Vehicle battery health status assessment method, device, medium and equipment

Abstract

The present disclosure relates to a vehicle battery health status assessment method, device, medium and equipment, the method comprising: obtaining first indicator data of a vehicle battery to be tested; determining a first state label and a second state label of the vehicle battery to be tested according to the first indicator data; determining a health status score of the vehicle battery to be tested according to a first frequency interval corresponding to the first state label and a first degree interval corresponding to the second state label, wherein the first frequency interval is determined according to first frequency information corresponding to each of M first vehicle batteries pre-labeled as first state labels, and the first degree interval is determined according to first degree information corresponding to each of N second vehicle batteries pre-labeled as second state labels. In this way, an accurate health status score of the vehicle battery to be tested can be obtained according to the first frequency interval and the first degree interval, and the vehicle battery health status can be scored and quantified, thereby accurately assessing the battery health status.

Description

Technical Field

[0001] The present disclosure relates to the technical field of power batteries, and in particular to a vehicle battery health status assessment method, device, medium and equipment. Background Art

[0002] With the rapid development of the new energy vehicle industry, the number of new energy vehicles has continued to increase. For new energy vehicles, power batteries are important components of the vehicle, and they have an impact on vehicle range, driving safety, service life and other aspects. Therefore, how to accurately evaluate the health status of vehicle batteries is a problem that needs to be solved. Summary of the invention

[0003] The purpose of the present disclosure is to provide a vehicle battery health status assessment method, device, medium and equipment, which can obtain an accurate health status score of the vehicle battery to be tested according to the frequency range and degree range, thereby accurately assessing the battery health status.

[0004] In order to achieve the above objectives, in a first aspect, the present disclosure provides a vehicle battery health status assessment method, the method comprising:

[0005] Acquire first indicator data of a vehicle battery to be tested, wherein the indicator data includes data of an indicator that affects a health status of the vehicle battery;

[0006] Determine a first status label and a second status label of the vehicle battery to be tested according to the first indicator data, wherein the first status label is used to characterize the frequency of abnormal health status of the vehicle battery, and the second status label is used to characterize the degree of abnormal health status of the vehicle battery;

[0007] The health status score of the vehicle battery to be tested is determined according to the first frequency interval corresponding to the first status label and the first degree interval corresponding to the second status label, wherein the first frequency interval is determined according to the first frequency information corresponding to each of the M first vehicle batteries pre-labeled as the first status label, and the first frequency information is the frequency information of abnormal health status of the first vehicle battery; the first degree interval is determined according to the first degree information corresponding to each of the N second vehicle batteries pre-labeled as the second status label, and the first degree information is the degree information of abnormal health status of the second vehicle battery; M is a positive integer greater than 1, and N is a positive integer greater than 1.

[0008] In a second aspect, the present disclosure provides a vehicle battery health status assessment device, the device comprising:

[0009] A first acquisition module is used to acquire first indicator data of a vehicle battery to be tested, wherein the indicator data includes data of an indicator that affects a health status of the vehicle battery;

[0010] A first determination module is used to determine a first status label and a second status label of the vehicle battery to be tested according to the first indicator data, wherein the first status label is used to characterize the frequency of abnormal health status of the vehicle battery, and the second status label is used to characterize the degree of abnormal health status of the vehicle battery;

[0011] A second determination module is used to determine the health status score of the vehicle battery to be tested according to a first frequency interval corresponding to the first status label and a first degree interval corresponding to the second status label, wherein the first frequency interval is determined according to the first frequency information corresponding to each of M first vehicle batteries pre-labeled as the first status label, and the first frequency information is the frequency information of abnormal health status of the first vehicle battery; the first degree interval is determined according to the first degree information corresponding to each of N second vehicle batteries pre-labeled as the second status label, and the first degree information is the degree information of abnormal health status of the second vehicle battery; M is a positive integer greater than 1, and N is a positive integer greater than 1.

[0012] In a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle battery health status assessment method provided in the first aspect of the present disclosure.

[0013] In a fourth aspect, the present disclosure provides an electronic device, including:

[0014] a memory having a computer program stored thereon;

[0015] A processor is used to execute the computer program in the memory to implement the steps of the vehicle battery health status assessment method provided in the first aspect of the present disclosure.

[0016] Through the above technical solution, the health status score of the vehicle battery to be tested can be determined according to the first frequency interval corresponding to the first status label and the first degree interval corresponding to the second status label. Among them, different status labels used to characterize the high and low abnormal frequencies can correspond to different frequency intervals. According to the first frequency information corresponding to each of the M first vehicle batteries, the first frequency interval corresponding to the first status label is determined, and the interval of accurate frequency information under the first status label can be obtained. Different status labels used to characterize the high and low abnormal degrees can correspond to different degree intervals. According to the first degree information corresponding to each of the N second vehicle batteries, the first degree interval corresponding to the second status label is determined, and the interval of accurate degree information under the second status label can be obtained. Therefore, an accurate health status score of the vehicle battery to be tested can be obtained based on the first frequency interval and the first degree interval. The health status score comprehensively considers the abnormal frequency and abnormal degree of the vehicle battery to be tested, and is more accurate, especially for vehicle batteries with relatively high abnormal frequency and low abnormal degree each time, and vehicle batteries with relatively low abnormal frequency but high abnormal degree each time. The health status of the battery can be evaluated from two dimensions of abnormal frequency and abnormal degree at the same time, and the obtained health status score is more accurate, and the vehicle battery health status can be scored and quantified, thereby accurately evaluating the battery health status.

[0017] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0019] Figure 1 The figure is a flow chart of a vehicle battery health status assessment method according to an exemplary embodiment.

[0020] Figure 2 The figure is a flow chart of a vehicle battery health status assessment method according to an exemplary embodiment.

[0021] Figure 3 It is a schematic diagram showing first abnormality degree information corresponding to different moments according to an exemplary embodiment.

[0022] Figure 4 The present invention is a flowchart of a method for determining a frequency interval corresponding to a first state tag according to an exemplary embodiment.

[0023] Figure 5 The present invention is a flowchart of a method for determining a degree interval corresponding to a second state label according to an exemplary embodiment.

[0024] Figure 6 The figure is a block diagram of a vehicle battery health status assessment device according to an exemplary embodiment.

[0025] Figure 7 It is a block diagram of an electronic device according to an exemplary embodiment.

[0026] Figure 8 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0027] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0028] Figure 1 is a flow chart of a vehicle battery health status evaluation method according to an exemplary embodiment, which method can be applied to electronic devices with processing capabilities, such as servers, personal computers, etc. Figure 1 As shown, the method may include steps 11 to 13.

[0029] In step 11, first indicator data of the vehicle battery to be tested is obtained.

[0030] The vehicle battery to be tested may be a power battery of any electric vehicle. The first indicator data may include indicator data of the vehicle battery to be tested at K moments, where K is a positive integer greater than 1. The indicator data includes data of indicators that affect the health status of the vehicle battery. Considering that evaluating the battery health status from only a single dimension cannot fully reflect the overall situation of the battery health status, the indicator data in the present disclosure may include indicators that affect the health status of the vehicle battery. m The data corresponding to each indicator are m is a positive integer greater than 1. For example, the indicators that affect the health status of the vehicle battery may include current, voltage, SOC, charging state, etc., and the indicator data of the vehicle battery to be tested at a moment may include the current value, voltage value, SOC value, temperature value, etc. of the vehicle battery to be tested at that moment, or indicators that characterize the consistency of battery voltage, temperature, etc., such as composite indicators such as battery cell voltage / voltage standard deviation.

[0031] Among them, the sensor set in the vehicle battery can detect various indicator data of the vehicle battery and send it to the electronic device through the vehicle's communication device. It should be noted that the various indicator data of the vehicle battery in this disclosure are collected and sent to the electronic device with the authorization of the vehicle user.

[0032] In step 12, a first status label and a second status label of the vehicle battery to be tested are determined according to the first indicator data.

[0033] The first status tag is used to characterize the frequency of abnormal health status of the vehicle battery, and the second status tag is used to characterize the degree of abnormal health status of the vehicle battery.

[0034] In step 13, the health status score of the vehicle battery to be tested is determined according to the first frequency interval corresponding to the first status tag and the first degree interval corresponding to the second status tag.

[0035] Among them, the first frequency interval is determined based on the first frequency information corresponding to each of the M first vehicle batteries that are pre-marked as the first status label, and the first frequency information is the frequency information of the abnormal health status of the first vehicle battery. The first degree interval is determined based on the first degree information corresponding to each of the N second vehicle batteries that are pre-marked as the second status label, and the first degree information is the degree information of the abnormal health status of the second vehicle battery. M is a positive integer greater than 1, and N is a positive integer greater than 1.

[0036] In the present disclosure, considering that some vehicles have a relatively high frequency of battery abnormalities but a low degree of abnormality each time, and some vehicles have a relatively low frequency of battery abnormalities but a high degree of abnormality each time, the health status of the battery is evaluated from two dimensions of abnormality frequency and abnormality degree, and the resulting health status score is more accurate.

[0037] Among them, different status tags for representing high and low abnormal frequencies may correspond to different frequency intervals. For example, a status tag for representing a low frequency of abnormal health status of a vehicle battery corresponds to a frequency interval [p 11 , p 12 ], p 11 is the lower limit of the frequency range, p 12 is the upper limit of the frequency range. For example, a status label used to characterize the abnormal health status of a vehicle battery with a high frequency corresponds to the frequency range [p 21 , p 22 ], p 21 is the lower limit of the frequency range, p 22 is the upper limit of the frequency range. Different status labels used to characterize the degree of abnormality can correspond to different degree ranges. For example, a status label used to characterize the low degree of abnormality in the health status of a vehicle battery corresponds to a degree range [r 11 , r 12 ],r 11 is the lower limit of the degree interval, r 12is the upper limit of the degree interval, for example, a state label used to indicate that the degree of abnormality of the health status of the vehicle battery is high, corresponding to the degree interval [r 21 , r 22 ],r 21 is the lower limit of the degree interval, r 22 It should be noted that the number and type of the above tags are only for explanation, and the present disclosure does not limit the classification and number of tags.

[0038] Through the above technical solution, the health status score of the vehicle battery to be tested can be determined according to the first frequency interval corresponding to the first status label and the first degree interval corresponding to the second status label. Among them, different status labels used to characterize the high and low abnormal frequencies can correspond to different frequency intervals. According to the first frequency information corresponding to each of the M first vehicle batteries, the first frequency interval corresponding to the first status label is determined, and the interval of accurate frequency information under the first status label can be obtained. Different status labels used to characterize the high and low abnormal degrees can correspond to different degree intervals. According to the first degree information corresponding to each of the N second vehicle batteries, the first degree interval corresponding to the second status label is determined, and the interval of accurate degree information under the second status label can be obtained. Therefore, an accurate health status score of the vehicle battery to be tested can be obtained based on the first frequency interval and the first degree interval. The health status score comprehensively considers the abnormal frequency and abnormal degree of the vehicle battery to be tested, and is more accurate, especially for vehicle batteries with relatively high abnormal frequency and low abnormal degree each time, and vehicle batteries with relatively low abnormal frequency but high abnormal degree each time. The health status of the battery can be evaluated from two dimensions of abnormal frequency and abnormal degree at the same time, and the obtained health status score is more accurate, and the vehicle battery health status can be scored and quantified, thereby accurately evaluating the battery health status.

[0039] Figure 2 is a flow chart of a vehicle battery health status assessment method according to an exemplary embodiment. Figure 2 As shown, step 12 may include steps 121 to 123 , and step 13 may include steps 131 to 133 .

[0040] In step 121 , second frequency information and second degree information of abnormal health status of the battery of the vehicle to be tested are determined according to the indicator data of the battery of the vehicle to be tested at K moments.

[0041] In one embodiment, the index data of the vehicle battery under test at K moments can be input into a battery abnormality prediction model to obtain the second frequency information and the second degree information output by the model, wherein the battery abnormality prediction model can be a neural network model trained using methods in related technologies.

[0042] In another embodiment, step 121 may be implemented as follows:

[0043] For each of the K moments, according to the transformation matrix and the index data of the battery of the vehicle to be tested at the moment, the first Hotelling statistic and the first square prediction error statistic corresponding to the moment are determined, and according to the first Hotelling statistic and the first square prediction error statistic, the first abnormality degree information of the battery of the vehicle to be tested at the moment is determined, wherein the transformation matrix is ​​obtained by performing principal component analysis on the index data of the battery of the vehicle whose state label represents normality;

[0044] If there is first abnormality degree information greater than the abnormality degree threshold, the ratio of the number of first abnormality degree information greater than the abnormality degree threshold to K is used as the second frequency information, and the second degree information is determined based on the first abnormality degree information greater than the abnormality degree threshold.

[0045] The first Hotelling statistic can be determined by the following formula (1): , the first square prediction error statistic is determined by the following formula (2): , the first abnormality degree information is determined by the following formula (3):

[0046] (1)

[0047] (2)

[0048] (3)

[0049] in, The matrix represents the index data of the vehicle battery under test at time t1, for example, the index data includes the factors affecting the health status of the vehicle battery. m The data corresponding to each indicator can be a row m The matrix of columns, t1∈[1,K], represents the transformation matrix, is a diagonal matrix of eigenvalues, I represents the identity matrix, represents the squared prediction error statistic threshold, represents the Hotelling statistic threshold. Indicates the first abnormality level information of the vehicle battery under test at time t1.

[0050] In this way, each of the K moments corresponds to the first abnormality degree information, and the first abnormality degree information corresponding to each moment can be compared with the abnormality degree threshold. If the first abnormality degree information corresponding to a certain moment is greater than the abnormality degree threshold, it can be characterized that the health status of the battery of the vehicle to be tested at that moment is abnormal. Figure 3 is a schematic diagram showing first abnormality degree information corresponding to different moments according to an exemplary embodiment. Figure 3 As shown, there are 255 moments in total, wherein the comprehensive index refers to the first abnormality degree information, and the threshold line represents the abnormality degree threshold. Figure 3 In the schematic diagram shown, the number of first abnormality degree information greater than the abnormality degree threshold is 5, and the ratio of 5 to 255 can be used as the second frequency information. The first abnormality degree information greater than the abnormality degree threshold is 5.99, 9.05, 10.99, 14.35 and 14.69 respectively. For example, one of the mean, standard deviation and median of the first abnormality degree information greater than the abnormality degree threshold can be used as the second degree information, which is not limited in the present disclosure.

[0051] In step 122, a first status tag of the vehicle battery to be tested is determined according to the second frequency information.

[0052] In step 123, a second status tag of the vehicle battery to be tested is determined according to the second degree information.

[0053] For example, multiple status tags representing the frequency of abnormality can be preset, and the corresponding first status tag can be determined according to the correspondence between the frequency information and the status tag and the second frequency information. Multiple status tags representing the degree of abnormality can be preset, and the corresponding second status tag can be determined according to the correspondence between the degree information and the status tag and the second degree information.

[0054] In step 131, a first score is determined according to the second frequency information, the upper limit value and the lower limit value of the first frequency interval, and the upper limit value and the lower limit value of the first preset score interval corresponding to the first state tag.

[0055] For example, there are w state labels representing abnormal frequencies, and the abnormal frequencies represented by the first to the wth state labels increase in sequence. The first state label representing abnormal frequencies corresponds to a frequency interval P1=[p 11 , p 12 ] and preset scoring interval [s 11 ,s 12 ], the second state label representing the abnormal frequency corresponds to the frequency interval P2=[p 21 , p 22 ] and preset scoring interval [s 21 ,s 22], the wth state label representing the abnormal frequency corresponds to the frequency interval P w =[p w1 , p w2 ] and preset scoring interval [s w1 ,s w2 The preset scoring intervals corresponding to the w status labels representing the abnormal frequency can be preset, for example, the preset scoring interval [s 11 ,s 12 ] is set to [90, 100].

[0056] For example, the second frequency information is p i , the first state tag of the vehicle battery to be tested corresponds to the first frequency interval P j =[p j1 , p j2 ] and the first preset scoring interval [s j1 ,s j2 ], then the first score S i It can be calculated by the following formula (4):

[0057] (4)

[0058] Among them, s j1 is the lower limit of the first preset scoring interval, s j2 is the upper limit of the first preset scoring interval, p j1 The first frequency interval P j The lower limit of p j2 The first frequency interval P j The upper limit value of .

[0059] In step 132, a second score is determined according to the second degree information, the upper limit value and the lower limit value of the first degree interval, and the upper limit value and the lower limit value of the second preset score interval corresponding to the second state label.

[0060] For example, there are f state labels representing the degree of abnormality, and the degree of abnormality represented by the first to the fth state labels increases in sequence. f and w can be the same or different. The first state label representing the degree of abnormality corresponds to the degree interval D1=[d 11 , d 12 ] and the preset scoring interval [c 11 , c 12 ], the second state label representing the degree of abnormality corresponds to the degree interval D2=[d 21 , d 22 ] and the preset scoring interval [c 21 , c 22 ], the fth state label representing the degree of abnormality corresponds to the degree interval and preset scoring intervals The preset scoring intervals corresponding to the f status labels representing the degree of abnormality can be preset, for example, the preset scoring interval [c 11 , c 12 ] is set to [95, 100].

[0061] For example, the second degree information is d i The second state label of the battery of the vehicle to be tested corresponds to the first degree interval D j =[d j1 , d j2 ] and the second preset scoring interval [c j1 , c j2 ], then the second score R i It can be calculated by the following formula (5):

[0062] (5)

[0063] Among them, c j1 is the lower limit of the second preset scoring interval, c j2 is the upper limit of the second preset scoring interval, d j1 The first degree interval D j The lower limit of d j2 The first degree interval D j The upper limit value of .

[0064] In step 133, a weighted value of the first score and the second score is used as a health status score of the battery of the vehicle to be tested.

[0065] For example, the health status score G of the battery of the vehicle to be tested can be calculated by the following formula (6): i :

[0066] (6)

[0067] Among them, h1 is the weight of the first score.

[0068] Through the above technical scheme, a first score reflecting the abnormal frequency of the battery of the vehicle to be tested can be determined according to the second frequency information, the upper and lower limits of the first frequency interval, and the upper and lower limits of the first preset scoring interval corresponding to the first status label. A second score reflecting the abnormal degree of the battery of the vehicle to be tested can be determined according to the second degree information, the upper and lower limits of the first degree interval, and the upper and lower limits of the second preset scoring interval corresponding to the second status label. The weighted value of the first score and the second score is used as the health status score of the battery of the vehicle to be tested. The health status of the vehicle battery can be scored and quantified from two dimensions of abnormal frequency and abnormal degree at the same time, which can more accurately reflect the health status of the battery.

[0069] Figure 4 is a flowchart of a method for determining a first frequency interval according to an exemplary embodiment. Figure 4 As shown, the method includes steps 41 to 43.

[0070] In step 41 , second indicator data of each of the M first vehicle batteries is obtained.

[0071] The second indicator data of the i-th first vehicle battery includes the i-th first vehicle battery at T i The indicator data at each moment, i∈[1,M], T i is a positive integer greater than 1.

[0072] In step 42 , for each first vehicle battery, first frequency information corresponding to the first vehicle battery is determined according to the second indicator data of the first vehicle battery.

[0073] The first frequency information corresponding to the i-th first vehicle battery is determined in the following manner:

[0074] For T i At each of the moments, according to the transformation matrix and the index data of the first vehicle battery at the moment, determine the second Hotelling statistic and the second square prediction error statistic corresponding to the moment, and determine the second abnormality degree information of the first vehicle battery at the moment according to the second Hotelling statistic and the second square prediction error statistic;

[0075] If there is second abnormality level information greater than the abnormality level threshold, the number of second abnormality level information greater than the abnormality level threshold is added to T i as the first frequency information corresponding to the i-th first vehicle battery.

[0076] The second Hotelling statistic can be determined by the following formula (7): , the first square prediction error statistic is determined by the following formula (8): , the second abnormality degree information is determined by the following formula (9):

[0077] (7)

[0078] (8)

[0079] (9)

[0080] in, A matrix representing the index data of the first vehicle battery at time t2, for example, the index data includes the indicators affecting the health status of the vehicle battery. m The data corresponding to each indicator can be a rowm Column matrix, t2∈[1,T i ], Indicates second abnormality degree information of the first vehicle battery at time t2.

[0081] In step 43, the minimum value among the M first frequency information is used as the lower limit value of the frequency interval, and the maximum value among the M first frequency information is used as the upper limit value of the frequency interval, so as to obtain the first frequency interval.

[0082] Through the above scheme, the first frequency interval corresponding to the first state label is determined according to the first frequency information corresponding to each of the M first vehicle batteries, and the accurate frequency information interval under the first state label can be obtained, thereby ensuring the accuracy of the health status score obtained according to the first frequency interval.

[0083] Figure 5 is a flowchart of a method for determining a first degree interval according to an exemplary embodiment. Figure 5 As shown, the method includes steps 51 to 53.

[0084] In step 51 , third indicator data of each of N second vehicle batteries is obtained.

[0085] The third indicator data of the j-th second vehicle battery includes the j-th second vehicle battery at V j The indicator data at each moment, j∈[1,N], V j is a positive integer greater than 1.

[0086] In step 52 , for each second vehicle battery, first level information corresponding to the second vehicle battery is determined according to the third indicator data of the second vehicle battery.

[0087] The first degree information corresponding to the j-th second vehicle battery is determined in the following manner:

[0088] For V j At each moment in time, according to the transformation matrix and the indicator data of the second vehicle battery at the moment, determine the third Hotelling statistic and the third square prediction error statistic corresponding to the moment, and determine the third abnormality degree information of the second vehicle battery at the moment according to the third Hotelling statistic and the third square prediction error statistic;

[0089] If there is third abnormality degree information greater than the abnormality degree threshold, the first degree information corresponding to the j-th second vehicle battery is determined according to the third abnormality degree information greater than the abnormality degree threshold.

[0090] Among them, the third Hotelling statistic can be determined by the following formula (10): , the first square prediction error statistic is determined by the following formula (11): , the second abnormality degree information is determined by the following formula (12):

[0091] (10)

[0092] (11)

[0093] (12)

[0094] in, The matrix represents the index data of the second vehicle battery at time t3, for example, the index data includes the indicators that affect the health status of the vehicle battery. m The data corresponding to each indicator can be a row m The matrix of columns, t3∈[1,V j ], Indicates the third abnormality level information of the second vehicle battery at time t3. For example, one of the mean, standard deviation, and median of the third abnormality level information greater than the abnormality level threshold can be determined as the first level information corresponding to the jth second vehicle battery.

[0095] In step 53, the minimum value among the N first degree information is used as the lower limit value of the degree interval, and the maximum value among the N first degree information is used as the upper limit value of the degree interval, so as to obtain the first degree interval.

[0096] Through the above technical solution, the first degree interval corresponding to the second status label is determined according to the first degree information corresponding to each of the N second vehicle batteries, and the accurate degree information interval under the second status label can be obtained, thereby ensuring the accuracy of the health status score obtained according to the first degree interval.

[0097] For example, M and N may be the same or different, and the first vehicle battery and the second vehicle battery may be the same or different. In one embodiment, the number of status tags representing the high and low abnormality frequencies is the same as the number of status tags representing the high and low abnormality degrees. For example, three status tags representing the high, medium, and low abnormality frequencies are set, and three status tags representing the high, medium, and low abnormality degrees are set. The vehicle battery to be tested is labeled as having a low abnormality frequency and a low abnormality degree. For example, vehicle battery 1 is labeled as having a low abnormality frequency and a low abnormality degree. Then vehicle battery 1 can be used as both the first vehicle battery and the second vehicle battery.

[0098] In the present disclosure, the abnormality threshold may be a preset value, or a threshold determined in the following manner:

[0099] Acquiring fourth indicator data of a third vehicle battery;

[0100] Perform principal component analysis on the fourth indicator data to obtain the number of principal components k and k The transformation matrix composed of the eigenvectors of the principal components is k is a positive integer, k < m ;

[0101] According to the number of principal components k , determine the Hotelling statistic threshold, and according to the number of principal components k and number of indicators m , determine the threshold of the squared prediction error statistic;

[0102] Determine a fourth Hotelling statistic and a fourth squared prediction error statistic according to the fourth indicator data and the transformation matrix;

[0103] An abnormality level threshold is determined according to the fourth Hotelling statistic, the fourth square prediction error statistic, the Hotelling statistic threshold, and the square prediction error statistic threshold.

[0104] The third vehicle battery includes a vehicle battery with a normal status tag. For example, a vehicle battery with an abnormal frequency represented by a marked status tag lower than a frequency threshold and an abnormal degree represented by a marked status tag lower than a degree threshold can be regarded as a vehicle battery with a normal status tag. For example, the third vehicle battery may include Q vehicle batteries with normal status tags, where Q is a positive integer. The fourth indicator data of the e-th vehicle battery may include the e-th vehicle battery in U e The indicator data at each moment, e∈[1, Q], includes the indicators that affect the health status of the vehicle battery. m The data corresponding to each indicator, the matrix consisting of the fourth indicator data of the e-th vehicle battery X e Can be:

[0105]

[0106] Among them, the matrix X e for U e OK m A matrix of columns, x 11 represents the data of the first indicator of the e-th vehicle battery at the first moment, x 12 represents the data of the second indicator of the e-th vehicle battery at the first moment, x 1m represents the battery of the e-th vehicle at the first moment. mdata of indicators, x 21 represents the data of the first indicator of the e-th vehicle battery at the second moment, x 22 represents the data of the second indicator of the e-th vehicle battery at the second moment, x 2m represents the battery of the e-th vehicle at the second moment. m data of indicators, Indicates that the e-th vehicle battery is in the U e The data of the first indicator at a certain moment, Indicates that the e-th vehicle battery is in the U e The data of the second indicator at a certain moment, Indicates that the e-th vehicle battery is in the U e The moment m data of indicators.

[0107] The matrices composed of the fourth indicator data corresponding to the Q vehicle batteries can be superimposed to obtain the matrix X ,Right now . Perform principal component analysis on the indicator data of normal vehicle batteries, that is, based on the matrix X Perform principal component analysis and find the matrix X The covariance matrix S of , matrix S is the covariance matrix, which can be expressed as , the matrix C is the matrix composed of the eigenvectors of the matrix S, is a diagonal matrix composed of the eigenvalues ​​of the matrix S. The eigenvector obtained by principal component analysis is ,in, is the eigenvector corresponding to the first indicator, is the eigenvector corresponding to the second indicator, For the m The characteristic vectors corresponding to the indicators can determine the number of principal components according to the cumulative contribution rate. k , and get the previous k The transformation matrix P composed of the eigenvectors of the principal components k For example, the fourth Hotelling statistic is determined by the following formula (13): , the Hotelling statistic threshold is determined by the following formula (14): :

[0108] (13)

[0109] (14)

[0110] in, n Representation Matrix X the number of rows, is the significance level, To obey the first degree of freedom k The second degree of freedom is n - k of F distributed.

[0111] For example, the fourth square prediction error statistic is determined by the following formula (15): SPE , the squared prediction error statistic threshold is determined by the following formula (16): :

[0112] (15)

[0113] (16)

[0114] in, , , , , represents the eigenvector corresponding to the jth index, represents the confidence interval of the standard normal distribution, .

[0115] For example, the abnormality threshold can be calculated by the following formula (17): :

[0116] (17)

[0117] in, , , , , abnormality threshold Obey probability distribution , the degrees of freedom are h The coefficient is The chi-square distribution of tr represents the trace of the matrix, T Represents the transpose of a matrix.

[0118] Through the above technical solution, the Hotelling statistic and the square prediction error statistic can be combined to calculate the abnormality threshold, so that the abnormality threshold accurately reflects the comprehensive index of the health status of a normal vehicle.

[0119] In the present disclosure, for the above-mentioned time quantities K, T i 、V j , U e There is no restriction on the value of , which can be the same or different.

[0120] Based on the same inventive concept, the present disclosure also provides a vehicle battery health status assessment device, Figure 6 is a block diagram of a vehicle battery health status evaluation device according to an exemplary embodiment. Figure 6 As shown, the device 60 may include:

[0121] A first acquisition module 61 is used to acquire first indicator data of a vehicle battery to be tested, wherein the indicator data includes data of indicators that affect the health status of the vehicle battery;

[0122] A first determination module 62 is used to determine a first state label and a second state label of the vehicle battery to be tested according to the first indicator data, wherein the first state label is used to characterize the frequency of abnormal health status of the vehicle battery, and the second state label is used to characterize the degree of abnormal health status of the vehicle battery;

[0123] The second determination module 63 is used to determine the health status score of the vehicle battery to be tested according to the first frequency interval corresponding to the first status label and the first degree interval corresponding to the second status label, wherein the first frequency interval is determined according to the first frequency information corresponding to M first vehicle batteries that are pre-labeled as the first status label, and the first frequency information is the frequency information of abnormal health status of the first vehicle battery; the first degree interval is determined according to the first degree information corresponding to N second vehicle batteries that are pre-labeled as the second status label, and the first degree information is the degree information of abnormal health status of the second vehicle battery; M is a positive integer greater than 1, and N is a positive integer greater than 1.

[0124] Optionally, the first indicator data includes indicator data of the battery of the vehicle to be tested at K moments respectively, where K is a positive integer greater than 1;

[0125] The first determining module 62 includes:

[0126] A first determination submodule is used to determine second frequency information and second degree information of abnormal health status of the battery of the vehicle to be tested according to the indicator data of the battery of the vehicle to be tested at K moments respectively;

[0127] A first label determination submodule, used to determine a first state label of the vehicle battery to be tested according to the second frequency information;

[0128] The second label determination submodule is used to determine the second status label of the vehicle battery to be tested according to the second degree information.

[0129] Optionally, the second determining module 63 includes:

[0130] a first score determination submodule, configured to determine a first score according to the second frequency information, an upper limit value and a lower limit value of the first frequency interval, and an upper limit value and a lower limit value of a first preset score interval corresponding to the first state tag;

[0131] A second score determination submodule, configured to determine a second score according to the second degree information, the upper limit value and the lower limit value of the first degree interval, and the upper limit value and the lower limit value of the second preset score interval corresponding to the second state tag;

[0132] The second determination submodule is used to use the weighted value of the first score and the second score as the health status score of the battery of the vehicle to be tested.

[0133] Optionally, the first determining submodule includes:

[0134] A third determination submodule is used to determine, for each of the K moments, a first Hotelling statistic and a first square prediction error statistic corresponding to the moment according to a transformation matrix and the indicator data of the vehicle battery to be tested at the moment, and determine first abnormality degree information of the vehicle battery to be tested at the moment according to the first Hotelling statistic and the first square prediction error statistic, wherein the transformation matrix is ​​obtained by performing principal component analysis on the indicator data of the vehicle battery whose state label represents normal;

[0135] The fourth determination submodule is used to, if there is the first abnormality degree information greater than the abnormality degree threshold, use the ratio of the number of the first abnormality degree information greater than the abnormality degree threshold to K as the second frequency information, and determine the second degree information based on the first abnormality degree information greater than the abnormality degree threshold.

[0136] Optionally, the first frequency interval is determined by the following module:

[0137] The second acquisition module is used to acquire second indicator data of each of the M first vehicle batteries, wherein the second indicator data of the i-th first vehicle battery includes the second indicator data of the i-th first vehicle battery at T i The indicator data at each moment, i∈[1,M], T i is a positive integer greater than 1;

[0138] a third determining module, configured to determine, for each of the first vehicle batteries, the first frequency information corresponding to the first vehicle battery according to the second indicator data of the first vehicle battery;

[0139] a fourth determination module, configured to use a minimum value among the M first frequency information as a lower limit value of the first frequency interval, and use a maximum value among the M first frequency information as an upper limit value of the first frequency interval, to obtain the first frequency interval;

[0140] The first frequency information corresponding to the i-th first vehicle battery is determined by the third determination module in the following manner:

[0141] For T i At each moment in time, according to the transformation matrix and the indicator data of the first vehicle battery at the moment, determine the second Hotelling statistic and the second square prediction error statistic corresponding to the moment, and according to the second Hotelling statistic and the second square prediction error statistic, determine the second abnormality degree information of the first vehicle battery at the moment, wherein the transformation matrix is ​​obtained by performing principal component analysis on the indicator data of the vehicle battery with a normal state label;

[0142] If there is the second abnormality level information greater than the abnormality level threshold, the number of the second abnormality level information greater than the abnormality level threshold is added to T i as the first frequency information corresponding to the i-th first vehicle battery.

[0143] Optionally, the first degree interval is determined by the following modules:

[0144] The third acquisition module is used to acquire third indicator data of each of the N second vehicle batteries, wherein the third indicator data of the j-th second vehicle battery includes the third indicator data of the j-th second vehicle battery at V j The indicator data at each moment, j∈[1,N], V j is a positive integer greater than 1;

[0145] a fifth determining module, configured to determine, for each of the second vehicle batteries, the first degree information corresponding to the second vehicle battery according to the third indicator data of the second vehicle battery;

[0146] a sixth determination module, configured to use the minimum value among the N first degree information as the lower limit value of the first degree interval, and use the maximum value among the N first degree information as the upper limit value of the first degree interval, to obtain the first degree interval;

[0147] The first degree information corresponding to the j-th second vehicle battery is determined by the fifth determination module in the following manner:

[0148] For V jAt each of the moments, according to the transformation matrix and the indicator data of the second vehicle battery at the moment, a third Hotelling statistic and a third square prediction error statistic corresponding to the moment are determined, and according to the third Hotelling statistic and the third square prediction error statistic, third abnormality degree information of the second vehicle battery at the moment is determined, wherein the transformation matrix is ​​obtained by performing principal component analysis on the indicator data of the vehicle battery whose state label represents normality;

[0149] If the third abnormality degree information greater than the abnormality degree threshold exists, the first degree information corresponding to the j-th second vehicle battery is determined according to the third abnormality degree information greater than the abnormality degree threshold.

[0150] Optionally, the transformation matrix and the abnormality threshold are determined by the following modules:

[0151] The fourth acquisition module is used to acquire fourth indicator data of a third vehicle battery, wherein the third vehicle battery includes a status tag indicating a normal vehicle battery, and the indicator data includes a status tag affecting the health status of the vehicle battery. m The data corresponding to each indicator are m is a positive integer greater than 1;

[0152] An analysis module is used to perform principal component analysis on the fourth indicator data to obtain the transformation matrix consisting of the number of principal components k and the eigenvectors of k principal components, k is a positive integer, k < m ;

[0153] The first threshold determination module is used to determine the number of principal components according to the k , determine the Hotelling statistic threshold, and according to the number of principal components k and number of indicators m , determine the threshold of the squared prediction error statistic;

[0154] A statistics determination module, used for determining a fourth Hotelling statistic and a fourth square prediction error statistic according to the fourth indicator data and the transformation matrix;

[0155] The second threshold determination module is used to determine the abnormality degree threshold according to the fourth Hotelling statistic, the fourth square prediction error statistic, the Hotelling statistic threshold and the square prediction error statistic threshold.

[0156] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0157] Figure 7 FIG. 7 is a block diagram of an electronic device 700 according to an exemplary embodiment. Figure 7 As shown, the electronic device 700 may include: a processor 701 , a memory 702 . The electronic device 700 may also include one or more of a multimedia component 703 , an input / output (I / O) interface 704 , and a communication component 705 .

[0158] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned vehicle battery health status assessment method. The memory 702 is used to store various types of data to support the operation of the electronic device 700. For example, these data may include instructions for any application or method used to operate on the electronic device 700, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the above-mentioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module.

[0159] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned vehicle battery health status assessment method.

[0160] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the vehicle battery health status assessment method described above are implemented. For example, the computer-readable storage medium may be the memory 702 including the program instructions, and the program instructions may be executed by the processor 701 of the electronic device 700 to complete the vehicle battery health status assessment method described above.

[0161] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program that can be executed by a processor. When the computer program is executed by the processor, the steps of the above-mentioned vehicle battery health status assessment method are implemented.

[0162] Figure 8 1 is a block diagram of an electronic device 1900 according to an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. Figure 8 The electronic device 1900 includes a processor 1922, which may be one or more, and a memory 1932 for storing a computer program executable by the processor 1922. The computer program stored in the memory 1932 may include one or more modules each corresponding to a set of instructions. In addition, the processor 1922 may be configured to execute the computer program to perform the above-mentioned vehicle battery health status assessment method.

[0163] In addition, the electronic device 1900 may further include a power supply component 1926 and a communication component 1950, wherein the power supply component 1926 may be configured to perform power management of the electronic device 1900, and the communication component 1950 may be configured to implement communication of the electronic device 1900, for example, wired or wireless communication. In addition, the electronic device 1900 may further include an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, etc.

[0164] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the vehicle battery health status assessment method described above are implemented. For example, the computer-readable storage medium may be the memory 1932 including the program instructions, and the program instructions may be executed by the processor 1922 of the electronic device 1900 to complete the vehicle battery health status assessment method described above.

[0165] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program that can be executed by a processor. When the computer program is executed by the processor, the steps of the above-mentioned vehicle battery health status assessment method are implemented.

[0166] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0167] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0168] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A vehicle battery health status assessment method, characterized in that: The method comprises: Acquire first indicator data of a vehicle battery to be tested, wherein the indicator data includes data of an indicator that affects a health status of the vehicle battery; Determine a first status label and a second status label of the vehicle battery to be tested according to the first indicator data, wherein the first status label is used to characterize the frequency of abnormal health status of the vehicle battery, and the second status label is used to characterize the degree of abnormal health status of the vehicle battery; The health status score of the vehicle battery to be tested is determined according to the first frequency interval corresponding to the first status label and the first degree interval corresponding to the second status label, wherein the first frequency interval is determined according to the first frequency information corresponding to each of the M first vehicle batteries pre-labeled as the first status label, and the first frequency information is the frequency information of abnormal health status of the first vehicle battery; the first degree interval is determined according to the first degree information corresponding to each of the N second vehicle batteries pre-labeled as the second status label, and the first degree information is the degree information of abnormal health status of the second vehicle battery; M is a positive integer greater than 1, and N is a positive integer greater than 1.

2. The method according to claim 1, characterized in that The first indicator data includes indicator data of the battery of the vehicle to be tested at K moments respectively, where K is a positive integer greater than 1; Determining the first status label and the second status label of the vehicle battery to be tested according to the first indicator data includes: Determine second frequency information and second degree information of abnormal health status of the battery of the vehicle to be tested according to the indicator data of the battery of the vehicle to be tested at K moments respectively; Determine a first status tag of the vehicle battery to be tested according to the second frequency information; A second status label of the vehicle battery to be tested is determined according to the second level information.

3. The method according to claim 2, characterized in that The step of determining the health status score of the battery of the vehicle to be tested according to the first frequency interval corresponding to the first status tag and the first degree interval corresponding to the second status tag includes: Determine a first score according to the second frequency information, the upper limit value and the lower limit value of the first frequency interval, and the upper limit value and the lower limit value of the first preset score interval corresponding to the first state tag; Determine a second score according to the second degree information, the upper limit value and the lower limit value of the first degree interval, and the upper limit value and the lower limit value of the second preset score interval corresponding to the second state label; A weighted value of the first score and the second score is used as a health status score of the battery of the vehicle to be tested.

4. The method according to claim 2, characterized in that: The determining, according to the indicator data of the vehicle battery under test at K moments, second frequency information and second degree information of abnormal health status of the vehicle battery under test includes: For each of the K moments, according to the transformation matrix and the indicator data of the vehicle battery to be tested at the moment, determine the first Hotelling statistic and the first square prediction error statistic corresponding to the moment, and according to the first Hotelling statistic and the first square prediction error statistic, determine the first abnormality degree information of the vehicle battery to be tested at the moment, wherein the transformation matrix is ​​obtained by performing principal component analysis on the indicator data of the vehicle battery whose state label represents normal; If there is the first abnormality degree information greater than the abnormality degree threshold, the ratio of the number of the first abnormality degree information greater than the abnormality degree threshold to K is used as the second frequency information, and the second degree information is determined based on the first abnormality degree information greater than the abnormality degree threshold.

5. The method according to claim 1, characterized in that The first frequency interval is determined by: Obtain the second indicator data of each of the M first vehicle batteries, wherein the second indicator data of the i-th first vehicle battery includes the second indicator data of the i-th first vehicle battery at T i The indicator data at each moment, i∈[1,M], T i is a positive integer greater than 1; For each of the first vehicle batteries, determining the first frequency information corresponding to the first vehicle battery according to the second indicator data of the first vehicle battery; Taking the minimum value among the M first frequency information as the lower limit value of the first frequency interval, and taking the maximum value among the M first frequency information as the upper limit value of the first frequency interval, to obtain the first frequency interval; The first frequency information corresponding to the i-th first vehicle battery is determined in the following manner: For T i At each moment in time, according to the transformation matrix and the indicator data of the first vehicle battery at the moment, determine the second Hotelling statistic and the second square prediction error statistic corresponding to the moment, and according to the second Hotelling statistic and the second square prediction error statistic, determine the second abnormality degree information of the first vehicle battery at the moment, wherein the transformation matrix is ​​obtained by performing principal component analysis on the indicator data of the vehicle battery with a normal state label; If there is the second abnormality level information greater than the abnormality level threshold, the number of the second abnormality level information greater than the abnormality level threshold is added to T i as the first frequency information corresponding to the i-th first vehicle battery.

6. The method according to claim 1, characterized in that The first degree interval is determined by: Obtain the third indicator data of each of the N second vehicle batteries, wherein the third indicator data of the j-th second vehicle battery includes the third indicator data of the j-th second vehicle battery at V j The indicator data at each moment, j∈[1,N], V j is a positive integer greater than 1; For each of the second vehicle batteries, determining the first level information corresponding to the second vehicle battery according to the third indicator data of the second vehicle battery; Taking the minimum value among the N first degree information as the lower limit value of the first degree interval, and taking the maximum value among the N first degree information as the upper limit value of the first degree interval, to obtain the first degree interval; The first degree information corresponding to the j-th second vehicle battery is determined in the following manner: For V j At each of the moments, according to the transformation matrix and the indicator data of the second vehicle battery at the moment, a third Hotelling statistic and a third square prediction error statistic corresponding to the moment are determined, and according to the third Hotelling statistic and the third square prediction error statistic, third abnormality degree information of the second vehicle battery at the moment is determined, wherein the transformation matrix is ​​obtained by performing principal component analysis on the indicator data of the vehicle battery whose state label represents normality; If the third abnormality degree information greater than the abnormality degree threshold exists, the first degree information corresponding to the j-th second vehicle battery is determined based on the third abnormality degree information greater than the abnormality degree threshold.

7. The method according to any one of claims 4 to 6, characterized in that: The transformation matrix and the abnormality threshold are determined in the following manner: Acquire fourth indicator data of a third vehicle battery, wherein the third vehicle battery includes a status tag indicating a normal vehicle battery, and the indicator data includes a parameter affecting the health status of the vehicle battery. m The data corresponding to each indicator are m is a positive integer greater than 1; Perform principal component analysis on the fourth indicator data to obtain the number of principal components k and k The transformation matrix is ​​composed of the eigenvectors of the principal components, k is a positive integer, k < m ; According to the number of principal components k , determine the Hotelling statistic threshold, and according to the number of principal components k and number of indicators m , determine the threshold of the squared prediction error statistic; Determine a fourth Hotelling statistic and a fourth square prediction error statistic according to the fourth indicator data and the transformation matrix; The abnormality level threshold is determined according to the fourth Hotelling statistic, the fourth square prediction error statistic, the Hotelling statistic threshold and the square prediction error statistic threshold.

8. A vehicle battery health status assessment device, characterized in that: The device comprises: A first acquisition module is used to acquire first indicator data of a vehicle battery to be tested, wherein the indicator data includes data of an indicator that affects a health status of the vehicle battery; A first determination module is used to determine a first status label and a second status label of the vehicle battery to be tested according to the first indicator data, wherein the first status label is used to characterize the frequency of abnormal health status of the vehicle battery, and the second status label is used to characterize the degree of abnormal health status of the vehicle battery; A second determination module is used to determine the health status score of the vehicle battery to be tested according to a first frequency interval corresponding to the first status label and a first degree interval corresponding to the second status label, wherein the first frequency interval is determined according to the first frequency information corresponding to each of M first vehicle batteries pre-labeled as the first status label, and the first frequency information is the frequency information of abnormal health status of the first vehicle battery; the first degree interval is determined according to the first degree information corresponding to each of N second vehicle batteries pre-labeled as the second status label, and the first degree information is the degree information of abnormal health status of the second vehicle battery; M is a positive integer greater than 1, and N is a positive integer greater than 1.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.

Images