Battery performance real-time evaluation method and evaluation device

Abstract

The invention provides a battery performance real-time evaluation method and evaluation device, and the method comprises the steps: converting a battery performance multi-index characteristic into a trapezoidal fuzzy number, forming a battery performance multi-index evaluation model of a battery performance index-trapezoidal fuzzy number, taking a battery performance index as the input, taking the trapezoidal fuzzy number as the output to train a neural network, and employing an MARCOS fuzzy algorithm to evaluate the performance of a battery. The method comprises the following steps: constructing a final utility function of multiple indexes of the battery performance of the electric vehicle, converting a trapezoidal fuzzy number output by a neural network into a one-dimensional comprehensive evaluation result of the battery performance indexes, and finally, analyzing the real-time data of the battery performance indexes through the method, so that the real-time evaluation of the battery performance can be realized in real time. Therefore, the multi-dimensional data of the battery performance indexes are fused to output a one-dimensional comprehensive evaluation result of the battery performance indexes, the problem of multi-index coupling evaluation of the battery performance is solved, real-time comprehensive evaluation of the battery performance is realized, and a theoretical basis and engineering guidance are provided for safe and reliable operation of the battery.

Description

Technical Field

[0001] The present invention relates to the technical field of battery management, and in particular to a method and a device for real-time evaluation of battery performance. Background Art

[0002] As electric vehicle production and sales increase, the number of electric vehicle fires caused by battery failures is increasing. Research has found that thermal runaway, a circuit failure during the battery charge and discharge process (such as an internal or external short circuit), is the primary cause of these fires. Therefore, monitoring battery failures during the charge and discharge process is essential.

[0003] At present, machine learning methods are generally used to analyze battery performance indicators such as current, voltage and power to predict the occurrence of faults. However, the warning triggering criteria are mainly based on the abnormality or exceeding of a single performance indicator, or the abnormality or exceeding of different indicators are evaluated separately. It is difficult to solve the problem of battery thermal failure caused by the coupling of multiple performance indicators, and it is impossible to reveal the coupling effect between multiple indicators. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a method for real-time evaluation of battery performance in a first aspect.

[0005] A second embodiment of the present invention provides a device for real-time evaluation of battery performance.

[0006] The technical solution adopted in the present invention is as follows:

[0007] A first embodiment of the present invention provides a real-time battery performance evaluation method, comprising the following steps: determining battery performance indicators of an electric vehicle, wherein the battery performance indicators include: battery voltage, current, temperature, humidity, usage time, and charge and discharge times; obtaining historical battery performance indicator data of the battery, wherein the historical data includes: each battery performance indicator data and the quality grade corresponding to the data; converting the quality grade into a trapezoidal fuzzy number to form a battery performance multi-indicator evaluation model of battery performance indicators-trapezoidal fuzzy numbers; using the battery performance multi-indicator evaluation model to train a neural network, wherein the input of the neural network is the battery performance indicator and the output is a trapezoidal fuzzy number; using the MARCOS (Measurement of Alternatives and Ranking Ordering according to Compromise Solution) fuzzy algorithm to construct a final utility function of the multiple indicators of the battery performance of the electric vehicle, and converting the trapezoidal fuzzy number output by the neural network into a one-dimensional comprehensive evaluation result of the battery performance indicators; collecting real-time data of the battery performance indicators and inputting it into the trained neural network, and calculating the comprehensive evaluation result of the battery performance indicators based on the output of the neural network and the final utility function, thereby realizing real-time battery performance evaluation.

[0008] The above-mentioned method for real-time battery performance evaluation of the present invention also has the following additional technical features:

[0009] According to an embodiment of the present invention, the quality grades include: very high, high, medium, low and very low.

[0010] According to one embodiment of the present invention, the neural network is a BAS-BP (Beetle Antennae Search-Back Propagation) neural network.

[0011] According to one embodiment of the present invention, the MARCOS fuzzy algorithm is used to construct the final utility function of multiple indicators of electric vehicle battery performance, specifically including: according to the battery performance indicator A i The trapezoidal fuzzy number x at time point j ij Establish the multi-index trapezoidal fuzzy number matrix X of battery performance m×n , where m is the number of battery performance indicators and n is the number of indicator test time points; obtain the battery performance multi-indicator trapezoidal fuzzy number matrix X m×n , the positive ideal solution TP at different time points j j and anti-ideal solution TQ j Trapezoidal fuzzy numbers; normalized trapezoidal fuzzy number matrix X m×n Get the first normalized matrix S, normalize the positive ideal solution TP at different time points jj The trapezoidal fuzzy number is obtained by the second normalized matrix S q , normalize the anti-ideal solution TQ at different time points j j The trapezoidal fuzzy number is obtained by the third normalized matrix S p ; According to S, S q and S p Calculate different indicators A i The positive utility K relative to the positive ideal solution + i and the anti-effect K relative to the anti-ideal solution - i According to the K + i and K - i Construct different indicators A i The final utility function f(K i ) and sort them.

[0012] According to one embodiment of the present invention, the following formula is used to calculate different indicators A: i The positive utility K relative to the positive ideal solution + i and the anti-effect K relative to the anti-ideal solution - i : Among them, S qi and S pi Indicator A i The normalized matrix of trapezoidal fuzzy numbers of positive ideal solutions and anti-ideal solutions, i=1,2,3…m, S i For indicator A i The weighted sum of the trapezoidal fuzzy number normalized matrix at different time points j, (a, b, c, d) is the matrix element, and R(a, b, c, d) is the defuzzification function.

[0013] A second embodiment of the present invention proposes a real-time battery performance evaluation device, comprising: a determination module, the determination module being used to determine the battery performance indicators of an electric vehicle, the battery performance indicators including: battery voltage, current, temperature, humidity, usage time, and charge and discharge times; an acquisition module, the acquisition module being used to acquire historical battery performance indicator data of the battery, the historical data including: each battery performance indicator data and the quality grade corresponding to the data; a conversion module, the conversion module being used to convert the quality grade into a trapezoidal fuzzy number to form a battery performance multi-indicator evaluation model of battery performance indicator-trapezoidal fuzzy number; a training module, the training module being used to train a neural network using the battery performance multi-indicator evaluation model, the input of the neural network being the battery performance indicator and the output being the trapezoidal fuzzy number; a construction module, the construction module being used to use the MARCOS fuzzy algorithm to construct a final utility function of the multiple indicators of the battery performance of the electric vehicle, and converting the trapezoidal fuzzy number output by the neural network into a one-dimensional comprehensive evaluation result of the battery performance indicator; a real-time evaluation module, the real-time evaluation module being used to collect real-time data of the battery performance indicator and input it into the trained neural network, and calculate the comprehensive evaluation result of the battery performance indicator based on the output of the neural network and the final utility function, thereby realizing real-time evaluation of the battery performance.

[0014] The above-mentioned battery performance real-time evaluation device of the present invention also has the following additional technical features:

[0015] According to an embodiment of the present invention, the quality grades include: very high, high, medium, low and very low.

[0016] According to one embodiment of the present invention, the neural network is a BAS-BP neural network.

[0017] According to one embodiment of the present invention, the building module is specifically used to: i The trapezoidal fuzzy number x at time point j ij Establish the multi-index trapezoidal fuzzy number matrix X of battery performance m×n , where m is the number of battery performance indicators and n is the number of indicator test time points; obtain the battery performance multi-indicator trapezoidal fuzzy number matrix X m×n , the positive ideal solution TP at different time points j j and anti-ideal solution TQ j Trapezoidal fuzzy numbers; normalized trapezoidal fuzzy number matrix X m×n Get the first normalized matrix S, normalize the positive ideal solution TP at different time points j j The trapezoidal fuzzy number is obtained by the second normalized matrix S q , normalize the anti-ideal solution TQ at different time points j j The trapezoidal fuzzy number is obtained by the third normalized matrix S p ; According to S, Sq and S p Calculate different indicators A i The positive utility K relative to the positive ideal solution + i and the anti-effect K relative to the anti-ideal solution - i According to the K + i and K - i Construct different indicators A i The final utility function f(K i ) and sort them.

[0018] According to one embodiment of the present invention, the construction module specifically uses the following formula to calculate different indicators A i The positive utility K relative to the positive ideal solution + i and the anti-effect K relative to the anti-ideal solution - i :

[0019]

[0020] Among them, S qi and S pi Indicator A i The normalized matrix of trapezoidal fuzzy numbers of positive ideal solutions and anti-ideal solutions, i=1,2,3…m, S i For indicator A i The weighted sum of the trapezoidal fuzzy number normalized matrix at different time points j, (a, b, c, d) is the matrix element, and R(a, b, c, d) is the defuzzification function.

[0021] Beneficial effects of the present invention:

[0022] The present invention fuses multi-dimensional data of battery performance indicators to output a one-dimensional comprehensive evaluation result of battery performance indicators, solving the problem of multi-indicator coupled evaluation of battery performance, revealing the coupling effect between multiple indicators, realizing real-time comprehensive evaluation of battery performance, improving the level of battery fault warning, and providing a theoretical basis and engineering guidance for safe and reliable operation of batteries.

[0023] The BAS-BP neural network can better learn the experience data and has high indicator evaluation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of a method for real-time evaluation of battery performance according to one embodiment of the present invention;

[0025] Figure 2is a schematic diagram showing the quality levels of voltage and current during a battery discharge process according to a specific example of the present invention;

[0026] Figure 3 FIG. 4 is a block diagram of a device for real-time evaluation of battery performance according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0028] Figure 1 FIG. 1 is a flow chart of a method for real-time evaluation of battery performance according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0029] S1, determine the battery performance indicators of the electric vehicle, which include: battery voltage, current, temperature, humidity, usage time and number of charge and discharge times.

[0030] Specifically, battery voltage, current, temperature, humidity, usage time, and charge and discharge times are important indicators for evaluating battery performance. Battery failure can cause abnormalities in one or more of the above indicators, and different abnormal states of indicators can reveal the cause of battery failure. Therefore, the present invention collects and analyzes the above indicators to achieve battery performance evaluation.

[0031] S2, obtaining battery performance index historical data of the battery, the historical data including: each battery performance index data and the quality grade corresponding to the data.

[0032] In one embodiment of the present invention, the quality grades include: very high, high, medium, low and very low.

[0033] Specifically, the quality grades corresponding to battery performance indicators can be labeled by authoritative experts, and then the K-means clustering method can be used to simulate expert labeling to obtain the quality grades of multiple battery performance indicators, including five grades: very high, high, medium, low and very low, forming rich sample data. For example, for the quality grades of voltage and current during battery discharge, please refer to Figure 2 shown.

[0034] S3, converts the quality grade into trapezoidal fuzzy number to form a battery performance multi-index evaluation model of battery performance index-trapezoidal fuzzy number.

[0035] As a specific example, according to the trapezoidal fuzzy number theory, the trapezoidal fuzzy number x = (a, b, c, d), where a, b, c, and d are elements in the matrix, can be used to establish corresponding trapezoidal fuzzy numbers for the quality grades corresponding to the battery performance indicators, as shown in Table 1:

[0036] Table 1

[0037]

[0038] S4, uses the battery performance multi-index evaluation model to train the neural network. The input of the neural network is the battery performance index and the output is the trapezoidal fuzzy number.

[0039] In a specific embodiment of the present invention, the neural network is a BAS-BP neural network.

[0040] Specifically, relevant verification tests have shown that the output results of the BAS-BP neural network are basically consistent with the evaluation results of experts in historical data, indicating that the BAS-BP neural network can better learn expert evaluation.

[0041] S5, using the MARCOS fuzzy algorithm, constructs the final utility function of multiple indicators of electric vehicle battery performance, and converts the trapezoidal fuzzy numbers output by the neural network into one-dimensional comprehensive evaluation results of battery performance indicators.

[0042] In a specific embodiment of the present invention, the MARCOS fuzzy algorithm is used to construct a final utility function of multiple indicators of electric vehicle battery performance, which specifically includes the following steps S51-S55:

[0043] S51, according to the battery performance index A i The trapezoidal fuzzy number x at time point j ij Establish the multi-index trapezoidal fuzzy number matrix X of battery performance m×n , where m is the number of battery performance indicators and n is the number of indicator test time points.

[0044] Specifically, there are six battery performance indicators, including real-time voltage data A1, real-time current data A2, real-time temperature data A3, real-time humidity data A4, real-time charge and discharge time A5, and real-time total battery usage time A6, where m = 6. Time node j can be divided into gradients according to needs.

[0045]

[0046] Among them, the battery performance multi-index trapezoidal fuzzy number matrix X m×n The element x ij A is the battery performance index i The trapezoidal fuzzy number at time point j, x ij =(a ij ,bij ,c ij ,d ij ), i=1,2,3…m, j=0,…n.

[0047] S52, obtain the battery performance multi-index trapezoidal fuzzy number matrix X m×n , the positive ideal solution TP at different time points j j and anti-ideal solution TQ j The trapezoidal fuzzy number of .

[0048] Among them, TP j =[x pj ] 1×n , TQ j =[x qj ] 1×n .

[0049]

[0050] Where B is the criterion related to the positive ideal solution, and C is the criterion related to the anti-ideal solution.

[0051] S53, normalized trapezoidal fuzzy number matrix X m×n Get the first normalized matrix S, normalize the positive ideal solution TP at different time points j j The trapezoidal fuzzy number is obtained by the second normalized matrix S q , normalize the anti-ideal solution TQ at different time points j j The trapezoidal fuzzy number is obtained by the third normalized matrix S p ;

[0052] Specifically, for X m×n TP j and TQ j As a specific example, the following formula can be used to normalize X m×n The normalized matrix can be expressed as S = [s ij ] m×n , where s ij for:

[0053]

[0054] Similarly, we can get the positive ideal solution TP at different time points j j The second normalized matrix S of the trapezoidal fuzzy number q , the anti-ideal solution TQ at different time points j j The third normalized matrix S of the trapezoidal fuzzy number p .

[0055] S54, according to S, S q and S p Calculate different indicators Ai The positive utility K relative to the positive ideal solution + i and the anti-effect K relative to the anti-ideal solution - i .

[0056] In one embodiment of the present invention, the following formula is used to calculate different indicators A: i The positive utility K relative to the positive ideal solution + i and the anti-effect K relative to the anti-ideal solution - i :

[0057]

[0058] Among them, S qi and S pi Indicator A i The normalized matrix of the trapezoidal fuzzy numbers of the positive ideal solution and the anti-ideal solution, i=1,2,3…m,j=1,…n,S i For indicator A i The weighted sum of the trapezoidal fuzzy number normalized matrix at different time points j, (a, b, c, d) is the matrix element, and R(a, b, c, d) is the defuzzification function.

[0059] S55, according to K + i and K - i Construct different indicators A i The final utility function f(K i ) and sort them.

[0060] In one embodiment of the present invention, the client calculates different indicators A using the following formula i The final utility function f(K i ):

[0061]

[0062] By substituting the multi-index trapezoidal fuzzy numbers of battery performance into the above S51-S55, the multi-performance indicators of the battery can be converted into a one-dimensional comprehensive evaluation result (numerical value) of the battery performance indicators, realizing the comprehensive evaluation of the multi-index of battery performance, and quantifying the coupling effect between the multiple indicators into one data, which is more intuitive.

[0063] S6, collects real-time data of battery performance indicators and inputs them into the trained neural network, calculates the comprehensive evaluation results of the battery performance indicators based on the output of the neural network and the final utility function, and realizes real-time evaluation of battery performance.

[0064] Specifically, in actual applications, real-time data of battery performance indicators are collected in real time and input into the trained neural network. Then, based on the output of the neural network, the final utility function is used to calculate the comprehensive evaluation results of the battery performance indicators to achieve real-time evaluation of battery performance.

[0065] In summary, the real-time battery performance evaluation method according to the embodiment of the present invention fuses the multi-dimensional data of battery performance indicators to output a one-dimensional comprehensive evaluation result of battery performance indicators, solves the problem of multi-indicator coupled evaluation of battery performance, reveals the coupling effect between multiple indicators, realizes real-time comprehensive evaluation of battery performance, improves the level of battery fault warning, and provides a theoretical basis and engineering guidance for the safe and reliable operation of batteries.

[0066] Corresponding to the above-mentioned method for real-time battery performance evaluation, the present invention also provides a device for real-time battery performance evaluation. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, any details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment and will not be further described in this invention.

[0067] Figure 3 FIG. 1 is a block diagram of a device for real-time evaluation of battery performance according to an embodiment of the present invention. Figure 3 As shown, the device includes: a determination module 1, an acquisition module 2, a conversion module 3, a training module 4, a construction module 5 and a real-time evaluation module 6.

[0068] Among them, the determination module 1 is used to determine the battery performance indicators of the electric vehicle, and the battery performance indicators include: battery voltage, current, temperature, humidity, usage time and number of charge and discharge times; the acquisition module 2 is used to obtain the battery performance indicator historical data of the battery, and the historical data includes: each battery performance indicator data and the quality grade corresponding to the data; the conversion module 3 is used to convert the quality grade into a trapezoidal fuzzy number to form a battery performance multi-indicator evaluation model of battery performance indicator-trapezoidal fuzzy number; the training module 4 is used to train the neural network using the battery performance multi-indicator evaluation model, the input of the neural network is the battery performance indicator, and the output is the trapezoidal fuzzy number; the construction module 5 is used to use the MARCOS fuzzy algorithm to construct the final utility function of the electric vehicle battery performance multi-indicator, and convert the trapezoidal fuzzy number output by the neural network into a one-dimensional battery performance indicator comprehensive evaluation result; the real-time evaluation module 6 is used to collect real-time data of the battery performance indicator and input it into the trained neural network, calculate the battery performance indicator comprehensive evaluation result according to the output of the neural network and the final utility function, and realize real-time evaluation of battery performance.

[0069] According to an embodiment of the present invention, the quality grades include: very high, high, medium, low and very low.

[0070] According to one embodiment of the present invention, the neural network is a BAS-BP neural network.

[0071] According to one embodiment of the present invention, the construction module 5 is specifically used to: i The trapezoidal fuzzy number x at time point j ij Establish the multi-index trapezoidal fuzzy number matrix X of battery performance m×n , where m is the number of battery performance indicators and n is the number of indicator test time points; obtain the battery performance multi-indicator trapezoidal fuzzy number matrix X m×n , the positive ideal solution TP at different time points j j and anti-ideal solution TQ j Trapezoidal fuzzy numbers; normalized trapezoidal fuzzy number matrix X m×n Get the first normalized matrix S, normalize the positive ideal solution TP at different time points j j The trapezoidal fuzzy number is obtained by the second normalized matrix S q , normalize the anti-ideal solution TQ at different time points j j The trapezoidal fuzzy number is obtained by the third normalized matrix S p ; According to S, S q and S p Calculate different indicators A i The positive utility K relative to the positive ideal solution + i and the anti-effect K relative to the anti-ideal solution - i According to K + i and K - i Construct different indicators A i The final utility function f(K i ) and sort them.

[0072] According to one embodiment of the present invention, the construction module 5 specifically uses the following formula to calculate different indicators A i The positive utility K relative to the positive ideal solution + i and the anti-effect K relative to the anti-ideal solution - i :

[0073]

[0074] Among them, S qi and S pi Indicator A i The normalized matrix of trapezoidal fuzzy numbers of positive ideal solutions and anti-ideal solutions, i=1,2,3…m, S i For indicator A iThe weighted sum of the trapezoidal fuzzy number normalized matrix at different time points j, (a, b, c, d) is the matrix element, and R(a, b, c, d) is the defuzzification function.

[0075] According to the real-time battery performance evaluation device of an embodiment of the present invention, the multi-dimensional data of battery performance indicators are integrated to output a one-dimensional comprehensive evaluation result of the battery performance indicators, thereby solving the problem of coupled evaluation of multiple indicators of battery performance, revealing the coupling effect between multiple indicators, realizing real-time comprehensive evaluation of battery performance, improving the level of battery fault warning, and providing a theoretical basis and engineering guidance for the safe and reliable operation of batteries.

[0076] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. "Multiple" means two or more, unless otherwise specifically defined.

[0077] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. Throughout this specification, the schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and integrate different embodiments or examples described in this specification, as well as features from different embodiments or examples, without conflicting requirements. Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. Throughout this specification, the schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and integrate different embodiments or examples and features of different embodiments or examples described in this specification without mutual contradiction.

[0078] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0079] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0080] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0081] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0082] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0083] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and are not to be construed as limiting the present invention. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

[0084] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for real-time evaluation of battery performance, characterized in that: The following steps are involved: Determine battery performance indicators of the electric vehicle, wherein the battery performance indicators include: battery voltage, current, temperature, humidity, usage time, and charge and discharge times; Acquire battery performance index historical data of the battery, wherein the historical data includes: each battery performance index data and the quality grade corresponding to the data; The quality grade is converted into trapezoidal fuzzy numbers to form a battery performance multi-index evaluation model of battery performance index-trapezoidal fuzzy number; A battery performance multi-index evaluation model is used to train a neural network, wherein the input of the neural network is the battery performance index and the output is a trapezoidal fuzzy number; The MARCOS fuzzy algorithm is used to construct the final utility function of multiple indicators of electric vehicle battery performance, and the trapezoidal fuzzy number output by the neural network is converted into a one-dimensional comprehensive evaluation result of battery performance indicators; The real-time data of battery performance indicators is collected and input into the trained neural network. The comprehensive evaluation results of battery performance indicators are calculated based on the output of the neural network and the final utility function to realize real-time evaluation of battery performance.

2. The method for real-time evaluation of battery performance according to claim 1, wherein: The quality levels include: very high, high, medium, low and very low.

3. The method for real-time battery performance evaluation according to claim 1, wherein: The neural network is a BAS-BP neural network.

4. The method for real-time evaluation of battery performance according to claim 1, wherein: The MARCOS fuzzy algorithm is used to construct the final utility function of multiple indicators of electric vehicle battery performance, including: According to the battery performance index A i The trapezoidal fuzzy number x at time point j ij Establish the multi-index trapezoidal fuzzy number matrix X of battery performance m×n , where m is the number of battery performance indicators and n is the number of indicator test time points; Get the battery performance multi-index trapezoidal fuzzy number matrix X m×n , the positive ideal solution TP at different time points j j and anti-ideal solution TQ j Trapezoidal fuzzy number of ; Normalized trapezoidal fuzzy number matrix X m×n Get the first normalized matrix S, normalize the positive ideal solution TP at different time points j j The trapezoidal fuzzy number is obtained by the second normalized matrix S q , normalize the anti-ideal solution TQ at different time points j j The trapezoidal fuzzy number is obtained by the third normalized matrix S p ; According to S, S q and S p Calculate different indicators A i The positive utility K relative to the positive ideal solution + i and the anti-effect K relative to the anti-ideal solution - i ; According to the K + i and K - i Construct different indicators A i The final utility function f(K i ) and sort them.

5. The method for real-time evaluation of battery performance according to claim 1, wherein: The following formula is used to calculate different indicators A i The positive utility K relative to the positive ideal solution + i and the anti-effect K relative to the anti-ideal solution - i : Among them, S qi and S pi Indicator A i The normalized matrix of the trapezoidal fuzzy numbers of the positive ideal solution and the anti-ideal solution, S i For indicator A i The weighted sum of the trapezoidal fuzzy number normalized matrix at different time points j, (a, b, c, d) is the matrix element, and R(a, b, c, d) is the defuzzification function.

6. A real-time battery performance evaluation device, characterized in that: include: A determination module, the determination module is used to determine the battery performance indicators of the electric vehicle, the battery performance indicators including: battery voltage, current, temperature, humidity, usage time and charge and discharge times; An acquisition module, the acquisition module is used to acquire battery performance index historical data of the battery, the historical data including: each battery performance index data and the quality grade corresponding to the data; A conversion module, wherein the conversion module is used to convert the quality grade into a trapezoidal fuzzy number to form a battery performance multi-index evaluation model of battery performance index-trapezoidal fuzzy number; A training module, the training module is used to train a neural network using a battery performance multi-index evaluation model, the input of the neural network is the battery performance index, and the output is a trapezoidal fuzzy number; A construction module, wherein the construction module is used to construct a final utility function of multiple indicators of electric vehicle battery performance using a MARCOS fuzzy algorithm, and convert the trapezoidal fuzzy number output by the neural network into a one-dimensional comprehensive evaluation result of the battery performance indicator; A real-time evaluation module is used to collect real-time data of battery performance indicators and input them into the trained neural network, calculate the comprehensive evaluation results of battery performance indicators based on the output of the neural network and the final utility function, and realize real-time evaluation of battery performance.

7. The battery performance real-time evaluation device according to claim 6, characterized in that: The quality levels include: very high, high, medium, low and very low.

8. The battery performance real-time evaluation device according to claim 6, characterized in that: The neural network is a BAS-BP neural network.

9. The battery performance real-time evaluation device according to claim 6, characterized in that: The building blocks are specifically used for: According to the battery performance index A i The trapezoidal fuzzy number x at time point j ij Establish the multi-index trapezoidal fuzzy number matrix X of battery performance m×n , where m is the number of battery performance indicators and n is the number of indicator test time points; Get the battery performance multi-index trapezoidal fuzzy number matrix X m×n , the positive ideal solution TP at different time points j j and anti-ideal solution TQ j Trapezoidal fuzzy number of ; Normalized trapezoidal fuzzy number matrix X m×n Get the first normalized matrix S, normalize the positive ideal solution TP at different time points j j The trapezoidal fuzzy number is obtained by the second normalized matrix S q , normalize the anti-ideal solution TQ at different time points j j The trapezoidal fuzzy number is obtained by the third normalized matrix S p ; According to S, S q and S p Calculate different indicators A i The positive utility K relative to the positive ideal solution + i and the anti-effect K relative to the anti-ideal solution - i ; According to the K + i and K - i Construct different indicators A i The final utility function f(K i ) and sort them.

10. The battery performance real-time evaluation device according to claim 9, characterized in that: The building block specifically uses the following formula to calculate different indicators A i The positive utility K relative to the positive ideal solution + i and the anti-effect K relative to the anti-ideal solution - i : Among them, S qi and S pi Indicator A i The normalized matrix of trapezoidal fuzzy numbers of positive ideal solutions and anti-ideal solutions, i=1,2,3…m, S i For indicator A i The weighted sum of the trapezoidal fuzzy number normalized matrix at different time points j, (a, b, c, d) is the matrix element, and R(a, b, c, d) is the defuzzification function.

Images