New energy vehicle health state evaluation system based on big data
Through the big data acquisition and analysis module, the charging, static discharge and dynamic discharge data of new energy vehicle batteries are collected and processed in real time. Combined with the weight adjustment and health constraints in the preset scenario, the accurate evaluation of the battery's health status and real-time real-time performance are achieved. Feedback solves the problem of inconvenient battery health status assessment in the prior art.
Patent Information
- Application Number
- CN202411253130.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-09
- Publication Date
- 2024-12-06
AI Technical Summary
In the prior art, it is inconvenient to evaluate the health status of batteries, and it is difficult to accurately evaluate the nonlinear attenuation law under the influence of various factors.
Adopt a new energy vehicle health status assessment system based on big data, and collect battery characteristic data in real time through the data acquisition module. The data processing module processes and obtains the data to be analyzed, and conducts comprehensive analysis through the data analysis module in the preset scenario to obtain health status assessment. result.
It realizes an accurate assessment of the health status of new energy vehicles, solves the problem of inconvenient assessment of battery health status, and provides real-time health status feedback and alarm information.
Smart Images

Figure CN119087266A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of new energy vehicles, and in particular to a new energy vehicle health status assessment system based on big data. Background Art
[0002] The power battery pack is the core component of electric vehicles, and the evaluation of its health status is the key to ensure the safe, stable and efficient operation of electric vehicles. Since the performance parameters of the battery pack are highly related to the operating conditions of electric vehicles, and it is difficult to simulate the actual operating conditions under laboratory conditions, the study of battery pack evaluation based on real vehicle data has great practical value and realistic significance.
[0003] However, in practical applications, the attenuation of battery health status often shows a nonlinear law and is affected by multiple factors, making the battery health status difficult to evaluate. Summary of the invention
[0004] The purpose of the present invention is to provide a new energy vehicle health status assessment system and system based on big data, which solves the technical problem of inconvenient battery health status assessment in the prior art.
[0005] The present invention provides a new energy vehicle health status assessment system based on big data, the system comprising: A data acquisition module, wherein the data acquisition module is used to collect characteristic data of new energy vehicle batteries, the characteristic data including charging data, static discharge data and dynamic discharge data; A data processing module, the data processing module is used to process the characteristic data to obtain data to be analyzed; the data to be analyzed includes: charging health data, static health data and dynamic health data; The data analysis module is used to analyze the data to be analyzed according to the preset conditions corresponding to the preset scenarios when the new energy vehicle enters several preset scenarios, obtain the health status assessment results and send them to the user end.
[0006] Furthermore, the data acquisition module includes: A current sensor, which is used to collect current data of the battery of the new energy vehicle in real time; A voltage sensor, which is used to collect voltage data of a new energy vehicle battery in real time; A temperature sensor, which is used to collect temperature data of the new energy vehicle battery in real time; A battery monitoring sensor, which is used to collect internal resistance data of new energy vehicle batteries in real time; A speed sensor, wherein the speed sensor is used to collect speed data of the new energy vehicle; A first processor is used to obtain charging data, static discharge data and dynamic discharge data according to current data, voltage data, temperature data, internal resistance data and speed data.
[0007] Furthermore, the charging data includes several charging segments; each charging segment includes several battery data-time curves; the static discharge data includes several static discharge segments, and several static discharge segments include several battery data-time curves; the dynamic discharge data includes several dynamic discharge segments, and several dynamic discharge segments include several battery data-speed curves; the battery data includes current, voltage, temperature and internal resistance.
[0008] Furthermore, the data processing module is used to process the feature data to obtain data to be analyzed, including: The data processing module is provided with a first health analysis model, a second health analysis model and a third health analysis module; Inputting the charging data into a first health analysis model to obtain charging health data; Inputting the static discharge data into a second health analysis model to obtain static health data; Inputting the dynamic discharge data into a third health analysis model to obtain dynamic health data; The charging health data, static health data and dynamic health data all include health evaluation.
[0009] Furthermore, the preset scenarios include parking and charging scenarios, parking without charging scenarios, and driving scenarios; The preset conditions corresponding to the preset scenarios include weight coefficients corresponding to charging health data, static health data, and dynamic health data.
[0010] Furthermore, the data to be analyzed is analyzed according to the preset conditions corresponding to the preset scenarios to obtain health status assessment results, including: Obtain the comparison sequence, reference sequence, and weight coefficients corresponding to the charging health data, static health data, and dynamic health data corresponding to the current preset scenario; According to the charging health data, static health data and dynamic health data, confirm the input matrix corresponding to the current preset scenario; Obtain an analysis matrix based on the input matrix, the comparison sequence, and the reference sequence; Based on the analysis matrix, confirm the correlation coefficient matrix; Determine the weight matrix based on the weight coefficients corresponding to the charging health data, the static health data, and the dynamic health data; Based on the correlation coefficient matrix and the weight matrix, confirm the evaluation value corresponding to the input matrix and the ranking in the comparison sequence; The health status assessment results include input matrix evaluation values and rankings.
[0011] Furthermore, the preset conditions corresponding to the preset scenarios also include weight adjustment conditions, and the weight adjustment conditions are used to adjust the weight coefficients corresponding to the preset conditions corresponding to the preset scenarios, including charging health data, static health data, and dynamic health data.
[0012] Furthermore, the weight adjustment condition includes: determining whether there are several sub-scenes in the preset scene, and if so, obtaining the duration ratio of each sub-scene in the preset scene; and adjusting the weight coefficient of the current preset scene according to the duration ratio of each sub-scene.
[0013] Furthermore, according to the charging health data, the static health data and the dynamic health data, the input matrix corresponding to the current preset scenario is confirmed, including: Standardize the health evaluation of charging health data, static health data, and dynamic health data; the standardization includes de-dimensionalization and positive processing; Based on the health evaluation of the charging health data, the static health data and the dynamic health data after the standardized processing, an input matrix is obtained.
[0014] Furthermore, the preset conditions corresponding to the preset scenario also include health status constraints; when the car enters the preset scenario, it is determined whether the health status assessment result meets the health status constraints; if not, an alarm message is generated and sent to the user end.
[0015] Compared with the prior art, the present invention has the following beneficial effects: In this embodiment, a data acquisition module is set to collect charging data, static discharge data and dynamic discharge data of new energy vehicle batteries; so that the data processing module can analyze and obtain corresponding charging health data, static health data and dynamic health data respectively; the data analysis module can comprehensively judge the health status in a preset scenario according to the charging health data, static health data and dynamic health data according to preset conditions in several preset scenarios and obtain the health status evaluation result and send it to the user end. The technical problem of inconvenient battery health status evaluation in the prior art is solved. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 This is a principle block diagram of the new energy vehicle health status assessment system based on big data of the present invention. DETAILED DESCRIPTION
[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0018] like Figure 1 As shown, a new energy vehicle health status assessment system based on big data includes: A data acquisition module, wherein the data acquisition module is used to collect characteristic data of new energy vehicle batteries, the characteristic data including charging data, static discharge data and dynamic discharge data; A data processing module, the data processing module is used to process the characteristic data to obtain data to be analyzed; the data to be analyzed includes: charging health data, static health data and dynamic health data; The data analysis module is used to analyze the data to be analyzed according to the preset conditions corresponding to the preset scenarios when the new energy vehicle enters several preset scenarios, obtain the health status assessment results and send them to the user end.
[0019] The specific implementation process of this embodiment includes: In this embodiment, a data acquisition module is set to collect charging data, static discharge data and dynamic discharge data of new energy vehicle batteries; so that the data processing module can analyze and obtain corresponding charging health data, static health data and dynamic health data respectively; the data analysis module can comprehensively judge the health status in a preset scenario according to the charging health data, static health data and dynamic health data according to preset conditions in several preset scenarios and obtain the health status evaluation result and send it to the user end. The technical problem of inconvenient battery health status evaluation in the prior art is solved.
[0020] In this embodiment, the use status of the new energy vehicle battery is divided into a charging state, a static discharge state and a dynamic discharge state, wherein the static discharge state includes the natural discharge state of the battery when the speed of the new energy vehicle is 0, and the discharge state for maintaining the static basic operation of the new energy vehicle; the dynamic discharge state includes the discharge state of the battery when the speed of the new energy vehicle is greater than 0.
[0021] The battery usage status is divided into charging state, static discharge state and dynamic discharge state, and the charging data in the charging state and the charging health data obtained based on the charging data are obtained respectively; the static discharge data in the static discharge state and the static health data obtained based on the static discharge data; the dynamic discharge data in the dynamic discharge state and the dynamic health data obtained based on the dynamic discharge data are obtained respectively.
[0022] In this embodiment, the data acquisition module includes: A current sensor, which is used to collect the current data of the battery of a new energy vehicle in real time; a voltage sensor, which is used to collect the voltage data of the battery of a new energy vehicle in real time; a temperature sensor, which is used to collect the temperature data of the battery of a new energy vehicle in real time; a battery monitoring sensor, which is used to collect the internal resistance data of the battery of a new energy vehicle in real time; a speed sensor, which is used to collect the speed data of the new energy vehicle; A first processor is used to obtain charging data, static discharge data and dynamic discharge data according to current data, voltage data, temperature data, internal resistance data and speed data.
[0023] In this embodiment, the charging data includes several charging segments; each charging segment includes several battery data-time curves; the static discharge data includes several static discharge segments, and the several static discharge segments include several battery data-time curves; the dynamic discharge data includes several dynamic discharge segments, and the several dynamic discharge segments include several battery data-speed curves; the battery data includes current, voltage, temperature and internal resistance.
[0024] In this embodiment, a plurality of charging segments, a plurality of static discharge segments, and a plurality of dynamic discharge segments are all within the corresponding preset time range. The charging segment includes a segment with abnormal battery data during the charging process; the static discharge segment includes a segment with abnormal battery data during the static discharge process; and the dynamic discharge segment includes a segment with abnormal battery data during the dynamic discharge process.
[0025] When at least one item in the battery data is abnormal, the abnormal data item and other data items in the battery data are intercepted to obtain a charging segment, a static discharge segment, and a dynamic discharge segment.
[0026] In this embodiment, the data processing module is used to process the feature data to obtain the data to be analyzed, including: The data processing module is provided with a first health analysis model, a second health analysis model and a third health analysis module; Inputting the charging data into a first health analysis model to obtain charging health data; Inputting the static discharge data into a second health analysis model to obtain static health data; Inputting the dynamic discharge data into a third health analysis model to obtain dynamic health data; The charging health data, static health data and dynamic health data all include health evaluation.
[0027] In this embodiment, the first health analysis model, the second health analysis model, and the third health analysis model all include a neural network model; The process of obtaining the first health analysis model includes: Based on the charging segments, acquiring a charging health relationship database, wherein the health relationship database includes a plurality of charging segments, health evaluations, and mapping relationships between the plurality of charging segments and health evaluations; The neural network analysis model is trained using the charging health relationship database to obtain a first health analysis model.
[0028] The process of obtaining the second health analysis model includes: Based on the static discharge segment, a static discharge health relationship database is obtained, wherein the static discharge health relationship database includes a plurality of static discharge segments, health evaluations, and mapping relationships between the plurality of static discharge segments and health evaluations; The electrostatic discharge health relationship database is used to train the neural network analysis model to obtain a second health analysis model.
[0029] The process of obtaining the third health analysis model includes: Based on the motion discharge segment, a motion discharge health relationship database is obtained, wherein the motion discharge health relationship database includes a plurality of motion discharge segments, health evaluations, and mapping relationships between the plurality of motion discharge segments and health evaluations; The neural network analysis model is trained using the dynamic discharge health relationship database to obtain a third health analysis model.
[0030] According to another embodiment of the present invention, the preset scenarios include a parking and charging scenario, a parking and non-charging scenario, and a driving scenario; The preset conditions corresponding to the preset scenarios include weight coefficients corresponding to charging health data, static health data, and dynamic health data.
[0031] The specific implementation process of this embodiment includes: In this embodiment, the use scenarios of new energy vehicles are divided into multiple preset scenarios, each of which corresponds to a different battery usage state and has different requirements for battery health status. For example, in the parking charging scenario, the battery charging health data requirement is the highest, the static health data is the second, and the dynamic health data requirement is the lowest.
[0032] For parking without charging, the static health data requirement for the battery is the highest, followed by the dynamic health data requirement, and the charging health data requirement is the lowest. In driving scenarios, the dynamic health data requirements for the battery are the highest, the static health data requirements are the second, and the charging health data requirements are the lowest.
[0033] Therefore, in the preset conditions corresponding to each preset scenario, the weight coefficients of charging health data, static health data and dynamic health data are different. The larger the weight coefficient, the more important the data is for the preset scenario.
[0034] In this embodiment, the data to be analyzed is analyzed according to the preset conditions corresponding to the preset scenarios to obtain the health status assessment results, including: Obtain the comparison sequence, reference sequence, and weight coefficients corresponding to the charging health data, static health data, and dynamic health data corresponding to the current preset scenario; According to the charging health data, static health data and dynamic health data, confirm the input matrix corresponding to the current preset scenario; Obtain an analysis matrix based on the input matrix, the comparison sequence, and the reference sequence; Based on the analysis matrix, confirm the correlation coefficient matrix; Determine the weight matrix based on the weight coefficients corresponding to the charging health data, the static health data, and the dynamic health data; Based on the correlation coefficient matrix and the weight matrix, confirm the evaluation value corresponding to the input matrix and the ranking in the comparison sequence; The health status assessment results include input matrix evaluation values and rankings.
[0035] It should be noted that, in this embodiment, the input matrix corresponding to the current preset scenario is determined based on the charging health data, the static health data, and the dynamic health data, including: Standardize the health evaluation of charging health data, static health data, and dynamic health data; the standardization includes de-dimensionalization and positive processing; Based on the health evaluation of the charging health data, the static health data and the dynamic health data after the standardized processing, an input matrix is obtained.
[0036] In this embodiment, the input matrix is represented as S=[s1,s2,…,s n ] T , where n is a positive integer, and in this embodiment, n is equal to 3; S n represents the nth health evaluation; The comparison sequence of the current preset scene is B=[B1,B2,B3,…B99]; there are 99 sets of data in the comparison sequence; the reference sequence is Z=[z1,z2,…,zn]T ; Where B1=[b 11 ,b 21 ,…,b n1 ] T ; The comparison sequence and standard input matrix form an analysis matrix D=[B1,B2,B3,…B99,S] with n rows and 100 columns; Based on the analysis matrix, confirm the correlation coefficient matrix, including: According to the analysis matrix D and the reference sequence Z, the minimum difference and maximum difference corresponding to each physical indicator are obtained. The formula is as follows: ; ; d ij For the element in row i and column j of the analysis matrix D, z i is the element in the i-th row of the reference sequence Z, i.e., the reference value of the health assessment.
[0037] According to the correlation coefficient formula, the correlation coefficient corresponding to each element in the analysis matrix is calculated to obtain the correlation coefficient matrix G; the correlation coefficient formula is as follows: ; Among them, g ij is the correlation coefficient of the elements in the i-th row and j-th column of the analysis matrix D, Cmini is the minimum difference of the i-th health evaluation; Cmaxi is the maximum difference of the i-th health evaluation; ρ is the resolution; ρ is 0.6; d ij is the element in row i and column j of the analysis matrix D; z i is the i-th element in the reference sequence Z; 1≤i≤n; 1≤j≤100.
[0038] Based on the weight coefficients corresponding to the charging health data, static health data, and dynamic health data, a weight matrix is determined, including: In this embodiment, the weight matrix Q=[q1, q2, ..., q n ];q n is the weight coefficient corresponding to the nth health data.
[0039] Based on the correlation coefficient matrix and the weight matrix, confirm the evaluation value corresponding to the input matrix and the ranking in the comparison sequence, including: The evaluation values of the standard input data and each comparison data are obtained according to the correlation coefficient matrix G and the weight matrix Q, where G=[G1, G2, …, G 100 ],G1=[g 11 ,g 21 ,…,g n1 ] T ; The calculation formula is as follows: ; Among them, PJ j is the evaluation value corresponding to the jth group of data, G j is the correlation coefficient column matrix corresponding to the j-th group of data. 1≤j≤100; Q is the weight matrix.
[0040] The evaluation value and ranking of the input matrix are obtained as the health status assessment result.
[0041] According to another embodiment of the present invention, the preset conditions corresponding to the preset scenarios also include weight adjustment conditions, which are used to adjust the weight coefficients corresponding to the preset conditions corresponding to the preset scenarios, including charging health data, static health data, and dynamic health data.
[0042] The specific implementation process of this embodiment includes: In this embodiment, the weight adjustment condition includes: determining whether there are several sub-scenes in the preset scene, and if so, obtaining the duration ratio of each sub-scene in the preset scene; and adjusting the weight coefficient of the current preset scene according to the duration ratio of each sub-scene.
[0043] For example, in a driving scenario, by obtaining the departure point, destination, and current power, it can be estimated that there are static discharge sub-scenario, dynamic discharge sub-scenario, and charging sub-scenario between the departure point and the destination of the new energy vehicle; the static discharge sub-scenario includes parking and resting at a service area, waiting for traffic lights, etc.; the charging sub-scenario includes charging at a charging pile. In this embodiment, the duration ratio of each sub-scenario is obtained through big data analysis.
[0044] Based on the duration ratio of each sub-scene, the duration percentage corresponding to each sub-scene is obtained, where the duration percentage includes the percentage of the duration corresponding to the sub-scene in the total duration.
[0045] Then, the weight coefficients corresponding to the charging health data, static health data and dynamic health data in the preset scenario are multiplied by the duration percentage in the corresponding sub-scenario to obtain new weight coefficients corresponding to the charging health data, static health data and dynamic health data.
[0046] According to another embodiment of the present invention, the preset conditions corresponding to the preset scene also include health status constraints; when the car enters the preset scene, it is determined whether the health status assessment result meets the health status constraints; if not, an alarm message is generated and sent to the user end.
[0047] The specific implementation process of this embodiment includes: In this implementation, the health status constraints include the ranking not being lower than a preset ranking, and the evaluation value not being lower than a preset evaluation value.
[0048] If the new energy vehicle enters the preset scenario and does not meet the corresponding health constraint conditions at this time, an alarm message is generated and sent to the user end to remind the owner not to drive the new energy vehicle into the current preset scenario.
[0049] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0050] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.
Claims
1. New energy vehicle health status assessment system based on big data, Features: The system comprises: A data acquisition module, wherein the data acquisition module is used to collect characteristic data of new energy vehicle batteries, the characteristic data including charging data, static discharge data and dynamic discharge data; A data processing module, the data processing module is used to process the characteristic data to obtain data to be analyzed; the data to be analyzed includes: charging health data, static health data and dynamic health data; The data analysis module is used to analyze the data to be analyzed according to the preset conditions corresponding to the preset scenarios when the new energy vehicle enters several preset scenarios, obtain the health status assessment results and send them to the user end.
2. The new energy vehicle health status assessment system based on big data as claimed in claim 1, Features: The data acquisition module comprises: A current sensor, which is used to collect current data of the battery of the new energy vehicle in real time; A voltage sensor, which is used to collect voltage data of a new energy vehicle battery in real time; A temperature sensor, which is used to collect temperature data of the new energy vehicle battery in real time; A battery monitoring sensor, which is used to collect internal resistance data of new energy vehicle batteries in real time; A speed sensor, wherein the speed sensor is used to collect speed data of the new energy vehicle; A first processor is used to obtain charging data, static discharge data and dynamic discharge data according to current data, voltage data, temperature data, internal resistance data and speed data.
3. The new energy vehicle health status assessment system based on big data as claimed in claim 2, Features: The charging data includes several charging segments; each charging segment includes several battery data-time curves; the static discharge data includes several static discharge segments, and several static discharge segments include several battery data-time curves; the dynamic discharge data includes several dynamic discharge segments, and several dynamic discharge segments include several battery data-speed curves; the battery data includes current, voltage, temperature and internal resistance.
4. The new energy vehicle health status assessment system based on big data as claimed in claim 3, Features: The data processing module is used to process the feature data to obtain data to be analyzed, including: The data processing module is provided with a first health analysis model, a second health analysis model and a third health analysis module; Inputting the charging data into a first health analysis model to obtain charging health data; Inputting the static discharge data into a second health analysis model to obtain static health data; Inputting the dynamic discharge data into a third health analysis model to obtain dynamic health data; The charging health data, static health data and dynamic health data all include health evaluation.
5. The new energy vehicle health status assessment system based on big data as claimed in claim 1, Features: The preset scenarios include parking and charging scenarios, parking without charging scenarios, and driving scenarios; The preset conditions corresponding to the preset scenarios include weight coefficients corresponding to charging health data, static health data, and dynamic health data.
6. The new energy vehicle health status assessment system based on big data as claimed in claim 5, Features: Analyze the data to be analyzed according to the preset conditions corresponding to the preset scenarios to obtain health status assessment results, including: Obtain the comparison sequence, reference sequence, and weight coefficients corresponding to the charging health data, static health data, and dynamic health data corresponding to the current preset scenario; According to the charging health data, static health data and dynamic health data, confirm the input matrix corresponding to the current preset scenario; Obtain an analysis matrix based on the input matrix, the comparison sequence, and the reference sequence; Based on the analysis matrix, confirm the correlation coefficient matrix; Determine the weight matrix based on the weight coefficients corresponding to the charging health data, the static health data, and the dynamic health data; Based on the correlation coefficient matrix and the weight matrix, confirm the evaluation value corresponding to the input matrix and the ranking in the comparison sequence; The health status assessment results include input matrix evaluation values and rankings.
7. The new energy vehicle health status assessment system based on big data as claimed in claim 6, Features: The preset conditions corresponding to the preset scenarios also include weight adjustment conditions, which are used to adjust the weight coefficients corresponding to the preset conditions corresponding to the preset scenarios, including charging health data, static health data, and dynamic health data.
8. The new energy vehicle health status assessment system based on big data as claimed in claim 7, Features: The weight adjustment condition includes: determining whether there are several sub-scenes in the preset scene, and if so, obtaining the duration ratio of each sub-scene in the preset scene; and adjusting the weight coefficient of the current preset scene according to the duration ratio of each sub-scene.
9. The new energy vehicle health status assessment system based on big data as claimed in claim 6, Features: According to the charging health data, static health data and dynamic health data, the input matrix corresponding to the current preset scenario is confirmed, including: Standardize the health evaluation of charging health data, static health data, and dynamic health data; the standardization includes de-dimensionalization and positive processing; Based on the health evaluation of the charging health data, the static health data and the dynamic health data after the standardized processing, an input matrix is obtained.
10. The new energy vehicle health status assessment system based on big data as claimed in claim 6, Features: The preset conditions corresponding to the preset scenario also include health status constraints; when the car enters the preset scenario, it is determined whether the health status assessment result meets the health status constraints; if not, an alarm message is generated and sent to the user end.
Citation Information
Cited By
Vehicle battery health degree detection method and system based on multi-parameter fusion analysis
CN120686096A
Vehicle battery health degree detection method and system based on multi-parameter fusion analysis
CN120686096B
Electric bicycle battery health state evaluation system based on data fusion
CN122017653A
Electric bicycle battery health state evaluation system based on data fusion
CN122017653B
