Unmanned vehicle power battery safety detection method and system based on big data

Abstract

The invention provides an unmanned vehicle power battery safety detection method and system based on big data, and relates to the technical field of power battery safety detection.The method comprises the steps that a battery appearance image of a power battery is collected; determining an appearance safety detection score of the power battery according to the battery appearance image; acquiring historical operation data; determining a power battery aging influence coefficient according to the historical operation data; battery parameters of the power battery are obtained through the battery management system; obtaining the internal resistance of the power battery through a detection instrument; determining a battery operation safety detection score according to the battery internal resistance, the battery parameters and the power battery aging influence coefficient; and generating a power battery safety detection report according to the battery operation safety detection score and the battery appearance safety detection score. According to the invention, the safety condition of the power battery can be comprehensively detected according to the appearance safety and the operation safety of the power battery, and the comprehensiveness and the accuracy of the safety detection result of the power battery are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power battery safety detection, and in particular to a method and system for unmanned vehicle power battery safety detection based on big data. Background Art

[0002] In the related art, CN114137428A discloses a portable power battery safety detection system and device, including a main control module, an input module, a data acquisition module, an OBD data acquisition module, a network module, a cloud server module and a connection module; by connecting the detection device in series between the charging pile and the electric vehicle, the health status detection function of the power battery during the charging process is realized, and the collected data is subjected to multiple detection and analysis using the health diagnosis algorithm and the fault diagnosis algorithm, and finally a comprehensive and accurate detection result report is obtained. This solution has the advantages of simple and convenient power battery safety detection process, accurate power battery health status assessment results, and effectively improving the safety of electric vehicle use.

[0003] CN116298478A discloses a functional safety detection method, device and vehicle for a power battery. The method includes: obtaining a first current signal, a second current signal, a voltage signal and a temperature signal corresponding to the power battery, wherein the first current signal is a digital signal and the second current signal is an analog signal; performing sensor fault diagnosis and overcurrent detection based on the first current signal and the second current signal to obtain a first detection result; performing rationality detection and overcurrent detection based on the voltage signal, the temperature signal and the opening and closing state of the contactor of the power battery to obtain a second detection result; determining a target overcurrent detection result corresponding to the power battery according to the first detection result and the second detection result. The solution solves the technical problem that the existing functional safety detection method for power batteries only uses current sensors for overcurrent detection, resulting in low accuracy and poor safety.

[0004] Based on the above related technologies, the accuracy of the power battery health status assessment results can be improved. However, the related technologies do not take into account the impact of the power battery's appearance and the vehicle and usage conditions on the power battery safety status assessment. That is, the related technologies cannot comprehensively assess the power battery's safety status based on the power battery's appearance and the vehicle's historical usage conditions. Summary of the invention

[0005] The present invention provides a method and system for unmanned vehicle power battery safety detection based on big data, which can solve the technical problem that related technologies cannot comprehensively evaluate the safety status of power batteries based on the appearance of the power batteries and the historical usage status of the vehicle.

[0006] According to a first aspect of the present invention, a method for detecting power battery safety of an unmanned vehicle based solely on big data is provided, comprising: Using an image acquisition device, an image of the battery appearance of the power battery is acquired; Determining an appearance safety inspection score of the power battery according to the battery appearance image; Acquire historical operation data of the unmanned vehicle in a historical operation cycle, wherein the historical operation data includes: historical operation environment data, historical operation mileage, total charging times and battery discharge depth; Determine the power battery aging influence coefficient based on the historical operation data; At multiple moments in the detection cycle, battery parameters of the power battery are obtained through the battery management system, wherein the battery parameters include: battery current, battery voltage and battery temperature; At multiple times during the detection cycle, the battery internal resistance of the power battery is obtained through the detection instrument; Determining a battery operation safety detection score according to the battery internal resistance, the battery parameters and the power battery aging influence coefficient; A power battery safety inspection report is generated according to the battery operation safety inspection score and the battery appearance safety inspection score.

[0007] According to a second aspect of the present invention, there is provided an unmanned vehicle power battery safety detection system based on big data, comprising: An image acquisition module, used to acquire a battery appearance image of a power battery through an image acquisition device; An appearance safety module, used to determine an appearance safety inspection score of the power battery according to the battery appearance image; A historical data module, used to obtain historical operation data of the unmanned vehicle in a historical operation cycle, wherein the historical operation data includes: historical operation environment data, historical operation mileage, total charging times and battery discharge depth; An aging impact module, used to determine an aging impact coefficient of a power battery according to the historical operation data; A battery parameter module, used to obtain battery parameters of the power battery through the battery management system at multiple times in the detection cycle, wherein the battery parameters include: battery current, battery voltage and battery temperature; The battery internal resistance module is used to obtain the battery internal resistance of the power battery through a detection instrument at multiple times in the detection cycle; An operation safety module, used to determine a battery operation safety detection score according to the battery internal resistance, the battery parameters and the power battery aging influence coefficient; The test report module is used to generate a power battery safety test report based on the battery operation safety test score and the battery appearance safety test score.

[0008] Technical effect: According to the present invention, the appearance safety status of the power battery can be evaluated according to the appearance image of the power battery, and the battery appearance safety detection score can be determined. The influence of the historical operation status of the unmanned vehicle on the aging degree of the power battery can be accurately analyzed, and the operation safety status of the power battery can be evaluated based on the influence and the battery internal resistance, battery current, battery voltage and battery temperature of the power battery in the detection cycle, and the battery operation safety detection score can be determined. Further, according to the battery operation safety detection score and the battery appearance safety detection score, the power battery safety can be comprehensively evaluated. When determining the battery appearance safety detection score, the artificial intelligence model can be used to detect multiple elements in the battery appearance image, so as to evaluate the appearance safety status of the power battery from multiple aspects, thereby improving the accuracy and objectivity of the appearance safety detection score. When determining the power battery aging influence coefficient, the power battery aging influence coefficient can be determined according to the historical operation humidity function, the historical operation temperature function, the historical operation mileage, the total number of charging times and the battery discharge depth. During the calculation process, the influence of the historical operation status of the unmanned vehicle on the aging of the power battery can be evaluated according to the operating environment, discharge depth, total number of charging times and historical operation mileage of the unmanned vehicle, thereby improving the comprehensiveness and accuracy of the power battery aging influence coefficient. When determining the battery operation safety detection score, the battery operation safety detection score can be determined based on the similarity change rate, battery internal resistance, first standard deviation, battery cell temperature and power battery aging influence coefficient. During the calculation process, the operation safety status of the power battery under high and low temperature conditions can be accurately analyzed. Furthermore, the safety performance of the power battery is evaluated from three aspects: the temperature distribution balance status of each battery cell, the battery internal resistance safety status and the battery operation temperature status, thereby improving the comprehensiveness and objectivity of the battery operation safety detection score.

[0009] It should be understood that the above general description and the following detailed description are exemplary and explanatory only and do not limit the present invention. Other features and aspects of the present invention will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other embodiments can be obtained based on these drawings without creative work. Figure 1A schematic diagram of a process flow of a method for safety detection of power batteries of unmanned vehicles based on big data according to an embodiment of the present invention is exemplarily shown; Figure 2 A schematic diagram of an unmanned vehicle power battery safety detection system based on big data according to an embodiment of the present invention is exemplarily shown. DETAILED DESCRIPTION

[0011] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0012] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0013] Figure 1 A schematic diagram of a process flow of a method for safety detection of power batteries of unmanned vehicles based on big data according to an embodiment of the present invention is exemplarily shown, and the method comprises: Step S101, capturing a battery appearance image of a power battery by using an image acquisition device; Step S102, determining an appearance safety inspection score of the power battery according to the battery appearance image; Step S103, obtaining historical operation data of the unmanned vehicle in a historical operation cycle, wherein the historical operation data includes: historical operation environment data, historical operation mileage, total charging times and battery discharge depth; Step S104, determining a power battery aging influence coefficient according to the historical operation data; Step S105, obtaining battery parameters of the power battery through the battery management system at multiple moments in the detection cycle, wherein the battery parameters include: battery current, battery voltage and battery temperature; Step S106, obtaining the battery internal resistance of the power battery through a detection instrument at multiple moments in the detection cycle; Step S107, determining a battery operation safety detection score according to the battery internal resistance, the battery parameters and the power battery aging influence coefficient; Step S108, generating a power battery safety inspection report according to the battery operation safety inspection score and the battery appearance safety inspection score.

[0014] According to the unmanned vehicle power battery safety detection method based on big data of an embodiment of the present invention, the appearance safety status of the power battery can be evaluated according to the appearance image of the power battery, and the battery appearance safety detection score can be determined. The influence of the historical operating conditions of the unmanned vehicle on the aging degree of the power battery can be accurately analyzed, and the operating safety status of the power battery can be evaluated based on the influence and the battery internal resistance, battery current, battery voltage and battery temperature of the power battery during the detection cycle, and the battery operating safety detection score can be determined. Furthermore, according to the battery operating safety detection score and the battery appearance safety detection score, the power battery safety can be comprehensively evaluated.

[0015] According to an embodiment of the present invention, in step S101, an image acquisition device is used to acquire a battery appearance image of a power battery.

[0016] For example, a camera is used to collect appearance images of a power battery from various angles.

[0017] According to an embodiment of the present invention, in step S102, the appearance safety inspection score of the power battery is determined according to the battery appearance image.

[0018] According to one embodiment of the present invention, step S102 includes: Determine the appearance safety test score of the power battery according to the battery appearance image, including: In the battery appearance image, identifying whether there are cracks in the outer shell of the power battery through an image detection model, and determining a crack identification result; In the battery appearance image, identifying whether there is a dent on the outer shell of the power battery through an image detection model, and determining a dent recognition result; In the battery appearance image, identifying whether there is corrosion on the outer shell of the power battery through the image detection model, and determining a corrosion identification result; In the battery appearance image, identifying whether a cable of the power battery is damaged by using an image detection model, and determining a damage identification result; In the battery appearance image, identifying whether a battery connector of the power battery is loose by using an image detection model, and determining a loose identification result; An appearance safety inspection score of the power battery is determined according to the crack identification result, the dent identification result, the corrosion identification result, the damage identification result and the looseness identification result.

[0019] For example, the image detection model is a type of deep learning model. The image detection model is trained through historical data so that the image detection model can identify whether there are various defects in the appearance and connection of the power battery. The image detection model is used to identify the shell of the power battery. If there is a crack in the shell, the crack recognition result is 0, and if there is no crack in the shell, the crack recognition result is 1; if there is a dent in the shell, the dent recognition result is 0, and if there is no dent in the shell, the dent recognition result is 1; if there is corrosion on the shell, the corrosion recognition result is 0, and if there is no corrosion on the shell, the corrosion recognition result is 1; if the power battery cable is damaged, the damage recognition result is 0, and if the power battery cable is not damaged, the damage recognition result is 1; if the battery connector of the power battery is loose, the loose recognition result is 0, and if the battery connector of the power battery is not loose, the loose recognition result is 1; based on the crack recognition results, dent recognition results, corrosion recognition results, damage recognition results and loose recognition results, the appearance safety status of the power battery is evaluated to determine the appearance safety test score of the power battery.

[0020] According to an embodiment of the present invention, determining the appearance safety inspection score of the power battery according to the crack identification result, the dent identification result, the corrosion identification result, the damage identification result and the looseness identification result includes: determining the appearance safety inspection score of the power battery according to formula (1): , (1) in, is the crack identification result, is the result of concave recognition, is the corrosion identification result, The damage identification result is To loosen the recognition result, , , , , .

[0021] According to one embodiment of the present invention, This is the crack identification result. If there are cracks in the battery shell, it means there is a safety hazard. The value is 0, otherwise The value of is 1; It is a dent identification structure. If there is a dent on the battery shell, it means there is a safety hazard. The value is 0, otherwise The value of is 1; This is the corrosion identification result. If there is corrosion on the battery shell, it means there is a safety hazard. The value is 0, otherwise The value of is 1; This is the damage identification result. If the power battery cable is damaged, it means there is a safety hazard. The value is 0, otherwise The value of is 1; For loose identification results, if the battery connector of the power battery is loose, it means there is a safety hazard. The value is 0, otherwise The value is 1; the crack identification result, dent identification result, corrosion identification result, damage identification result and damage identification result are multiplied to obtain the appearance safety inspection score of the power battery ; A value of 1 indicates that the appearance of the power battery is relatively complete, and the battery connector and cable are firm, not loose or damaged, and the appearance safety of the battery is relatively high; A value of 0 indicates that the power battery has abnormal appearance, such as cracks, dents and corrosion, or the battery connectors and cables are damaged and loose, and the battery's appearance safety is poor.

[0022] In this way, the artificial intelligence model can be used to detect multiple elements in the battery appearance image, thereby evaluating the appearance safety status of the power battery from multiple aspects, improving the accuracy and objectivity of the appearance safety inspection score.

[0023] According to one embodiment of the present invention, in step S103, historical operation data of the unmanned vehicle in a historical operation cycle is obtained, wherein the historical operation data includes: historical operation environment data, historical operation mileage, total charging times and battery discharge depth.

[0024] For example, during the operation of an unmanned vehicle, a large amount of historical operation data will be accumulated, including the total number of battery charging times (the total number of times the vehicle is charged in multiple historical operation cycles), the battery discharge depth (the percentage of the battery discharged relative to the total battery capacity), the historical operating mileage of the unmanned vehicle, and the road conditions and environmental data during the operation of the unmanned vehicle, namely, historical environmental data. Among them, the battery discharge depth indicates the discharge depth of the unmanned vehicle in a historical operation cycle.

[0025] According to an embodiment of the present invention, in step S104, the power battery aging influence coefficient is determined based on the historical operation data.

[0026] According to one embodiment of the present invention, step S104 includes: Determining a historical operating temperature and a historical operating humidity according to the historical operating environment data; Fitting the historical operating temperature and the time in the historical operating cycle to obtain a historical operating temperature function in the historical operating cycle; Fitting the historical operating humidity and the time in the historical operating cycle to obtain a historical operating humidity function in the historical operating cycle; The power battery aging influence coefficient is determined according to the historical operating humidity function, the historical operating temperature function, the historical operating mileage, the total number of charging times and the battery discharge depth.

[0027] For example, historical operating temperatures and moments in corresponding historical operating cycles are fitted to obtain historical operating temperature functions of historical operating temperatures in each historical operating cycle; historical operating humidity and moments in corresponding historical operating cycles are fitted to obtain historical operating humidity functions of historical operating humidity in each historical operating cycle; based on the historical operating humidity function, the historical operating temperature function, the historical operating mileage of the unmanned vehicle, the number of times the power battery is charged, and the depth of discharge of the power battery, the impact of the use of the unmanned vehicle on the aging of the power battery is evaluated to determine the power battery aging impact coefficient.

[0028] According to one embodiment of the present invention, the power battery aging influence coefficient is determined according to the historical operating humidity function, the historical operating temperature function, the historical operating mileage, the total number of charging times and the battery discharge depth, including: determining the power battery aging influence coefficient according to formula (2): , (2) in, , , , and is the preset weight, is the starting time of the historical operation cycle, is the nth moment of the historical operation cycle, is the preset temperature threshold, To preset the humidity threshold, is the historical operating temperature function of the kth historical operating cycle, is the historical operating humidity function of the kth historical operating cycle, The total number of charging times for unmanned vehicles, is the preset charging times threshold, is the battery discharge depth of the kth historical operation cycle, is the preset discharge depth threshold, is the historical mileage of the unmanned vehicle, is the preset running mileage threshold, K is the number of historical running cycles, k≤K, and both k and K are positive integers.

[0029] According to one embodiment of the present invention, It is the relative difference between the historical operating temperature at time t of the kth historical operating cycle and the preset temperature threshold. The larger the ratio is, the greater the difference between the historical operating temperature at time t of the kth historical operating cycle and the preset temperature threshold is. The historical operating temperature at time t of the kth historical operating cycle has a greater impact on the aging of the power battery. When the historical operating temperature is too high, the negative electrode of the battery will reduce the electrolyte, resulting in the loss of active lithium ions and accelerating the aging of the battery. When the historical operating temperature is too low, the activity of the active material of the battery is reduced, resulting in a reduction in the available capacity of the battery, which accelerates the aging of the battery. is the number of Integrate to show the influence of the operating temperature of the kth historical operating cycle on the aging of the power battery. It is the relative difference between the historical operating humidity at time t of the kth historical operating cycle and the preset humidity threshold. The larger the ratio is, the greater the historical operating humidity at time t of the kth historical operating cycle is relative to the preset humidity threshold. Excessive humidity will accelerate the chemical reaction inside the battery, leading to the aging of the electrode material and the decomposition of the electrolyte, and accelerating the aging of the battery. The historical operating humidity at time t of the kth historical operating cycle has a greater impact on the aging of the power battery. is the number of Integrate to show the influence of the operating humidity on the aging of the power battery in the kth historical operating cycle. Indicates the impact of the operating environment of unmanned vehicles in K historical cycles on the aging of power batteries, It is the relative difference between the battery discharge depth of the kth historical operation cycle and the preset discharge depth threshold. The larger the ratio is, the greater the discharge depth of the kth historical operation cycle is relative to the preset discharge depth threshold. During the deep discharge process, the chemical reaction inside the battery is more intense, causing greater damage to the battery structure and accelerating battery aging. The discharge depth of the power battery in the kth historical operation cycle has a greater impact on the aging of the power battery. Indicates the impact of the discharge depth of unmanned vehicles in K historical cycles on the aging of power batteries, is the relative difference between the total number of charging times of the unmanned vehicle and the preset number of charging times. The larger the ratio is, the more the total number of charging times of the unmanned vehicle is relative to the preset number of charging times. Frequent charging will accelerate the aging process of the battery and shorten its overall service life. The total number of charging times of the unmanned vehicle in K historical cycles has a greater impact on the aging of the power battery. is the relative difference between the historical mileage of the unmanned vehicle and the preset mileage. The larger the ratio is, the greater the historical mileage of the unmanned vehicle is relative to the preset mileage. The historical mileage of the unmanned vehicle in K historical cycles has a greater impact on the aging of the power battery. It means that the power battery aging influence coefficient is determined according to the operating environment, discharge depth, total charging times and historical operating mileage of the unmanned vehicle in K historical cycles.

[0030] In this way, the power battery aging impact coefficient can be determined based on the historical operating temperature function, historical operating mileage, total charging times and battery discharge depth. During the calculation process, the impact of the unmanned vehicle's historical operating conditions on the aging of the power battery can be evaluated based on the unmanned vehicle's operating environment, discharge depth, total charging times and historical operating mileage, thereby improving the comprehensiveness and accuracy of the power battery aging impact coefficient.

[0031] According to an embodiment of the present invention, in step S105, at multiple moments in the detection cycle, battery parameters of the power battery are acquired through a battery management system, wherein the battery parameters include: battery current, battery voltage and battery temperature.

[0032] For example, during a detection cycle, a battery management system (BMS) may be used to obtain a battery current, a battery voltage, and a battery temperature of the battery, wherein the battery temperature represents the overall temperature of the power battery.

[0033] According to an embodiment of the present invention, in step S106, the battery internal resistance of the power battery is obtained by a detection instrument at multiple moments in the detection cycle.

[0034] For example, the battery dynamic testing function of professional new energy equipment (such as 909CEV) can be used to accurately test the internal resistance of power batteries.

[0035] According to an embodiment of the present invention, in step S107, a battery operation safety detection score is determined based on the battery internal resistance, the battery parameters and the power battery aging influence coefficient.

[0036] According to one embodiment of the present invention, step S107 includes: Determining the battery cell temperature of each battery cell of the power battery according to the battery temperature; Determining a first standard deviation of the battery cell temperature according to the battery cell temperature of each battery cell; Determining a real-time battery state vector according to the battery current, the battery voltage and the battery temperature; Obtaining normal battery current, normal battery voltage and normal battery temperature under normal battery operation; Determine a normal battery state vector according to the normal battery current, the normal battery voltage and the normal battery temperature; A battery operation safety detection score is determined according to the battery cell temperature, the battery internal resistance, the real-time battery state vector, the normal battery state vector, the first standard deviation, the battery parameters and the power battery aging influence coefficient.

[0037] For example, a power battery is composed of multiple battery cells. The temperature of each battery cell of the power battery is determined through the temperature acquisition system in the BMS. The first standard deviation of the battery temperature at the jth moment of the detection cycle is determined based on the battery temperature of each battery cell at the jth moment of the detection cycle. The real-time battery state vector is combined according to the battery current, battery voltage and battery temperature to represent the battery state of the power battery during the detection cycle. The normal battery current, normal battery voltage and normal battery temperature under normal battery operation are combined to form a normal battery state vector to represent the normal battery operation state. The safety status of the battery during the detection cycle is evaluated based on the battery internal resistance, the real-time battery state vector, the normal battery state, the first standard deviation, the battery temperature and the power battery aging influence coefficient to determine the battery operation safety detection score.

[0038] According to an embodiment of the present invention, determining a battery operation safety detection score according to the battery cell temperature, the battery internal resistance, the real-time battery state vector, the normal battery state vector, the first standard deviation, the battery parameter and the power battery aging influence coefficient includes: Determining battery state similarity according to the real-time battery state vector and the normal battery state vector; Fitting the battery state similarity and the time in the detection cycle to obtain a similarity function of the battery state similarity in the detection cycle; According to the similarity function, obtaining a similarity derivative function; Determine the similarity change rate at multiple moments in the current detection cycle according to the similarity derivative function; A battery operation safety detection score is determined according to the similarity change rate, the battery internal resistance, the first standard deviation, the battery cell temperature and the power battery aging influence coefficient.

[0039] For example, a cosine similarity operation is performed based on the real-time battery state vector and the normal battery state vector to determine the battery state similarity. The greater the battery state similarity, the closer the battery temperature, battery voltage and battery current of the power battery in the detection cycle are to the normal battery current, normal battery voltage and normal battery temperature under normal operating conditions. The more normal the operating condition of the power battery in the detection cycle is, the higher the safety of the power battery is. The battery state similarity and the moment in the detection cycle are fitted to obtain a similarity function for describing the law of battery state similarity change in the detection cycle. The similarity function is derived to obtain a similarity derivative function. The moment in the detection cycle is substituted into the similarity derivative function to determine the similarity change rate of multiple moments in the current detection cycle. According to the similarity change rate, battery internal resistance, first standard deviation, cell temperature and power battery aging influence coefficient, the operating safety status of the power battery in the detection cycle is evaluated to determine the battery operation safety detection score.

[0040] According to an embodiment of the present invention, determining a battery operation safety detection score according to the similarity change rate, the battery internal resistance, the first standard deviation, the battery cell temperature and the power battery aging influence coefficient includes: determining the battery operation safety detection score according to formula (3): , (3) in, , and is the preset weight, is the preset multiple, if is the conditional function, is the jth moment of the detection cycle, is the similarity change rate at the jth moment of the detection period, is the first preset similarity change rate threshold, is the second preset similarity change rate threshold, is the battery internal resistance at the rth moment of the detection cycle, is the battery internal resistance at the mth moment of the detection cycle, To preset the battery internal resistance threshold, is the power battery aging influence coefficient, is the cell temperature of the e-th cell at the r-th moment of the detection cycle, is the first standard deviation of the cell temperature at the rth moment of the detection cycle, is the cell temperature of the e-th cell at the m-th moment of the detection cycle, is the first standard deviation of the cell temperature at the mth moment of the detection cycle, E is the number of cells of the power battery, e≤E, m is the number of moments in the detection cycle, r is the first preset moment, s is the second preset moment, r<s<m, e, E, r, s and m are all positive integers.

[0041] According to one embodiment of the present invention, during the 1 to r moments in the detection cycle, the experimental environment temperature in the experimental space rises uniformly, and the experimental environment temperature at the r-th moment in the detection cycle is the maximum value of the experimental environment temperature in the detection cycle (e.g., the experimental environment temperature at the r-th moment in the detection cycle is 50 degrees Celsius), which is used to simulate the operating safety status of the detection battery at high temperature. During the r to m moments in the detection cycle, the experimental environment temperature in the experimental space decreases uniformly, and the experimental environment temperatures at the s-th moment and the 1st moment in the detection cycle are normal room temperature (e.g., the experimental environment temperatures at the s-th moment and the 1st moment in the detection cycle are 20 degrees Celsius), and the experimental environment temperature at the m-th moment in the detection cycle is the minimum value of the experimental environment temperature in the detection cycle (e.g., the experimental environment temperature at the m-th moment in the detection cycle is minus 20 degrees Celsius), r<s<m, which is used to simulate the operating safety status of the detection battery at low temperature.

[0042] According to one embodiment of the present invention, in formula (3), the conditional function The value of includes the following two cases, when satisfying When the condition is met, it means that the cell temperature of the e-th cell at the r-th moment of the detection cycle is within an interval with the average cell temperature as the center and the standard deviation of twice the preset multiple as the interval length. The value of the condition function is 1. When it is not met When the condition is met, the value of the condition function is 0. If the cell temperature of the e-th cell at the r-th moment of the detection cycle meets the above conditions, it means that the deviation between the cell temperature of the e-th cell at the r-th moment of the detection cycle and the mean value is small, and the possibility of abnormality of the cell temperature of the cell is small. Otherwise, it can be considered that the possibility of abnormality of the cell temperature of the cell is large. It indicates the ratio of the number of cells with normal cell temperature to the total number of cells. The larger the ratio is, the more balanced the temperature distribution of each battery of the power battery is under high temperature conditions, and the better the safety condition of the power battery under high temperature conditions.

[0043] According to one embodiment of the present invention, in formula (3), the conditional function The value of includes the following two cases, when satisfying When the condition is met, it means that the cell temperature of the e-th cell at the m-th moment of the detection cycle is within an interval with the average cell temperature as the center and the standard deviation of twice the preset multiple as the interval length. The value of the condition function is 1. When it is not met When the condition is met, the value of the condition function is 0. If the cell temperature of the e-th cell at the m-th moment of the detection cycle meets the above conditions, it means that the deviation between the cell temperature of the e-th cell at the m-th moment of the detection cycle and the mean value is small, and the possibility of abnormal cell temperature of the cell is small. Otherwise, it can be considered that the possibility of abnormal cell temperature of the cell is large. It indicates the ratio of the number of cells with normal cell temperature to the total number of cells. The larger the ratio is, the more balanced the temperature distribution of each battery of the power battery is under low temperature conditions, and the better the safety condition of the power battery is under low temperature conditions.

[0044] According to one embodiment of the present invention, It indicates the temperature distribution safety condition of the power battery cells under extreme environmental conditions. The larger the value is, the better the temperature distribution safety condition of the power battery cells under extreme environmental conditions.

[0045] According to one embodiment of the present invention, as the battery ages, its internal structure and chemical composition change, which results in an increase in the internal resistance of the battery. It is the product of the preset battery internal resistance threshold and the power battery aging influence coefficient, which represents the battery internal resistance threshold after considering the battery aging influence factor. It is the relative difference between the battery internal resistance at the rth moment of the detection cycle and the battery internal resistance threshold after considering the battery aging factors. The larger the ratio is, the larger the battery internal resistance at the rth moment of the detection cycle is relative to the battery internal resistance threshold after considering the battery aging factors. This means that the battery internal resistance of the power battery is larger under high temperature conditions, causing a greater degradation in battery performance and a greater possibility of explosion risk. The battery internal resistance safety of the power battery under high temperature conditions is poor. It is the relative difference between the battery internal resistance at the mth moment of the detection cycle and the battery internal resistance threshold after considering the battery aging factors. The larger the ratio is, the greater the battery internal resistance at the mth moment of the detection cycle is relative to the battery internal resistance threshold after considering the battery aging factors. This means that the battery internal resistance of the power battery is large under low temperature conditions, resulting in a large degradation in battery performance and a high possibility of explosion risk. The battery internal resistance safety of the power battery under low temperature conditions is poor. It indicates the safety status of the battery's internal resistance under extreme temperature conditions. The smaller the value is, the better the safety status of the battery's internal resistance under extreme temperature conditions.

[0046] According to one embodiment of the present invention, is the average value of the similarity change rate at the first r moments of the detection cycle, indicating the change of the operating state of the power battery under high temperature conditions. The smaller the average value, the less the operating state of the power battery is affected by high temperature, and the better the safety of the power battery. is the relative difference between the first preset similarity change rate threshold and the average value of the similarity change rate at the first r moments of the detection period. The larger the ratio is, the smaller the average value of the similarity change rate at the first r moments of the detection period is relative to the first preset similarity change rate threshold, the less the power battery operation is affected by high temperature, the higher the operation stability of the power battery under high temperature conditions, and the better the safety of the power battery. is the relative difference between the second preset similarity change rate threshold and the average value of the similarity change rate from the sth moment to the mth moment of the detection period. The larger the ratio is, the smaller the average value of the similarity change rate from the sth moment to the mth moment of the detection period is relative to the second preset similarity change rate threshold, the less the power battery operation status is affected by low temperature, the better the operation stability of the power battery in a low temperature environment, and the better the safety status of the power battery. It indicates the operating stability of the power battery under extreme environmental conditions. The larger the ratio is, the more stable the power battery is under extreme environmental conditions and the better the safety of the power battery is.

[0047] According to one embodiment of the present invention, It means that the battery operation safety test score is determined based on three aspects: the temperature distribution balance of each battery cell, the battery internal resistance safety condition and the battery operation temperature condition.

[0048] In this way, the battery operation safety detection score can be determined based on the similarity change rate, battery internal resistance, first standard deviation, battery cell temperature and power battery aging influence coefficient. During the calculation process, the operation safety status of the power battery under high and low temperature conditions can be accurately analyzed. Furthermore, the safety performance of the power battery is evaluated from three aspects: the temperature distribution balance status of each battery cell, the battery internal resistance safety status and the battery operation temperature status, thereby improving the comprehensiveness and objectivity of the battery operation safety detection score.

[0049] According to an embodiment of the present invention, in step S108, a power battery safety inspection report is generated according to the battery operation safety inspection score and the battery appearance safety inspection score.

[0050] For example, if the battery appearance safety detection score is less than a preset battery appearance safety detection score threshold, a battery appearance safety alarm message is generated; if the battery operation safety detection score is less than a preset battery operation safety detection score threshold, a battery operation safety alarm message is generated.

[0051] According to the unmanned vehicle power battery safety detection method based on big data of the embodiment of the present invention, the appearance safety status of the power battery can be evaluated based on the appearance image of the power battery, and the battery appearance safety detection score can be determined. The impact of the historical operating conditions of the unmanned vehicle on the aging degree of the power battery can be accurately analyzed, and based on the impact and the battery internal resistance, battery current, battery voltage and battery temperature of the power battery in the detection cycle, the operating safety status of the power battery is evaluated to determine the battery operation safety detection score. Further, based on the battery operation safety detection score and the battery appearance safety detection score, the power battery safety is comprehensively evaluated. When determining the battery appearance safety detection score, the artificial intelligence model can be used to detect multiple elements in the battery appearance image, so as to evaluate the appearance safety status of the power battery from multiple aspects, thereby improving the accuracy and objectivity of the appearance safety detection score. When determining the power battery aging influence coefficient, the power battery aging influence coefficient can be determined based on the historical operating humidity function, historical operating temperature function, historical operating mileage, total charging times and battery discharge depth. During the calculation process, the historical operating conditions of the unmanned vehicle can be evaluated for the aging influence of the power battery based on the operating environment, discharge depth, total charging times and historical operating mileage of the unmanned vehicle, thereby improving the comprehensiveness and accuracy of the power battery aging influence coefficient. When determining the battery operation safety detection score, the battery operation safety detection score can be determined based on the similarity change rate, battery internal resistance, first standard deviation, battery cell temperature and power battery aging influence coefficient. During the calculation process, the operation safety status of the power battery under high and low temperature conditions can be accurately analyzed. Furthermore, the safety performance of the power battery can be evaluated from three aspects: the temperature distribution balance status of each battery cell, the battery internal resistance safety status and the battery operation temperature status, thereby improving the comprehensiveness and objectivity of the battery operation safety detection score.

[0052] Figure 2 A schematic diagram of an unmanned vehicle power battery safety detection system based on big data according to an embodiment of the present invention is exemplarily shown, the system comprising: An image acquisition module, used to acquire a battery appearance image of a power battery through an image acquisition device; An appearance safety module, used to determine an appearance safety inspection score of the power battery according to the battery appearance image; A historical data module, used to obtain historical operation data of the unmanned vehicle in a historical operation cycle, wherein the historical operation data includes: historical operation environment data, historical operation mileage, total charging times and battery discharge depth; An aging impact module, used to determine an aging impact coefficient of a power battery according to the historical operation data; A battery parameter module, used to obtain battery parameters of the power battery through the battery management system at multiple times in the detection cycle, wherein the battery parameters include: battery current, battery voltage and battery temperature; The battery internal resistance module is used to obtain the battery internal resistance of the power battery through a detection instrument at multiple times in the detection cycle; An operation safety module, used to determine a battery operation safety detection score according to the battery internal resistance, the battery parameters and the power battery aging influence coefficient; The test report module is used to generate a power battery safety test report based on the battery operation safety test score and the battery appearance safety test score.

[0053] It should be understood by those skilled in the art that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may be deformed or modified in any way without departing from the principles.

Claims

1. A method for safety detection of power batteries for unmanned vehicles based on big data, characterized in that: include: Using an image acquisition device, an image of the battery appearance of the power battery is acquired; Determining an appearance safety inspection score of the power battery according to the battery appearance image; Acquire historical operation data of the unmanned vehicle in a historical operation cycle, wherein the historical operation data includes: historical operation environment data, historical operation mileage, total charging times and battery discharge depth; Determine the power battery aging influence coefficient based on the historical operation data; At multiple moments in the detection cycle, battery parameters of the power battery are obtained through the battery management system, wherein the battery parameters include: battery current, battery voltage and battery temperature; At multiple times during the detection cycle, the battery internal resistance of the power battery is obtained through the detection instrument; Determining a battery operation safety detection score according to the battery internal resistance, the battery parameters and the power battery aging influence coefficient; A power battery safety inspection report is generated according to the battery operation safety inspection score and the battery appearance safety inspection score.

2. The unmanned vehicle power battery safety detection method based on big data according to claim 1 is characterized in that: Determine the appearance safety test score of the power battery according to the battery appearance image, including: In the battery appearance image, identifying whether there are cracks in the outer shell of the power battery through an image detection model, and determining a crack identification result; In the battery appearance image, identifying whether there is a dent on the outer shell of the power battery through an image detection model, and determining a dent recognition result; In the battery appearance image, identifying whether there is corrosion on the outer shell of the power battery through the image detection model, and determining a corrosion identification result; In the battery appearance image, identifying whether a cable of the power battery is damaged by using an image detection model, and determining a damage identification result; In the battery appearance image, identifying whether a battery connector of the power battery is loose by using an image detection model, and determining a loose identification result; An appearance safety inspection score of the power battery is determined according to the crack identification result, the dent identification result, the corrosion identification result, the damage identification result and the looseness identification result.

3. The unmanned vehicle power battery safety detection method based on big data according to claim 2 is characterized in that: Determining the appearance safety inspection score of the power battery according to the crack identification result, the dent identification result, the corrosion identification result, the damage identification result and the looseness identification result, including: According to the formula Determine the appearance safety test score of the power battery ,in, is the crack identification result, is the result of concave recognition, is the corrosion identification result, The damage identification result is To loosen the recognition result, , , , , .

4. The unmanned vehicle power battery safety detection method based on big data according to claim 1 is characterized in that: According to the historical operation data, the power battery aging influence coefficient is determined, including: Determining a historical operating temperature and a historical operating humidity according to the historical operating environment data; Fitting the historical operating temperature and the time in the historical operating cycle to obtain a historical operating temperature function in the historical operating cycle; Fitting the historical operating humidity and the time in the historical operating cycle to obtain a historical operating humidity function in the historical operating cycle; The power battery aging influence coefficient is determined according to the historical operating humidity function, the historical operating temperature function, the historical operating mileage, the total number of charging times and the battery discharge depth.

5. The unmanned vehicle power battery safety detection method based on big data according to claim 4 is characterized in that: Determining a power battery aging influence coefficient according to the historical operating humidity function, the historical operating temperature function, the historical operating mileage, the total number of charging times and the battery discharge depth includes: According to the formula Determine the power battery aging influence coefficient ,in, , , , and is the preset weight, is the starting time of the historical operation cycle, is the nth moment of the historical operation cycle, is the preset temperature threshold, To preset the humidity threshold, is the historical operating temperature function of the kth historical operating cycle, is the historical operating humidity function of the kth historical operating cycle, The total number of charging times for unmanned vehicles, is the preset charging times threshold, is the battery discharge depth of the kth historical operation cycle, is the preset discharge depth threshold, is the historical mileage of the unmanned vehicle, is the preset running mileage threshold, K is the number of historical running cycles, k≤K, and both k and K are positive integers.

6. The unmanned vehicle power battery safety detection method based on big data according to claim 1 is characterized in that: Determining a battery operation safety detection score according to the battery internal resistance, the battery parameters and the power battery aging influence coefficient includes: Determining the battery cell temperature of each battery cell of the power battery according to the battery temperature; Determining a first standard deviation of the battery cell temperature according to the battery cell temperature of each battery cell; Determining a real-time battery state vector according to the battery current, the battery voltage and the battery temperature; Obtaining normal battery current, normal battery voltage and normal battery temperature under normal battery operation; Determine a normal battery state vector according to the normal battery current, the normal battery voltage and the normal battery temperature; A battery operation safety detection score is determined according to the battery cell temperature, the battery internal resistance, the real-time battery state vector, the normal battery state vector, the first standard deviation, the battery parameters and the power battery aging influence coefficient.

7. The unmanned vehicle power battery safety detection method based on big data according to claim 6 is characterized in that: Determining a battery operation safety detection score according to the battery cell temperature, the battery internal resistance, the real-time battery state vector, the normal battery state vector, the first standard deviation, the battery parameter, and the power battery aging influence coefficient includes: Determining battery state similarity according to the real-time battery state vector and the normal battery state vector; Fitting the battery state similarity and the time in the detection cycle to obtain a similarity function of the battery state similarity in the detection cycle; According to the similarity function, obtaining a similarity derivative function; Determine the similarity change rate at multiple moments in the current detection cycle according to the similarity derivative function; A battery operation safety detection score is determined according to the similarity change rate, the battery internal resistance, the first standard deviation, the battery cell temperature and the power battery aging influence coefficient.

8. The unmanned vehicle power battery safety detection method based on big data according to claim 7 is characterized in that: Determining a battery operation safety detection score according to the similarity change rate, the battery internal resistance, the first standard deviation, the battery cell temperature, and the power battery aging influence coefficient includes: According to the formula Determine the battery operation safety test score ,in, , and is the preset weight, is the preset multiple, if is the conditional function, is the jth moment of the detection cycle, is the similarity change rate at the jth moment of the detection period, is the first preset similarity change rate threshold, is a second preset similarity change rate threshold, is the battery internal resistance at the rth moment of the detection cycle, is the battery internal resistance at the mth moment of the detection cycle, To preset the battery internal resistance threshold, is the power battery aging influence coefficient, is the cell temperature of the e-th cell at the r-th moment of the detection cycle, is the first standard deviation of the cell temperature at the rth moment of the detection cycle, is the cell temperature of the e-th cell at the m-th moment of the detection cycle, is the first standard deviation of the cell temperature at the mth moment of the detection cycle, E is the number of cells of the power battery, e≤E, m is the number of moments in the detection cycle, r is the first preset moment, s is the second preset moment, r<s<m, e, E, r, s and m are all positive integers.

9. An unmanned vehicle power battery safety detection system based on big data, characterized in that: include: An image acquisition module, used to acquire a battery appearance image of a power battery through an image acquisition device; An appearance safety module, used to determine an appearance safety inspection score of the power battery according to the battery appearance image; A historical data module, used to obtain historical operation data of the unmanned vehicle in a historical operation cycle, wherein the historical operation data includes: historical operation environment data, historical operation mileage, total charging times and battery discharge depth; An aging impact module, used to determine an aging impact coefficient of a power battery according to the historical operation data; A battery parameter module, used to obtain battery parameters of the power battery through the battery management system at multiple times in the detection cycle, wherein the battery parameters include: battery current, battery voltage and battery temperature; The battery internal resistance module is used to obtain the battery internal resistance of the power battery through a detection instrument at multiple times in the detection cycle; An operation safety module, used to determine a battery operation safety detection score according to the battery internal resistance, the battery parameters and the power battery aging influence coefficient; The test report module is used to generate a power battery safety test report based on the battery operation safety test score and the battery appearance safety test score.

Images