the charging status field;

[0111] Based on the preset SOC interval, at least one charging segment data in the preset SOC interval is extracted from at least one original charging segment data, and the at least one charging segment data is pre-processed.

[0112] In one embodiment, the data processing module 301 is used to extract features from at least one charging segment data to obtain original matrix data of the vehicle; the original matrix data at least includes a voltage list;

[0113] Based on the voltage list in the original matrix data, determining statistical characteristics of the vehicle, the statistical characteristics including at least one of the following: maximum single cell voltage, minimum single cell voltage, average voltage value, extreme positive deviation, and extreme negative deviation;

[0114] Based on the statistical characteristics, relative characteristic information of the vehicle is determined, where the relative characteristic information includes at least one of the following: a relative extreme positive deviation and a relative extreme negative deviation.

[0115] In one embodiment, the feature calculation module 302 is used to determine the relative extreme negative deviation of the start frame of the target grid and the relative extreme negative deviation of the end frame of the target grid in the target charging segment data based on the statistical features;

[0116] calculating a slope value of a target grid in the target charging segment data based on the relative extreme negative deviation of the start frame and the relative extreme negative deviation of the end frame, and constructing a slope matrix of the vehicle based on the slope value of each gateway in the at least one gateway;

[0117] Based on the slope matrix, construct the vehicle's slope growth rate matrix.

[0118] In one embodiment, the model training module 303 is used to set a first label for the slope growth rate matrix of the faulty vehicle and set a second label for the slope growth rate matrix of the normal vehicle;

[0119] The slope growth rate matrix of the faulty vehicle and the slope growth rate matrix of the normal vehicle are vertically spliced ​​as input values ​​in the training data, and the first label and the second label are used as output values ​​in the training data;

[0120] The training data is used to train the support vector machine model to determine the target warning model corresponding to the minimum objective function.

[0121] It should be noted that: the above embodiment provides a power battery safety warning system based on slope change rate. When implementing the corresponding power battery safety warning method based on slope change rate, only the division of the above program modules is used as an example. In actual application, the above processing can be assigned to different program modules as needed, that is, the internal structure of the above system can be divided into different program modules to complete all or part of the above-described processing. In addition, the system provided by the above embodiment and the corresponding Figure 1 The embodiments of the method shown belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0122] The present disclosure also provides a computer device having the above Figure 3 The power battery safety warning system based on slope change rate is shown.

[0123] See also Figure 4 , Figure 4 is another structural schematic diagram of a power battery safety warning system based on slope change rate provided by an embodiment of the present disclosure, such as Figure 4 As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other, and can be installed on a common mainboard or installed in other ways as required. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output system (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0124] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0125] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0126] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0127] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0128] The computer device also includes an input system 30 and an output system 40. The processor 10, the memory 20, the input system 30 and the output system 40 may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0129] The input system 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output system 40 may include a display device, an auxiliary lighting system (e.g., LED) and a tactile feedback system (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0130] The computer device also includes a communication interface, which is used for the computer device to communicate with other devices or a communication network.

[0131] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium and downloaded through a network, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0132] A part of the present disclosure may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present disclosure through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0133] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A power battery safety early warning method based on slope change rate, characterized in that: The method comprises: Screening out charging segment data in a preset SOC interval from the original message data of the vehicle, and determining statistical characteristics and relative characteristic information of voltage list data in the charging segment data; the vehicle includes a faulty vehicle and a normal vehicle; Based on a preset grid size, the preset SOC interval is grid-divided, and based on the statistical characteristics and the relative characteristic information, a slope matrix and a slope growth rate matrix of the vehicle in at least one grid are calculated; The slope growth rate matrix of the vehicle and the fault condition label are combined into training data, and a preset model is trained using the training data to determine a target early warning model; The target warning model is used to perform safety warning on the power battery of the vehicle to be detected, and the safety warning result of the vehicle to be detected is determined.

2. The method according to claim 1, characterized in that The step of filtering out charging segment data in a preset SOC range from the original message data of the vehicle includes: Acquire original message data of a vehicle, and extract at least one original charging segment data of the vehicle from the original message data based on a charging status field; Based on a preset SOC interval, at least one charging segment data in the preset SOC interval is extracted from the at least one original charging segment data, and the at least one charging segment data is pre-processed.

3. The method according to claim 2, characterized in that Determining the statistical characteristics and relative characteristic information of the voltage list data in the charging segment data is achieved based on the following steps: Performing feature extraction on at least one charging segment data to obtain original matrix data of the vehicle; the original matrix data at least includes a voltage list; Determine the statistical characteristics of the vehicle based on the voltage list in the original matrix data, the statistical characteristics comprising at least one of the following: maximum cell voltage, minimum cell voltage, average voltage value, extreme positive deviation, and extreme negative deviation; Based on the statistical characteristics, relative characteristic information of the vehicle is determined, and the relative characteristic information includes at least one of the following: a relative extreme positive deviation and a relative extreme negative deviation.

4. The method according to claim 3, characterized in that: Based on the statistical features and the relative feature information, a slope matrix and a slope growth rate matrix of the vehicle in at least one grid are calculated, which is achieved based on the following steps: Based on the statistical characteristics, determining a relative extreme negative deviation of a start frame of a target grid in the target charging segment data and a relative extreme negative deviation of an end frame of the target grid; calculating a slope value of the target grid in the target charging segment data based on the relative extreme negative deviation of the start frame and the relative extreme negative deviation of the end frame, and constructing a slope matrix of the vehicle based on the slope value of each gateway in at least one gateway; Based on the slope matrix, a slope growth rate matrix of the vehicle is constructed.

5. The method according to claim 1, characterized in that The step of combining the slope growth rate matrix of the vehicle and the fault condition label as training data, using the training data to train a preset model, and determining a target early warning model includes: Setting a first label for the slope growth rate matrix of the faulty vehicle and setting a second label for the slope growth rate matrix of the normal vehicle; The slope growth rate matrix of the faulty vehicle and the slope growth rate matrix of the normal vehicle are longitudinally spliced ​​as input values ​​in the training data, and the first label and the second label are used as output values ​​in the training data; The training data is used to train a support vector machine model to determine the target warning model corresponding to the minimum target function.

6. The power battery safety warning system based on slope change rate is characterized by: The system includes a data processing module, a feature calculation module, a model training module and a model prediction module, wherein: A data processing module, used to filter out charging segment data in a preset SOC interval from the original message data of the vehicle, and determine the statistical characteristics and relative characteristic information of the voltage list data in the charging segment data; the vehicle includes a faulty vehicle and a normal vehicle; A feature calculation module, configured to perform grid division processing on the preset SOC interval based on a preset grid size, and calculate a slope matrix and a slope growth rate matrix of the vehicle in at least one grid based on the statistical feature and the relative feature information; A model training module, used to combine the slope growth rate matrix of the vehicle and the fault condition label as training data, use the training data to train a preset model, and determine a target early warning model; The model prediction module is used to use the target warning model to perform safety warning on the power battery of the vehicle to be detected and determine the safety warning result of the vehicle to be detected.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the power battery safety early warning method based on slope change rate according to any one of claims 1 to 5.

8. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the power battery safety early warning method based on slope change rate according to any one of claims 1 to 5.

Images