A Big Data-Based Method for Evaluating the Safety Performance of New Energy Vehicle Batteries

Abstract

This invention discloses a big data-based method for evaluating the safety performance of new energy vehicle batteries. The method includes the following steps: acquiring operational data of the new energy vehicle battery through a vehicle network data platform; analyzing and processing the battery operational data to obtain analysis results; matching the analysis results with data in a preset battery database to obtain the safety level of the new energy vehicle battery; and sending the obtained safety level of the new energy vehicle battery to a mobile terminal via the Internet of Things (IoT). This invention can acquire real-time parameters of new energy vehicle batteries and fully utilize historical safety performance test data to analyze the current safety performance of new energy vehicle batteries under the same influencing factors. This enables real-time evaluation and feedback of new energy vehicle batteries, ensuring their safety and reliability and reducing related property losses.

Description

Technical Field

[0001] This invention relates to the field of power battery safety supervision technology, and more specifically, to a method for evaluating the safety performance of new energy vehicle batteries based on big data. Background Technology

[0002] With the promotion of electric vehicles and the application of vehicle-to-everything (V2X) technology in my country, more and more new energy vehicles are entering the consumer market. The main systems of new energy vehicles include electric drive systems, power supply systems, and related auxiliary systems. Electric drive consists of a drive controller, an electric motor, a mechanical rotating device, and wheels. The drive motor is similar to the engine of a fuel-powered car, converting the electrical energy in the power battery into the power to propel the car forward. At the same time, during braking, the kinetic energy on the wheels can be converted into electrical energy and recovered into the battery to complete the storage of braking energy.

[0003] The safety of new energy electric vehicles deserves everyone's attention. As the high-voltage source of electric vehicles, battery safety issues can not only endanger the driver's personal safety but also cause related property damage and affect the brand image of electric vehicles. Although existing methods for evaluating the safety performance of new energy vehicle batteries have a certain degree of scientific validity and reliability, some shortcomings still exist. Most existing methods for evaluating the safety performance of new energy vehicle batteries adopt laboratory testing methods, such as electrochemical performance testing and thermal runaway testing. The test results have a certain degree of reliability, but the testing process is cumbersome and costly, and most of them are offline tests. The evaluation results require a certain amount of data processing and analysis to obtain, making it difficult to achieve real-time evaluation and feedback of battery safety performance.

[0004] In existing technologies, historical and newly recorded battery parameter data must be stored in a unified data format to be identified and utilized. However, due to the diverse formats of historical battery data storage and the lack of complete standardization among various platforms, the most common method is storage in text format. Therefore, a large amount of existing data from new energy vehicle batteries cannot be effectively utilized.

[0005] No effective solutions have yet been proposed to address the problems in the relevant technologies. Summary of the Invention

[0006] In response to the problems in related technologies, this invention proposes a big data-based method for evaluating the safety performance of new energy vehicle batteries, in order to overcome the aforementioned technical problems existing in the current related technologies.

[0007] Therefore, the specific technical solution adopted by the present invention is as follows:

[0008] A method for evaluating the safety performance of new energy vehicle batteries based on big data, the method comprising the following steps:

[0009] S1. Obtain operating data of new energy vehicle batteries through the vehicle network data platform;

[0010] S2. Analyze and process the battery operation data, and obtain the analysis results;

[0011] S3. Match the analysis results with the data in the preset battery database to obtain the safety level of the new energy vehicle battery.

[0012] S4. The safety rating of the new energy vehicle battery is sent to the mobile terminal via the Internet of Things.

[0013] Furthermore, the analysis and processing of the battery operating data to obtain the analysis results includes the following steps:

[0014] S21. The battery operating data is denoised, filtered, and smoothed to obtain accurate data;

[0015] S22. Extract features from the accurate data to obtain the feature parameters of the new energy vehicle battery;

[0016] S23. Perform statistical analysis on the characteristic parameters of the new energy vehicle battery to obtain the analysis results, and pre-store them in text form.

[0017] Furthermore, the construction of the battery database includes the following steps:

[0018] Historical safety performance test data for new energy vehicle batteries were collected by reviewing literature.

[0019] Feature extraction is performed on the historical security performance test data to obtain historical feature parameters;

[0020] The safety level of new energy vehicle batteries is calculated based on the aforementioned historical characteristic parameters.

[0021] The obtained historical feature parameters and the safety level of the new energy vehicle battery are stored in text form to obtain a battery database. Further, calculating the safety level of the new energy vehicle battery based on the historical feature parameters includes the following steps:

[0022] Based on the aforementioned historical characteristic parameters, the factors affecting the safety performance of new energy vehicle batteries are analyzed, and an indicator factor system is constructed.

[0023] The indicator factor system was qualitatively screened using expert surveys, and useless indicator factors were deleted.

[0024] Standardize the remaining indicators and construct a set U of factors influencing the safety performance of new energy vehicle batteries.

[0025] The safety level of new energy vehicle batteries is calculated based on the set of influencing factors.

[0026] Furthermore, the construction of the set of factors influencing the safety performance of new energy vehicle batteries, U, also includes the following steps:

[0027] Define a set U of n types of influencing factors encountered by new energy vehicle batteries during their lifespan;

[0028] Define the critical levels of all influencing factors in the set U, and obtain the critical safety level set U of new energy vehicle batteries. A ;

[0029] Define U B This represents the set of highest safety levels of new energy vehicle batteries under the influence of all influencing factors in the set of influencing factors U.

[0030] The relationship transformation formula is used to convert the safety values ​​between different influencing factors and between different characteristic parameters of the same influencing factor into a unified safety value p. ij And obtain the safety set A of new energy vehicle batteries relative to the safety level of influencing factors. i .

[0031] Furthermore, the method of converting the safety values ​​between different influencing factors and between different characteristic parameters of the same influencing factor into a unified safety value p using a relational transformation formula is described. ij The calculation formula is:

[0032]

[0033] Where, p ij This represents the safe value representation of the j-th characteristic parameter in the i-th type of influencing factor.

[0034] x ij U represents the set of critical safety levels B The value of the j-th characteristic parameter in the i-th type of influencing factor;

[0035] x c-ij U represents the set of highest security levels. B The value of the j-th characteristic parameter in the i-th type of influencing factor;

[0036] k ij Indicates the conversion factor;

[0037] When the characteristic parameter x of the safety performance of new energy vehicle batteries under the influence of factors ijWhen the value of increases with the improvement of the safety performance of new energy vehicle batteries, the relational conversion formula takes a positive value; otherwise, the relational conversion formula takes a negative value.

[0038] Furthermore, the calculation of the safety level of new energy vehicle batteries based on the set of influencing factors includes the following steps:

[0039] Define variable R as the safety performance of new energy vehicle batteries, and the value of R is (0,1). R = 0.5 represents the critical safety level of new energy vehicle batteries, R ≥ 0.5 represents that new energy vehicle batteries are relatively safe, and the larger the value of R, the better the relative safety performance of new energy vehicle batteries. R < 0.5 represents that new energy vehicle batteries are low safety or unsafe, and the smaller the value of R, the less safe the safety performance of new energy vehicle batteries.

[0040] When p exists ij ∈A i , making p ij If the value is ≥0.5, it indicates that the new energy vehicle battery is relatively safe under the influence of influencing factors. The safety rating R of the new energy vehicle battery is calculated by the weighted average method.

[0041] When p exists ij ∈A i , making p ij If the value is less than 0.5, it indicates that the new energy vehicle battery is low in safety or unsafe under the influence of influencing factors, and the safety rating R of the new energy vehicle battery is not calculated using the weighted average method.

[0042] Furthermore, the formula for calculating the safety factor R of a new energy vehicle battery using the weighted average method is as follows:

[0043]

[0044] Where R represents the safety level of new energy vehicle batteries calculated using the weighted average method;

[0045] m represents the number of factors that affect the safety performance of new energy vehicle batteries;

[0046] p ij This represents the safe value representation of the j-th characteristic parameter in the i-th type of influencing factor.

[0047] The formula for calculating the safety factor R of new energy vehicle batteries without using the weighted average method is as follows:

[0048] R = min(p) ij ), j = 1, 2, ... m j

[0049] Where R represents the safety level of new energy vehicle batteries not calculated using the weighted average method.

[0050] Furthermore, the step of matching the analysis results with data from a preset battery database to obtain the safety level of the new energy vehicle battery includes the following steps:

[0051] S31. Perform word segmentation on the feature parameters in the analysis results and the historical feature parameters in the battery database respectively, and obtain the word segmentation set;

[0052] S32. After removing punctuation and stop words, obtain the dictionary dataset and calculate the weight value of each word in the dictionary dataset;

[0053] S33. Use the feature parameters in the analysis results and the historical feature parameters in the battery database as a vector space model, and calculate the vector cosine value between the vector space model A of the feature parameters in the analysis results and the vector space model B of the historical feature parameters in the battery database to obtain the matching correlation degree.

[0054] S34. Select the historical feature parameter with the highest matching correlation, and use the safety level of new energy vehicle batteries in the battery database as the current safety level of new energy batteries.

[0055] Furthermore, the process of sending the obtained safety information of the new energy vehicle battery to the mobile terminal via the Internet of Things includes the following steps:

[0056] S41. No warnings or reminders will be given when the safety performance of a new energy vehicle battery is in a relatively safe condition;

[0057] S42. When the safety performance of a new energy vehicle battery is low or unsafe, a warning will be issued to remind the user.

[0058] The beneficial effects of this invention are as follows:

[0059] 1. This invention acquires and analyzes the operating data of new energy vehicle batteries through a vehicle network data platform, thereby obtaining real-time parameters of the new energy vehicle batteries. The analysis results are then matched with data in a preset battery database. This allows for full utilization of historical safety performance test data of new energy vehicle batteries to analyze the current safety performance of new energy vehicle batteries under the same influencing factors, thus achieving real-time evaluation and feedback of new energy vehicle batteries. This ensures the safety and reliability of new energy vehicle batteries and reduces related property losses.

[0060] 2. This invention analyzes the safety of new energy vehicle batteries by collecting historical safety performance test data and based on the influencing factors of the batteries. This allows for a better analysis of the safety performance of new energy vehicle batteries and provides theoretical guidance for the safety design and safety performance evaluation of new energy vehicle batteries.

[0061] 3. This invention performs word segmentation on the feature parameters in the analysis results and the historical feature parameters in the battery database, and calculates the vector cosine value between the vector space model A of the feature parameters in the analysis results and the vector space model B of the historical feature parameters in the battery database to obtain the matching correlation degree. This results in a more accurate correlation degree, enabling the determination of the current safety performance of new energy vehicle batteries based on historical battery performance, thus achieving real-time evaluation of the safety performance of new energy vehicle batteries. Furthermore, although the historical battery parameter data and newly recorded battery parameter data from various platforms have inconsistent data formats, they can still be identified and utilized, thereby increasing the amount of data available for analysis. As a data source for big data analysis, this effectively improves the accuracy of analysis and evaluation. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 This is a flowchart of a method for evaluating the safety performance of new energy vehicle batteries based on big data, according to an embodiment of the present invention. Detailed Implementation

[0064] To further illustrate the various embodiments, the present invention provides accompanying drawings, which are part of the disclosure of the present invention. These drawings are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these drawings, those skilled in the art should be able to understand other possible implementation methods and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0065] According to an embodiment of the present invention, a method for evaluating the safety performance of new energy vehicle batteries based on big data is provided.

[0066] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments, such as... Figure 1 As shown, the method for evaluating the safety performance of new energy vehicle batteries based on big data according to an embodiment of the present invention includes the following steps:

[0067] S1. Obtain the operating data of new energy vehicle batteries through the vehicle network data platform.

[0068] Specifically, the operating data of new energy vehicle batteries includes battery type, battery capacity, battery voltage, battery internal resistance, battery discharge cycles, battery charging cycles, battery temperature, battery charging efficiency, and battery discharging efficiency.

[0069] S2. Analyze and process the battery operation data, and obtain the analysis results.

[0070] Specifically, the process of analyzing and processing the battery operating data to obtain the analysis results includes the following steps:

[0071] S21. The battery operating data is denoised, filtered, and smoothed to obtain accurate data.

[0072] Specifically, the purpose of denoising, filtering, and smoothing battery operating data is to eliminate noise and irregular fluctuations, and improve the accuracy and reliability of the data. Different denoising, filtering, and smoothing methods can be selected for different battery operating data to obtain more accurate and reliable data.

[0073] Noise reduction can be achieved using digital filters, such as median filtering, mean filtering, and Gaussian filtering. Median filtering can remove outliers and is suitable for removing periodic interference and impulse noise. Mean filtering can smooth curves and eliminate high-frequency noise. Gaussian filtering can preserve the details in the signal.

[0074] Filtering: Filtering can use low-pass, high-pass, band-pass, or band-stop filters; low-pass filters can remove high-frequency components and smooth curves; high-pass filters can remove low-frequency components and highlight high-frequency signals; band-pass filters can retain signals within a specific frequency range and filter out signals within other frequency ranges; band-stop filters can filter out signals within a specific frequency range and retain signals within other frequency ranges.

[0075] Smoothing: Smoothing methods can include moving average, exponential smoothing, etc. Moving average is suitable for situations with small data volume and relatively stable signals; exponential smoothing is suitable for situations with large data volume and large signal fluctuations.

[0076] S22. Extract features from the accurate data to obtain the feature parameters of the new energy vehicle battery.

[0077] Specifically, the characteristic parameters of new energy vehicle batteries include battery voltage, battery capacity, charging time and number of times, discharging time and number of times, operating temperature range, rated voltage, etc.

[0078] S23. Perform statistical analysis on the characteristic parameters of the new energy vehicle battery to obtain the analysis results, and pre-store them in text form.

[0079] S3. The analysis results are matched with the data in the preset battery database to obtain the safety level of the new energy vehicle battery.

[0080] Specifically, the step of matching the analysis results with data from a preset battery database to obtain the safety level of the new energy vehicle battery includes the following steps:

[0081] S31. Perform word segmentation on the feature parameters in the analysis results and the historical feature parameters in the battery database respectively, and obtain the word segmentation set C;

[0082] S32. After removing punctuation and stop words, the dictionary dataset is obtained, dataset = (w1, w2, ... w n And calculate the weight value of each word in the dictionary dataset;

[0083] Specifically, the formula for calculating the weight value of each word in the dictionary dataset is as follows:

[0084]

[0085] Among them, t r This represents the weight value of each word in the dictionary dataset.

[0086] d r The word w r Word frequency.

[0087] k indicates the number of times each word appears.

[0088] The word w r The inverse document frequency can be calculated by taking the logarithm of the quotient of the type of feature parameter and the number of feature parameters containing that word.

[0089] S33. Use the feature parameters in the analysis results and the historical feature parameters in the battery database as a vector space model, and calculate the vector cosine value between the vector space model A of the feature parameters in the analysis results and the vector space model B of the historical feature parameters in the battery database to obtain the matching correlation degree.

[0090] Specifically, the cosine value of a vector can be calculated using the cosine similarity principle.

[0091] Cosine similarity calculation originates from the idea of ​​vector cosine calculation. It measures the similarity between two vectors by measuring the cosine of the angle between their inner product space. It is commonly used in text processing in machine learning. Calculating the similarity between two text segments first requires segmenting the text, removing punctuation and stop words, uniformly encoding the words in the text, vectorizing the word frequencies based on the encoding, and then using the cosine theorem to calculate the cosine value of the two vectors. This yields the similarity between the two text segments.

[0092] S34. Select the historical feature parameter with the highest matching correlation, and use the safety level of new energy vehicle batteries in the battery database as the current safety level of new energy batteries.

[0093] Specifically, the construction of the battery database includes the following steps:

[0094] Historical safety performance test data for new energy vehicle batteries were collected by reviewing literature.

[0095] Specifically, historical safety performance test data for new energy vehicle batteries includes tests on the charge and discharge characteristics of batteries under different temperature conditions, thermal runaway tests, and explosion-proof tests.

[0096] Specifically, explosion-proof testing includes the following types of tests:

[0097] Impact test: The battery is impacted onto a hard surface with a certain impact force to test whether the battery explodes or catches fire.

[0098] Thermal shock test: The battery is placed in a high-temperature environment and then suddenly exposed to a low-temperature environment to detect whether the battery explodes or catches fire.

[0099] Short circuit test: A certain current is applied between the two terminals of the battery to simulate a short circuit and detect whether the battery explodes or catches fire.

[0100] External force compression test: Apply a certain external force to the battery to simulate the compression situation during battery use and detect whether the battery will explode or catch fire.

[0101] Feature extraction is performed on the historical security performance test data to obtain historical feature parameters.

[0102] The safety level of new energy vehicle batteries is calculated based on the aforementioned historical characteristic parameters.

[0103] Specifically, calculating the safety of new energy vehicle batteries based on the historical characteristic parameters includes the following steps:

[0104] Based on the aforementioned historical characteristic parameters, we analyzed the factors affecting the safety performance of new energy vehicle batteries and constructed an indicator factor system.

[0105] Specifically, a reasonable indicator system can hierarchically and systematically organize a large number of complex factors. The indicator system reflects the hierarchical structure and main characteristics of the evaluation objectives. The establishment and selection of the indicator system is the basis for comprehensive evaluation and a reliable guarantee for the reasonable and effective evaluation of battery safety performance.

[0106] The indicator factor system was qualitatively screened using expert surveys, and useless indicator factors were deleted.

[0107] The remaining indicators were standardized, and a set U of factors influencing the safety performance of new energy vehicle batteries was constructed.

[0108] Specifically, the standardization of indicators that have not been deleted mainly includes uniformization and dimensionless processing. Uniformization means unifying the types of evaluation indicators; dimensionless processing, also known as indicator normalization, is usually done by mathematical transformation to eliminate the influence of indicator units and orders of magnitude and avoid unreasonable phenomena during the evaluation process. Commonly used dimensionless processing methods include the "standardization" method and the "extreme value method".

[0109] Specifically, the construction of the set of factors influencing the safety performance of new energy vehicle batteries, U, also includes the following steps:

[0110] Define a set U of n types of influencing factors that new energy vehicle batteries encounter during their lifespan.

[0111] Define the critical levels of all influencing factors in the set U, and obtain the critical safety level set U of new energy vehicle batteries. A .

[0112] Define U B This represents the set of highest safety levels for new energy vehicle batteries under the influence of all factors in the set of influencing factors U.

[0113] The relationship transformation formula is used to convert the safety values ​​between different influencing factors and between different characteristic parameters of the same influencing factor into a unified safety value p. ij And obtain the safety set A of new energy vehicle batteries relative to the safety level of influencing factors. i .

[0114] Specifically, the method uses a relationship transformation formula to convert the safety values ​​between different influencing factors and between different characteristic parameters of the same influencing factor into a unified safety value p. ij The calculation formula is:

[0115]

[0116] Where, p ij This represents the safe value representation of the j-th characteristic parameter in the i-th type of influencing factor.

[0117] x ij U represents the set of critical safety levels B The value of the j-th characteristic parameter in the i-th type of influencing factor.

[0118] x c-ij U represents the set of highest security levels. B The value of the j-th characteristic parameter in the i-th type of influencing factor.

[0119] k ij This represents the conversion factor.

[0120] When the characteristic parameter x of the safety performance of new energy vehicle batteries under the influence of factors ij When the value of increases with the improvement of the safety performance of new energy vehicle batteries, the relational conversion formula takes a positive value; otherwise, the relational conversion formula takes a negative value.

[0121] The safety level of new energy vehicle batteries is calculated based on the set of influencing factors.

[0122] Specifically, calculating the safety of new energy vehicle batteries based on the set of influencing factors includes the following steps:

[0123] Define variable R as the safety performance of new energy vehicle batteries, with R taking the value (0,1). R = 0.5 represents the critical safety level of new energy vehicle batteries, R ≥ 0.5 indicates that new energy vehicle batteries are relatively safe, and the larger the value of R, the better the relative safety performance of new energy vehicle batteries. R < 0.5 indicates that new energy vehicle batteries are low-safety or unsafe, and the smaller the value of R, the less safe the safety performance of new energy vehicle batteries.

[0124] When p exists ij ∈A i , making p ij If the value is ≥0.5, it indicates that the new energy vehicle battery is relatively safe under the influence of various factors. The safety rating R of the new energy vehicle battery is calculated using the weighted average method.

[0125] Specifically, the formula for calculating the safety factor R of a new energy vehicle battery using the weighted average method is as follows:

[0126]

[0127] Where R represents the safety level of new energy vehicle batteries calculated using the weighted average method.

[0128] m represents the number of factors that affect the safety performance of new energy vehicle batteries.

[0129] p ij This represents the safe value representation of the j-th characteristic parameter in the i-th type of influencing factor.

[0130] When p exists ij ∈A i , making p ij If the value is less than 0.5, it indicates that the new energy vehicle battery is low in safety or unsafe under the influence of influencing factors, and the safety rating R of the new energy vehicle battery is not calculated using the weighted average method.

[0131] Specifically, the formula for calculating the safety factor R of new energy vehicle batteries without using the weighted average method is as follows:

[0132] R = min(p) ij ), j = 1, 2, ... m j

[0133] Where R represents the safety level of new energy vehicle batteries not calculated using the weighted average method.

[0134] The obtained historical feature parameters and the safety level of the new energy vehicle battery are stored in text form to obtain a battery database.

[0135] Specifically, by storing historical characteristic parameters and the safety level of new energy vehicle batteries in text form, it is possible to match the correlation between the historical characteristic parameters and the historical characteristic parameters detected in real time for new energy vehicle batteries. This allows for the full utilization of historical safety performance test data of new energy vehicle batteries to analyze the current safety performance of new energy vehicle batteries under the same influencing factors.

[0136] S4. The safety rating of the new energy vehicle battery is sent to the mobile terminal via the Internet of Things.

[0137] Specifically, the aforementioned mobile terminals can be mobile phones, mobile tablets, laptops, etc.

[0138] Specifically, sending the obtained safety rating of the new energy vehicle battery to the mobile terminal via the Internet of Things includes the following steps:

[0139] S41. No warnings or reminders will be given when the safety performance of a new energy vehicle battery is in a relatively safe condition;

[0140] S42. When the safety performance of a new energy vehicle battery is low or unsafe, a warning will be issued to remind the user.

[0141] In summary, by utilizing the above-mentioned technical solution of this invention, the present invention acquires and analyzes the operating data of new energy vehicle batteries through a vehicle network data platform, thereby enabling real-time acquisition of real-time parameters of the new energy vehicle batteries. The analysis results are then matched with data from a preset battery database, allowing full utilization of historical safety performance test data of new energy vehicle batteries to analyze the current safety performance of the batteries under the same influencing factors. This achieves real-time evaluation and feedback of the new energy vehicle batteries, ensuring their safety and reliability and reducing related property losses. This invention collects historical safety performance test data of new energy vehicle batteries and, based on the battery... This invention analyzes the influencing factors of new energy vehicle battery safety to better analyze the safety performance of new energy vehicle batteries, thereby providing theoretical guidance for the safety design and safety performance evaluation of new energy vehicle batteries. The invention further segments the feature parameters in the analysis results and the historical feature parameters in the battery database, and calculates the vector cosine value between the vector space model A of the feature parameters in the analysis results and the vector space model B of the historical feature parameters in the battery database to obtain the matching correlation degree. This results in a more accurate correlation degree, enabling the determination of the current safety performance of new energy vehicle batteries based on historical battery performance, thus achieving real-time evaluation of the safety performance of new energy vehicle batteries.

[0142] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for evaluating the safety performance of new energy vehicle batteries based on big data, characterized in that, include: S1. Obtain operating data of new energy vehicle batteries through the vehicle network data platform; S2. Analyze and process the battery operation data, and obtain the analysis results; S3. Match the analysis results with the data in the preset battery database to obtain the safety level of the new energy vehicle battery. S4. The safety rating of the new energy vehicle battery is sent to the mobile terminal via the Internet of Things. S3 includes: S31, performing word segmentation on the feature parameters in the analysis results and the historical feature parameters in the battery database respectively, and obtaining a word segmentation set; S32, removing punctuation and stop words to obtain a dictionary dataset, and calculating the weight value of each word in the dictionary dataset; S33, using the feature parameters in the analysis results and the historical feature parameters in the battery database as a vector space model, and calculating the vector cosine value between the vector space model A of the feature parameters in the analysis results and the vector space model B of the historical feature parameters in the battery database to obtain the matching correlation degree; S34, selecting the historical feature parameter with the highest matching correlation degree, and using the new energy vehicle battery safety level in the battery database as the current new energy battery safety level; the construction of the battery database includes: collecting new energy vehicle battery safety level data through literature review. Historical safety performance test data of new energy vehicle batteries; feature extraction of historical safety performance test data to obtain historical feature parameters; calculation of the safety level of new energy vehicle batteries based on historical feature parameters; storage of the obtained historical feature parameters and the safety level of new energy vehicle batteries in text form to obtain a battery database; calculation of the safety level of new energy vehicle batteries based on historical feature parameters includes: analyzing the influencing factors affecting the safety performance of new energy vehicle batteries based on historical feature parameters and constructing an indicator factor system; qualitatively screening the indicator factor system using expert surveys and deleting useless indicator factors; standardizing the remaining indicator factors and constructing a set U of influencing factors for the safety performance of new energy vehicle batteries; and calculating the safety level of new energy vehicle batteries based on the set of influencing factors. Constructing the set U of factors influencing the safety performance of new energy vehicle batteries also includes: defining a set U of n types of influencing factors encountered by new energy vehicle batteries during their lifespan; defining the critical levels of all influencing factors in the set U, thus obtaining the set U of critical safety levels for new energy vehicle batteries. A Define U B This represents the set of highest safety levels for new energy vehicle batteries under the influence of all factors in the set of influencing factors U; the safety values ​​between different influencing factors and between different characteristic parameters of the same influencing factor are converted into a unified safety value p through a relational transformation formula. ij And obtain the safety set A of new energy vehicle batteries relative to the safety level of influencing factors. i The relationship transformation formula is used to convert the safety values ​​between different influencing factors and between different characteristic parameters of the same influencing factor into a unified safety value p. ij The calculation formula is: p ij This represents the safe value representation of the j-th characteristic parameter in the i-th type of influencing factor; x ij U represents the set of critical safety levels B The value of the j-th characteristic parameter among the i-th influencing factors; x c-ij U represents the set of highest security levels. B The value of the j-th characteristic parameter in the i-th type of influencing factor; k ij Indicates the conversion factor; x is a characteristic parameter representing the safety performance of a new energy vehicle battery under the influence of various factors. ij When the value of increases with the improvement of the safety performance of new energy vehicle batteries, the relationship conversion formula takes a positive value; otherwise, the relationship conversion formula takes a negative value. The calculation of the safety level of new energy vehicle batteries based on the set of influencing factors includes: defining the variable R as the safety performance of new energy vehicle batteries, with the value of R taking the range of (0,1), and using R=0.5 to represent the critical safety level of new energy vehicle batteries, R≥0.5 to represent that new energy vehicle batteries are relatively safe, and the larger the value of R, the better the relative safety performance of new energy vehicle batteries; R<0.5 to represent that new energy vehicle batteries are low safety or unsafe, and the smaller the value of R, the less safe the safety performance of new energy vehicle batteries. a) When p exists ij ∈A i , making p ij A value ≥0.5 indicates that the new energy vehicle battery is relatively safe under the influence of various factors. The safety factor R of the new energy vehicle battery is calculated using the weighted average method. The formula for calculating the safety factor R of the new energy vehicle battery using the weighted average method is as follows: R represents the safety level of new energy vehicle batteries calculated using the weighted average method; m represents the number of factors that affect the safety performance of new energy vehicle batteries; p ij This represents the safe value representation of the j-th characteristic parameter in the i-th type of influencing factor. b) When p exists ij ∈A i , making p ij If the value is less than 0.5, it indicates that the new energy vehicle battery is low in safety or unsafe under the influence of various factors. The safety rating R of the new energy vehicle battery is not calculated using the weighted average method. The formula for calculating the safety rating R of the new energy vehicle battery without using the weighted average method is as follows: R indicates that the safety of new energy vehicle batteries is not calculated using the weighted average method.

2. The method for evaluating the safety performance of new energy vehicle batteries based on big data according to claim 1, characterized in that, The analysis and processing of battery operating data, and the resulting analysis, include the following steps: S21. Perform noise reduction, filtering, and smoothing on the battery operation data to obtain accurate data; S22. Extract features from accurate data and obtain the characteristic parameters of new energy vehicle batteries; S23. Perform statistical analysis on the characteristic parameters of new energy vehicle batteries to obtain the analysis results, and pre-store them in text form.

3. The method for evaluating the safety performance of new energy vehicle batteries based on big data according to claim 1, characterized in that, Sending the safety information of new energy vehicle batteries to mobile terminals via the Internet of Things includes the following steps: S41. No warnings or reminders will be given when the safety performance of a new energy vehicle battery is in a relatively safe condition; S42. When the safety performance of a new energy vehicle battery is low or unsafe, a warning will be issued to remind the user.

Images