Battery evaluation method and device, storage medium and electronic equipment

Abstract

The invention discloses a battery evaluation method and device, a storage medium and electronic equipment. An initial data set of a target battery is acquired, a quantized value corresponding to each characteristic factor in each working condition is acquired according to the initial data set, and a first intermediate result of each working condition is determined according to the quantized value corresponding to each characteristic factor in each working condition; the first intermediate result is used for representing the sum of the quantized values corresponding to the feature factors, forgetting the first intermediate result to obtain a second intermediate result corresponding to each working condition, and determining an accumulation identifier according to the first intermediate result and a predetermined threshold, and determining an evaluation result of the target battery according to the second intermediate result and the accumulated identifier. Therefore, the comprehensiveness of battery detection and the reliability of a battery evaluation result can be improved.

Description

Technical Field

[0001] The present invention relates to the field of battery technology, and in particular to a battery evaluation method, device, storage medium and electronic equipment. Background Art

[0002] With the rapid development of technology and people's increasing dependence on electronic devices, batteries, as the core energy supply components of these devices, have become increasingly important. For example, batteries play a vital role in mobile phones, laptops, electric vehicles, and other devices. However, battery performance and safety are directly related to the normal operation of devices and the vital interests of users. Therefore, battery status monitoring has a significant impact on battery usage.

[0003] Currently, battery status detection generally only targets a single specific feature, the battery detection perception is not comprehensive, and the detection results are unreliable. Summary of the Invention

[0004] In view of this, an object of the embodiments of the present invention is to provide a battery evaluation method, apparatus, storage medium, and electronic device, which can improve the comprehensiveness of battery detection and the reliability of battery evaluation results.

[0005] In a first aspect, an embodiment of the present invention provides a battery evaluation method, the method comprising:

[0006] Obtain the initial data set of the target battery;

[0007] Obtaining the quantitative value corresponding to each characteristic factor in each working condition according to the initial data set;

[0008] Determine a first intermediate result for each operating condition according to the quantized value corresponding to each characteristic factor in each operating condition;

[0009] Performing forgetting processing on the first intermediate results to obtain second intermediate results corresponding to each working condition;

[0010] determining a cumulative indicator according to the first intermediate result and a predetermined threshold;

[0011] An evaluation result of the target battery is determined according to the second intermediate result and the cumulative identifier.

[0012] In some embodiments, obtaining the quantitative value corresponding to each characteristic factor in each working condition according to the initial data set includes:

[0013] Acquire initial data corresponding to each characteristic factor in each working condition in the initial data set;

[0014] The initial data is quantized based on at least one of normalization, binarization, and item discretization to obtain the quantized value.

[0015] In some embodiments, the first intermediate result of each operating condition is determined according to the quantized value corresponding to each characteristic factor in each operating condition:

[0016] The sum of the quantized values ​​corresponding to the characteristic factors within the target operating condition is calculated to obtain a first intermediate result corresponding to the target operating condition.

[0017] In some embodiments, performing forgetting processing on the first intermediate result to obtain the second intermediate result corresponding to each working condition includes:

[0018] Determine the forgetting parameters corresponding to each working condition;

[0019] The product of the forgetting parameter corresponding to the target operating condition and the first intermediate result is determined as the second intermediate result.

[0020] In some embodiments, the forgetting parameter is calculated using the following formula:

[0021]

[0022] Among them, e1 is the forgetting parameter of the working condition on the current date, e k is the forgetting parameter of the working condition from the current date to k-1 days ago, and b is the preset forgetting factor.

[0023] In some embodiments, determining the cumulative indicator according to the first intermediate result and a predetermined threshold comprises:

[0024] Determining the predetermined threshold value based on the date, model, and region of the target battery;

[0025] In response to the first intermediate result being greater than or equal to the predetermined threshold, determining the cumulative flag to be a first value;

[0026] In response to the first intermediate result being smaller than the predetermined threshold, the cumulative flag is determined to be a second value.

[0027] In some embodiments, determining the evaluation result of the target battery according to the second intermediate result and the accumulated identifier includes:

[0028] Extracting a second intermediate result corresponding to the operating condition whose cumulative identifier is the first value;

[0029] Calculate the subtraction value corresponding to the working condition whose cumulative identifier is the second value;

[0030] The evaluation result is determined according to the second intermediate result corresponding to the working condition whose cumulative identification is the first value and the subtraction value corresponding to the working condition whose cumulative identification is the second value.

[0031] In some embodiments, calculating the subtraction value corresponding to the operating condition whose cumulative identifier is the second value includes:

[0032] The subtraction value is determined as a product of a predetermined reference parameter and a forgetting parameter corresponding to the working condition.

[0033] In some embodiments, determining the evaluation result based on the second intermediate result corresponding to the operating condition with the cumulative identification of the first value and the subtraction value corresponding to the operating condition with the cumulative identification of the second value includes:

[0034] Accumulating the second intermediate results corresponding to the working condition whose cumulative identifier is the first value to obtain a third intermediate result;

[0035] determining an adjustment value according to the subtraction value corresponding to the working condition whose cumulative identifier is the second value;

[0036] The evaluation result is obtained by subtracting the adjustment value from the third intermediate result.

[0037] In some embodiments, determining the adjustment value according to the subtraction value corresponding to the operating condition whose cumulative identifier is the second value includes:

[0038] Determine the subtraction value corresponding to the working condition in which the cumulative mark indicates that the second value is discontinuous as the adjustment value;

[0039] The subtraction value corresponding to the last operating condition among the operating conditions whose cumulative identifications are continuous second values ​​is determined as the adjustment value.

[0040] In some embodiments, subtracting the adjustment value from the third intermediate result to obtain the evaluation result includes:

[0041] Subtracting the adjustment value from the third intermediate result to obtain an initial evaluation result;

[0042] In response to the initial evaluation result being greater than or equal to an upper limit value, taking the upper limit value as an evaluation result;

[0043] In response to the initial evaluation result being greater than a lower limit value and less than an upper limit value, taking the initial evaluation result as an evaluation result;

[0044] In response to the initial evaluation result being less than or equal to a lower limit value, the lower limit value is used as the evaluation result.

[0045] In some embodiments, the characteristic factors include one or more of temperature difference change trend, health status, capacity attenuation change trend, single working condition temperature rise, expansion force, and system extreme difference.

[0046] In a second aspect, an embodiment of the present invention provides a battery evaluation device, the device comprising:

[0047] An initial data set acquisition unit, used to acquire an initial data set of a target battery;

[0048] A quantization value acquisition unit, configured to acquire a quantization value corresponding to each characteristic factor in each working condition according to the initial data set;

[0049] A first intermediate result obtaining unit, configured to determine a first intermediate result for each operating condition according to the quantized value corresponding to each characteristic factor in each operating condition;

[0050] a second intermediate result obtaining unit, configured to perform forgetting processing on the first intermediate result to obtain a second intermediate result corresponding to each working condition;

[0051] a cumulative flag determining unit, configured to determine a cumulative flag according to the first intermediate result and a predetermined threshold;

[0052] An evaluation result determining unit is configured to determine an evaluation result of the target battery according to the second intermediate result and the cumulative identifier.

[0053] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in the first aspect.

[0054] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer program instructions, which implement the method described in the first aspect when executed by a processor.

[0055] The technical solution of the embodiment of the present invention obtains an initial data set for the target battery, obtains the quantized values ​​corresponding to each characteristic factor within each operating condition based on the initial data set, determines a first intermediate result for each operating condition based on the quantized values ​​corresponding to each characteristic factor within each operating condition, and performs forgetting processing on the first intermediate result to obtain a second intermediate result corresponding to each operating condition. A cumulative flag is determined based on the first intermediate result and a predetermined threshold, and an evaluation result of the target battery is determined based on the second intermediate result and the cumulative flag. This improves the comprehensiveness of battery testing and the reliability of battery evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0057] Figure 1 is a flow chart of a battery evaluation method according to an embodiment of the present invention;

[0058] Figure 2 is a flow chart of obtaining a quantized value according to an embodiment of the present invention;

[0059] Figure 3 is a schematic diagram of quantized values ​​of characteristic factors according to an embodiment of the present invention;

[0060] Figure 4 is a flowchart of obtaining a second intermediate result according to an embodiment of the present invention;

[0061] Figure 5 is a flow chart of determining a cumulative identifier according to an embodiment of the present invention;

[0062] Figure 6 is a schematic diagram of a parameter matrix of an embodiment of the present invention;

[0063] Figure 7 is a flow chart of determining an evaluation result according to an embodiment of the present invention;

[0064] Figure 8 is a flowchart of determining an evaluation result according to another embodiment of the present invention;

[0065] Figure 9 is a schematic diagram of adjustment values ​​according to an embodiment of the present invention;

[0066] Figure 10 is a schematic diagram of a battery evaluation device according to an embodiment of the present invention;

[0067] Figure 11 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The present invention is described below based on the following embodiments, but the present invention is not limited to these embodiments. In the detailed description of the present invention below, certain specific details are described in detail. Those skilled in the art can fully understand the present invention without these details. To avoid obscuring the essence of the present invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0069] Furthermore, persons of ordinary skill in the art will appreciate that the figures provided herein are for illustration purposes only and are not necessarily drawn to scale.

[0070] Unless the context clearly requires otherwise, words like "include," "comprising," and the like throughout this application should be construed as including, rather than exclusive or exhaustive; that is, as meaning "including but not limited to."

[0071] In the description of the present invention, it should be understood that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood to indicate or imply relative importance. In addition, in the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0072] Battery status monitoring has a significant impact on battery performance. Currently, battery status monitoring typically focuses on a single, specific characteristic, resulting in incomplete detection and unreliable results. Currently, by characterizing specific parameters such as temperature, voltage range, and voltage consistency, and through deep data mining based on laboratory testing and ideal operating conditions, a high level of identification capability has been achieved for single, specific failures, enabling characterization of battery safety status in certain scenarios. Machine learning and neural network methods are also being used for model training, offering a viable real-time path for research and academic research under specific ideal conditions. However, these approaches all present several challenges, primarily the following: Due to the complex design and production of battery systems, the numerous components, and the diverse external environments and operating conditions during vehicle use, the causes of battery safety issues are complex, with significant temporal and spatial uncertainty in the evolution of potential hazards. Furthermore, challenges exist, such as insufficient battery anomaly characterization parameters, low transmission granularity, and poor data quality. Consequently, single anomalies present incomplete battery system status, unreliable risk quantification, and limited model robustness.

[0073] The battery system is a non-mature standard part, among which the battery cells, BMS, thermal management system, high and low voltage electrical components, etc. all have greatly differentiated designs based on different vehicle models. The corresponding component failure modes, abnormal evolution patterns, system protection and management capabilities, etc. cannot be regarded as the same, and the corresponding feature data do not have universality among different vehicle models and battery systems; in addition, the usage behavior of the customer groups corresponding to the same vehicle model varies greatly, resulting in great uncertainty in the safe evolution of the same failure mode on the time scale, and great difficulty in risk quantification; finally, since thermal runaway accidents are low-probability events, there is a serious shortage of applicable negative samples; in summary, due to the low commonality of feature data, insufficient negative samples and strong coupling operating conditions, the model trained by machine learning has inherent deficiencies and usage limitations in battery risk quantification.

[0074] Therefore, the present invention adopts an integrated modeling approach. First, the risk of characteristic factors is quantified in factor dimensions, and the segmented battery system usage conditions are used as the basic carrier for fusion. The risk value distribution under a specific "vehicle type-time-space domain" is used for threshold calculation. At the same time, the "single vehicle" analysis dimension and long-time scale specific constraints are focused on, and a risk accumulation strategy with a forgetting factor is used to realize the comprehensive perception and evaluation of the battery system status in a long-time domain, multi-dimensional, and multi-layer factor manner, which has high engineering practicality.

[0075] Figure 1 FIG. 1 is a flow chart of a battery evaluation method according to an embodiment of the present invention. Figure 1 As shown, the battery evaluation method according to the embodiment of the present invention includes the following steps:

[0076] Step S100: Acquire an initial data set of a target battery.

[0077] In this embodiment, the battery evaluation method can be implemented by various devices with data processing capabilities. The embodiment of the present invention is illustrated by taking server execution as an example. The initial data set of the target battery is the status information of the target battery over a period of history. Taking the evaluation of the power battery of an on-board battery as an example, the working status of the battery is collected in real time through the existing battery detection system on the vehicle or by installing a new battery detection system on the vehicle. The working status of the battery includes parameters such as temperature, battery power, working current, working voltage, charging current, charging voltage, internal pressure of the battery, and health status of the battery. These collected parameters are used as the initial data set. The target battery is the battery that needs to be evaluated.

[0078] It should be understood that the embodiments of the present invention are described using a vehicle-mounted power battery as an example, but the embodiments of the present invention do not limit the battery type. Batteries of other electronic devices are also applicable to the technical solutions of the embodiments of the present invention, for example, batteries of electronic devices such as mobile phones, laptops, and tablet computers.

[0079] Step S200: obtaining the quantitative value corresponding to each characteristic factor in each working condition according to the initial data set.

[0080] Specifically, Figure 2 This is a flow chart of obtaining quantization values ​​according to an embodiment of the present invention. Figure 2 As shown, obtaining the quantitative value corresponding to each characteristic factor in each working condition according to the initial data set includes the following steps:

[0081] Step S210: obtaining initial data corresponding to each characteristic factor in each working condition from the initial data set.

[0082] In this embodiment, expert experience and the results of retrospective analysis of thermal runaway accident samples are used to extract data corresponding to characteristic factors associated with battery safety from the battery big data feature library as initial data, and the input feature set FEATURE_SET of this integrated model is generated based on the initial data. The characteristic factors include temperature difference change trend z_tempdiff, health state (SOH, state of health), capacity attenuation change trend z_qdiff, single working condition temperature rise temp_rise, expansion force exp_threshold, system extreme difference v_diff, etc. The time range of information extracted from the initial data set can be data within a historical period. For example, it can be an interval of 60 days forward for calculating the dt of the current day. Focus on the strength of the correlation between each characteristic factor and battery safety, the certainty of time domain evolution, the accuracy of characteristic information, and the robustness of feature production.

[0083] Step S220 : performing quantization processing on the initial data based on at least one of normalization processing, binarization processing, and item discretization processing to obtain the quantization value.

[0084] In this embodiment, in order to facilitate calculation, risk quantification is performed on the characteristic factors in the feature set FEATURE_SET to obtain the quantified value corresponding to each characteristic factor in each working condition.

[0085] The quantization algorithm can be implemented based on at least one of normalization, binarization, and item discretization, thereby quantizing each characteristic factor into a numerical value.

[0086] Figure 3 Schematic diagram of the quantized value of the characteristic factor according to an embodiment of the present invention. Figure 3 As shown, the embodiment of the present invention divides the initial data according to the operating conditions, that is, the initial data is divided into multiple sub-data, each sub-data corresponds to one operating condition, wherein one operating condition can be a discharging operating condition, a charging operating condition, etc. Assuming that a vehicle is charged twice and used once on a certain day, there are three operating conditions in total on that day. Assuming that the initial data obtained is the interval of 60 days before the calculation of the dt on the day, all the operating conditions in the interval are obtained, and the initial data is divided according to the public to obtain sub-data, each sub-data corresponds to one operating condition. Figure 3 The quantified values ​​of the characteristic factors corresponding to the i-th working condition are shown. Figure 3 In the embodiment shown, there are n characteristic factors, which are temperature difference change trend, health status, capacity attenuation change trend, single working condition temperature rise, expansion force, ..., system extreme difference. For the i-th working condition, the quantitative value of each characteristic factor is C i,1 、C i,2 、C i,3 、Ci,4 、C i,5 ,……,C i,n .

[0087] In this way, the quantitative value corresponding to each characteristic factor in each working condition can be obtained.

[0088] Step S300: Determine a first intermediate result for each operating condition according to the quantized value corresponding to each characteristic factor in each operating condition.

[0089] In this embodiment, the first intermediate result is used to represent the sum of the quantized values ​​corresponding to each characteristic factor, that is, the sum of the quantized values ​​corresponding to each characteristic factor in the target operating condition is calculated to obtain the first intermediate result corresponding to the target operating condition.

[0090] Specifically, the working conditions are marked according to the time sequence, and the characteristic factors corresponding to the single working condition are summed to obtain the first intermediate result corresponding to each working condition. The calculation formula of the first intermediate result is:

[0091]

[0092] Among them, rs i Indicates the first intermediate result corresponding to the i-th working condition, C i,j It represents the quantitative value of the jth characteristic factor in the i-th working condition, and n is the total number of characteristic factors.

[0093] Thus, the first intermediate results of each working condition can be obtained, and then the first intermediate result data set of a single working condition can be obtained, that is, [rs1, rs2, rs3, rs4, ..., rs m ]. m is the total number of working conditions.

[0094] Step S400: performing forgetting processing on the first intermediate result to obtain a second intermediate result corresponding to each working condition.

[0095] In this embodiment, considering that different time scales have different relevance and coupling to the current state, the first intermediate result is forgotten to obtain the second intermediate result corresponding to each working condition, so as to improve the accuracy of the evaluation.

[0096] Specifically, Figure 4 This is a flow chart of obtaining the second intermediate result according to an embodiment of the present invention. Figure 4 As shown, performing forgetting processing on the first intermediate result to obtain the second intermediate result corresponding to each working condition includes the following steps:

[0097] Step S410: Determine the forgetting parameters corresponding to each working condition.

[0098] The forgetting parameter is calculated using the following formula:

[0099]

[0100] Among them, e1 is the forgetting parameter of the working condition on the current date, e k is the forgetting parameter of the working condition of k-1 days forward from the current date, b is the preset forgetting factor, 1<k≤D, k is a positive integer, and D is the total number of dates.

[0101] That is to say, when calculating the forgetting parameter of a certain working condition, the date of the working condition is first determined, and then the forgetting parameter is determined based on the date.

[0102] Step S420: Determine the product of the forgetting parameter corresponding to the target operating condition and the first intermediate result as the second intermediate result.

[0103] The calculation formula of the second intermediate result is:

[0104] rs' i =rs i *e k

[0105] Among them, the date of the i-th working condition is k days ahead from the current date, e k is the forgetting parameter of the working condition of k-1 days forward from the current date, rs i is the first intermediate result of the i-th working condition, rs' i is the second intermediate result of the i-th working condition, i is a positive integer, 1≤i≤m, and m is the total number of working conditions.

[0106] Therefore, in the embodiment of the present invention, the exponential moving weighted method is used to process the time series factor risk quantification value, wherein the forgetting factor is b, and the forgetting parameter is calculated based on the forgetting time scale to obtain the second intermediate result.

[0107] Step S500: Determine a cumulative flag according to the first intermediate result and a predetermined threshold.

[0108] In this embodiment, the cumulative identifier includes a first value and a second value. To facilitate calculation, the embodiment of the present invention sets the first value to 1 and the second value to 0.

[0109] Figure 5 This is a flow chart of determining the cumulative identifier according to an embodiment of the present invention. Figure 5 As shown, determining the cumulative indicator according to the first intermediate result and a predetermined threshold includes the following steps:

[0110] Step S510: Determine the predetermined threshold value according to the date, vehicle model, and region of the target battery.

[0111] In this embodiment, when calculating the predetermined threshold, the model, region, and operating date of the target battery are used as aggregation factors to perform Z-score statistical distribution to obtain the predetermined threshold.

[0112] Specifically, other batteries identical to the target battery are selected based on the target battery's vehicle model, region, and operating date, parameters of these batteries are obtained, a first intermediate result is calculated for each battery, and the predetermined threshold is determined based on the first intermediate results of all batteries. The details are as follows:

[0113]

[0114] Among them, rs is the variable of the first intermediate result, rs ave is the average value of the first intermediate results of all batteries, and s is the standard deviation of the first intermediate results of all batteries.

[0115] A predetermined threshold G1 is determined based on the Z distribution obtained above.

[0116] Step S520: In response to the first intermediate result being greater than or equal to the predetermined threshold, determine that the cumulative identifier is a first value.

[0117] Step S530: In response to the first intermediate result being smaller than the predetermined threshold, determining that the cumulative flag is a second value.

[0118] The first value is 1, and the second value is 0. That is, by judging whether the first intermediate result is less than the predetermined threshold of the single-operating-condition spatiotemporal dynamic risk, if so, the cumulative flag is determined to be 0; if so, the cumulative flag is determined to be 1.

[0119] The calculation formula of the cumulative mark is:

[0120]

[0121] Wherein, G1 is a predetermined threshold, rs is a first intermediate result, and rst is a cumulative flag.

[0122] Figure 6 Schematic diagram of the parameter matrix of the embodiment of the present invention. Figure 6 As shown, the parameter matrix includes date, interval days, working condition sorting, characteristic factor, cumulative identification, second intermediate result, etc. t To calculate today's date; d t-k is the date corresponding to k days forward from the current date; the interval number of days is the date of the historical working condition and d t The number of days between dates; the working conditions are sorted as [d t-k , d tThe time interval operating conditions are arranged in positive order. Characteristic factors include temperature difference change trend Zt, health status Zq, capacity attenuation change trend Et, etc.

[0123] exist Figure 6 There are k+1 dates and m working conditions. There may be multiple working conditions in one date. For example, the first working condition and the second working condition are both on date d. t-k middle.

[0124] Step S600: Determine an evaluation result of the target battery according to the second intermediate result and the cumulative identifier.

[0125] Figure 7 FIG. 1 is a flow chart of determining the evaluation result according to an embodiment of the present invention. Figure 7 As shown, determining the evaluation result of the target battery according to the second intermediate result and the cumulative identifier includes the following steps:

[0126] Step S610: extract the second intermediate result corresponding to the working condition with the cumulative identification being the first value.

[0127] In this embodiment, the operating condition with the cumulative identification being the first value is obtained, and the corresponding second intermediate result is extracted.

[0128] Step S620: Calculate the subtraction value corresponding to the working condition with the cumulative identification as the second value.

[0129] In this embodiment, the product of the predetermined reference parameter and the forgetting parameter corresponding to the working condition is determined as the write-down value. The forgetting parameter corresponding to the working condition is calculated by the following formula:

[0130]

[0131] Among them, e1 is the current date d t The forgetting parameter of the working condition, e k is the forgetting parameter of the working condition from the current date forward k-1 days, and b is the preset forgetting factor.

[0132] The calculation formula for the write-down value is as follows:

[0133] redh=ah×e k

[0134] Among them, redh is the write-down value of the hth operating condition in the continuous operating conditions whose cumulative mark is the second value, e k is the forgetting parameter of the date of the hth working condition in the continuous working conditions whose cumulative identification is the second value, and a is a preset benchmark parameter.

[0135] Step S630: Determine the evaluation result according to the second intermediate result corresponding to the working condition with the cumulative identification of the first value and the subtraction value corresponding to the working condition with the cumulative identification of the second value.

[0136] Figure 8 FIG. 1 is a flow chart of determining an evaluation result according to another embodiment of the present invention. Figure 8 As shown, determining the evaluation result according to the second intermediate result corresponding to the working condition with the first cumulative value and the subtraction value corresponding to the working condition with the second cumulative value includes the following steps:

[0137] Step S631: Accumulate the second intermediate results corresponding to the working condition with the cumulative identifier as the first value to obtain a third intermediate result.

[0138] In this embodiment, the second intermediate results corresponding to all the working conditions whose cumulative identification is the first value are obtained, and the second intermediate results corresponding to the working conditions whose cumulative identification is the first value are accumulated to obtain the third intermediate result.

[0139] Step S632: Determine an adjustment value according to the subtraction value corresponding to the working condition whose cumulative identifier is the second value.

[0140] In this embodiment, the subtraction value corresponding to the working condition with the cumulative mark of discontinuous second values ​​is determined as the adjustment value, and the subtraction value corresponding to the last working condition among the working conditions with the cumulative mark of continuous second values ​​is determined as the adjustment value.

[0141] Step S633: Subtract the adjustment value from the third intermediate result to obtain the evaluation result.

[0142] In this embodiment, the difference between the third intermediate result and the adjustment value is obtained as the evaluation result.

[0143] Figure 9 2 is a schematic diagram of adjustment values ​​according to an embodiment of the present invention. Figure 9 The figure shows the order of the m working conditions, the cumulative identifier rst, the second intermediate result rs', the continuous value h, and the adjustment value red'. The continuous value h indicates that the cumulative identifier of the consecutive working conditions is the hth working condition in the second value.

[0144] like Figure 9 As shown, there are m working conditions in total, among which the cumulative identification rst of the first to third working conditions is 1, the cumulative identification rst of the fourth to fifth working conditions is 0, the cumulative identification rst of the sixth working condition is 1, and the cumulative identification rst of the seventh to mth working conditions is 0.

[0145] Through the above steps, the second intermediate results corresponding to the working conditions with the cumulative identification as the first value are accumulated to obtain the third intermediate result: the cumulative identification of the first to third working conditions and the sixth working condition is 1, so the third intermediate result is: rs1'+rs2'+rs3'+rs6'.

[0146] The adjustment value is determined according to the subtraction value corresponding to the working condition with the cumulative mark of the second value: Figure 9 In the figure, there are two consecutive cases where the cumulative identification of multiple working conditions is the second value. The first case is the fourth and fifth consecutive working conditions, and the cumulative identification rst of these two consecutive working conditions is 0. The second case is the seventh and m-6 consecutive working conditions, and the cumulative identification rst of these two consecutive working conditions is 0. For the first consecutive case, the subtraction value corresponding to the last working condition is the subtraction value of the fifth working condition. Since the fifth working condition is ranked second in this consecutive case, the subtraction value of the fifth working condition is red2'. For the second consecutive case, the subtraction value corresponding to the last working condition is the subtraction value of the m-th working condition. Since the m-th working condition is ranked m-6 in this consecutive case, the subtraction value of the m-th working condition is red m-6 '.

[0147] Therefore, the evaluation result is rs1'+rs2'+rs3'+rs6'-red2'-red m-6 '.

[0148] It should be understood that the above is only one calculation method provided by the embodiment of the present invention, and the embodiment of the present invention does not limit the specific technical method. For example, the evaluation results can also be calculated by the following method:

[0149] Sorting by working conditions, starting from the first working condition, the rst corresponding to the first working condition is 1, so the calculation result is its own second intermediate result, that is, sum1=rs1'.

[0150] The second working condition corresponds to rst=1, so the calculation result is the cumulative sum of the calculation result of the previous working condition and its own second intermediate result rs2', that is, sum2=sum1+rs2'.

[0151] The third working condition corresponds to rst=1, so the calculation result is the cumulative sum of the calculation result of the previous working condition and its own second intermediate result rs3', that is, sum3=sum2+rs3'.

[0152] The fourth operating condition corresponds to rst=0, which triggers the write-down logic. Therefore, the calculation result is the difference between the calculation result of the previous operating condition with a cumulative mark of 1 and its own write-down value. Since the fourth operating condition is the first operating condition with a cumulative mark of 0, its corresponding write-down value is red1'. Therefore, the calculation result sum4=sum3-red1'.

[0153] The fifth operating condition corresponds to rst=0, which triggers the write-down logic. Therefore, the calculation result is the difference between the calculation result of the previous operating condition with a cumulative identification of 1 and its own write-down value. Since the fifth operating condition is the second operating condition with a cumulative identification of 0, its corresponding write-down value is red2', and the calculation result of the previous operating condition with a cumulative identification of 1 is sum3. Therefore, the calculation result sum5=sum3-red2'.

[0154] The rst corresponding to the sixth working condition is 1, which triggers the accumulation logic. Therefore, the calculation result is the sum of the calculation result of the last working condition in the continuous working condition with the cumulative mark of 0 and its own second intermediate result. Since the last working condition in the continuous working condition with the cumulative mark of 0 is the fifth working condition, the calculation result sum6=sum5+rs6'.

[0155] The rst corresponding to the seventh operating condition is 0, which triggers the deduction logic. Therefore, the calculation result is the difference between the calculation result of the previous operating condition with a cumulative identification of 1 and its own deduction value. Since the previous operating condition with a cumulative identification of 1 is the sixth operating condition, and the seventh operating condition is the first operating condition in the continuous operating conditions with a cumulative identification of 0 this time, its own deduction value is red1'. Therefore, the calculation result sum7 = sum6-red1'.

[0156] Similarly, the calculation result sum of the m-1th working condition is m-1 =sum6-red m-7 '.

[0157] The calculation result sum of the mth working condition m =sum6-red m-6 '.

[0158] From the above we can know:

[0159] sum6=sum5+rs6'=sum3-red2'+rs6'=sum2+rs3'-red2'+rs6'=sum1+rs2'+rs3'-red2'+rs6'=rs1'+rs2'+rs3'-red2'+rs6'.

[0160] Therefore, sum m =sum6-red m-6'=rs1'+rs2'+rs3'-red2'+rs6'-red m-6 '.

[0161] The evaluation results are consistent with those obtained by the first method mentioned above.

[0162] In some embodiments, subtracting the adjustment value from the third intermediate result to obtain the evaluation result comprises the following steps:

[0163] Step S6331: Subtract the adjustment value from the third intermediate result to obtain an initial evaluation result.

[0164] Step S6332: In response to the initial evaluation result being greater than or equal to an upper limit value, use the upper limit value as the evaluation result.

[0165] Step S6333: In response to the initial evaluation result being greater than a lower limit value and less than an upper limit value, the initial evaluation result is used as the evaluation result.

[0166] Step S6334: In response to the initial evaluation result being less than or equal to a lower limit value, use the lower limit value as the evaluation result.

[0167] Furthermore, in order to avoid the risk accumulation value continuing to increase, resulting in untimely deduction response when the subsequent RST continues to be 0, and also to avoid excessive deduction and untimely response to cumulative representation during the deduction process, which in turn leads to a serious "hysteresis effect" defect in the model, the upper and lower limits of the accumulation are constrained as follows:

[0168]

[0169] Among them, SA is the evaluation result, E up is the upper limit, E lower is the lower limit, E up and E lower is a preset value, sum m This is the initial assessment result.

[0170] Therefore, through the above long-term multi-factor fusion calculation, the assessment results of the latest battery system safety status corresponding to the model calculation are obtained, which are highly representative, can realize battery system status assessment and risk warning, and support the implementation of on-demand inspection, repair and maintenance and other security measures.

[0171] The embodiment of the present invention obtains an initial data set for a target battery, obtains quantized values ​​corresponding to each characteristic factor within each operating condition based on the initial data set, determines a first intermediate result for each operating condition based on the quantized values ​​corresponding to each characteristic factor within each operating condition, and performs forgetting processing on the first intermediate result to obtain a second intermediate result corresponding to each operating condition. A cumulative flag is determined based on the first intermediate result and a predetermined threshold, and an evaluation result for the target battery is determined based on the second intermediate result and the cumulative flag. This improves the comprehensiveness of battery testing and the reliability of battery evaluation results.

[0172] Figure 10 FIG is a schematic diagram of a battery evaluation device according to an embodiment of the present invention. Figure 10 As shown, the battery evaluation device of an embodiment of the present invention includes an initial dataset acquisition unit 101, a quantization value acquisition unit 102, a first intermediate result acquisition unit 103, a second intermediate result acquisition unit 104, a cumulative identification determination unit 105, and an evaluation result determination unit 106. The initial dataset acquisition unit 101 is used to acquire an initial dataset for a target battery. The quantization value acquisition unit 102 is used to acquire quantization values ​​corresponding to each characteristic factor within each operating condition based on the initial dataset. The first intermediate result acquisition unit 103 is used to determine a first intermediate result for each operating condition based on the quantization values ​​corresponding to each characteristic factor within each operating condition. The second intermediate result acquisition unit 104 is used to perform forgetting processing on the first intermediate result to obtain a second intermediate result corresponding to each operating condition. The cumulative identification determination unit 105 is used to determine a cumulative identification based on the first intermediate result and a predetermined threshold. The evaluation result determination unit 106 is used to determine an evaluation result for the target battery based on the second intermediate result and the cumulative identification.

[0173] In some embodiments, the quantization value acquisition unit includes:

[0174] An initial data acquisition subunit, configured to acquire initial data corresponding to each characteristic factor in each working condition from the initial data set;

[0175] The quantization subunit is configured to perform quantization processing on the initial data based on at least one of normalization processing, binarization processing, and item discretization processing to obtain the quantization value.

[0176] In some embodiments, the first intermediate result obtaining unit is specifically configured to:

[0177] The sum of the quantized values ​​corresponding to the characteristic factors within the target operating condition is calculated to obtain a first intermediate result corresponding to the target operating condition.

[0178] In some embodiments, the second intermediate result obtaining unit includes:

[0179] A forgetting parameter acquisition subunit is used to determine the forgetting parameters corresponding to each working condition;

[0180] The second intermediate result subunit is used to determine the product of the forgetting parameter corresponding to the target working condition and the first intermediate result as the second intermediate result.

[0181] In some embodiments, the forgetting parameter is calculated using the following formula:

[0182]

[0183] Among them, e1 is the forgetting parameter of the working condition on the current date, e k is the forgetting parameter of the working condition from the current date to k-1 days ago, and b is the preset forgetting factor.

[0184] In some embodiments, the cumulative identification determination unit includes:

[0185] a predetermined threshold value obtaining subunit, configured to determine the predetermined threshold value according to the date, vehicle model and region of the target battery;

[0186] a first flag determining subunit, configured to determine, in response to the first intermediate result being greater than or equal to the predetermined threshold, that the cumulative flag is a first value;

[0187] The second identifier determining subunit is configured to determine that the cumulative identifier is a second value in response to the first intermediate result being smaller than the predetermined threshold.

[0188] In some embodiments, the evaluation result determination unit includes:

[0189] A first calculation subunit is configured to extract a second intermediate result corresponding to the operating condition whose cumulative identifier is the first value;

[0190] A second calculation subunit is used to calculate the subtraction value corresponding to the working condition whose cumulative identification is a second value;

[0191] The third calculation subunit is used to determine the evaluation result according to the second intermediate result corresponding to the working condition with the cumulative identification of the first value and the subtraction value corresponding to the working condition with the cumulative identification of the second value.

[0192] In some embodiments, the second computing subunit is configured to:

[0193] The subtraction value is determined as a product of a predetermined reference parameter and a forgetting parameter corresponding to the working condition.

[0194] In some embodiments, the third computing subunit includes:

[0195] a third intermediate result determination module, configured to accumulate the second intermediate results corresponding to the working condition whose cumulative identifier is the first value to obtain a third intermediate result;

[0196] an adjustment value determination module, configured to determine an adjustment value according to a subtraction value corresponding to the operating condition whose cumulative identifier is a second value;

[0197] An evaluation result determination module is configured to obtain the evaluation result by subtracting the adjustment value from the third intermediate result.

[0198] In some embodiments, the adjustment value determination module includes:

[0199] A first determining submodule, configured to determine the subtraction value corresponding to the operating condition in which the cumulative mark indicates that the second value is discontinuous as the adjustment value;

[0200] The second determining submodule is configured to determine the subtracted value corresponding to the last operating condition in the operating conditions whose cumulative identifications are continuous second values ​​as the adjustment value.

[0201] In some embodiments, the evaluation result determination module includes:

[0202] an initial result acquisition submodule, configured to obtain an initial evaluation result by subtracting the adjustment value from the third intermediate result;

[0203] a first result determination submodule, configured to, in response to the initial evaluation result being greater than or equal to an upper limit value, use the upper limit value as an evaluation result;

[0204] a second result determination submodule, configured to, in response to the initial evaluation result being greater than a lower limit value and less than an upper limit value, use the initial evaluation result as an evaluation result;

[0205] The third result determination submodule is configured to, in response to the initial evaluation result being less than or equal to a lower limit value, use the lower limit value as the evaluation result.

[0206] In some embodiments, the characteristic factors include one or more of temperature difference change trend, health status, capacity attenuation change trend, single working condition temperature rise, expansion force, and system extreme difference.

[0207] The embodiment of the present invention obtains an initial data set for a target battery, obtains quantized values ​​corresponding to each characteristic factor within each operating condition based on the initial data set, determines a first intermediate result for each operating condition based on the quantized values ​​corresponding to each characteristic factor within each operating condition, and performs forgetting processing on the first intermediate result to obtain a second intermediate result corresponding to each operating condition. A cumulative flag is determined based on the first intermediate result and a predetermined threshold, and an evaluation result for the target battery is determined based on the second intermediate result and the cumulative flag. This improves the comprehensiveness of battery testing and the reliability of battery evaluation results.

[0208] Figure 11 is a schematic diagram of an electronic device according to an embodiment of the present invention. Figure 11 The electronic device shown is a general-purpose data processing device, which includes a general-purpose computer hardware structure, including at least a processor 111 and a memory 112. The processor 111 and the memory 112 are connected via a bus 113. The memory 112 is suitable for storing instructions or programs executable by the processor 111. The processor 111 can be a standalone microprocessor or a collection of one or more microprocessors. Thus, the processor 111 executes the instructions stored in the memory 112, thereby performing the method flow of the embodiment of the present invention described above to process data and control other devices. The bus 113 connects the above-mentioned multiple components together and also connects these components to the display controller 114 and the display device as well as the input / output (I / O) device 115. The input / output (I / O) device 115 can be a mouse, keyboard, modem, network interface, touch input device, somatosensory input device, printer, and other devices known in the art. Typically, the input / output device 115 is connected to the system via an input / output (I / O) controller 116.

[0209] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatuses (devices), or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0210] The present invention is described with reference to flowcharts of methods, apparatuses (devices), and computer program products according to embodiments of the present application. It should be understood that each process in the flowcharts can be implemented by computer program instructions.

[0211] These computer program instructions may be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device that implements the process Figure 1 A function specified in a process or multiple processes.

[0212] These computer program instructions can also be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce the instructions for implementing the process Figure 1 A device that specifies functions in a process or multiple processes.

[0213] Where the solutions described in this specification and examples involve the processing of personal information, such processing will be conducted with a legitimate basis (e.g., with the consent of the subject of personal information or as necessary for the performance of a contract) and only within the prescribed or agreed scope. A user's refusal to process personal information other than that required for basic functions will not affect the user's use of basic functions.

[0214] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A battery evaluation method, characterized in that: The method comprises: Obtain the initial data set of the target battery; Obtaining the quantitative value corresponding to each characteristic factor in each working condition according to the initial data set; Determine a first intermediate result for each operating condition according to the quantized value corresponding to each characteristic factor in each operating condition; Performing forgetting processing on the first intermediate results to obtain second intermediate results corresponding to each working condition; determining a cumulative indicator according to the first intermediate result and a predetermined threshold; An evaluation result of the target battery is determined according to the second intermediate result and the cumulative identifier.

2. The method according to claim 1, characterized in that The obtaining of the quantitative value corresponding to each characteristic factor in each working condition according to the initial data set includes: Acquire initial data corresponding to each characteristic factor in each working condition in the initial data set; The initial data is quantized based on at least one of normalization, binarization, and item discretization to obtain the quantized value.

3. The method according to claim 1, characterized in that The first intermediate result of each working condition is determined according to the quantized value corresponding to each characteristic factor in each working condition: The sum of the quantized values ​​corresponding to the characteristic factors within the target operating condition is calculated to obtain a first intermediate result corresponding to the target operating condition.

4. The method according to claim 1, wherein The forgetting process of the first intermediate result to obtain the second intermediate result corresponding to each working condition includes: Determine the forgetting parameters corresponding to each working condition; The product of the forgetting parameter corresponding to the target operating condition and the first intermediate result is determined as the second intermediate result.

5. The method according to claim 4, characterized in that The forgetting parameter is calculated by the following formula: Among them, e1 is the forgetting parameter of the working condition on the current date, e k is the forgetting parameter of the working condition from the current date to k-1 days ago, and b is the preset forgetting factor.

6. The method according to claim 5, characterized in that Determining the cumulative indicator according to the first intermediate result and a predetermined threshold includes: Determining the predetermined threshold value based on the date, model, and region of the target battery; In response to the first intermediate result being greater than or equal to the predetermined threshold, determining the cumulative flag to be a first value; In response to the first intermediate result being smaller than the predetermined threshold, the cumulative flag is determined to be a second value.

7. The method according to claim 6, characterized in that Determining the evaluation result of the target battery according to the second intermediate result and the accumulated identifier includes: Extracting a second intermediate result corresponding to the operating condition whose cumulative identifier is the first value; Calculate the subtraction value corresponding to the working condition whose cumulative identifier is the second value; The evaluation result is determined according to the second intermediate result corresponding to the working condition whose cumulative identification is the first value and the subtraction value corresponding to the working condition whose cumulative identification is the second value.

8. The method according to claim 7, characterized in that Calculating the deduction value corresponding to the working condition with the cumulative identification as the second value includes: The subtraction value is determined as a product of a predetermined reference parameter and a forgetting parameter corresponding to the working condition.

9. The method according to claim 7, characterized in that The determining of the evaluation result according to the second intermediate result corresponding to the operating condition with the first cumulative value and the subtraction value corresponding to the operating condition with the second cumulative value includes: Accumulating the second intermediate results corresponding to the working condition whose cumulative identifier is the first value to obtain a third intermediate result; determining an adjustment value according to the subtraction value corresponding to the working condition whose cumulative identifier is the second value; The evaluation result is obtained by subtracting the adjustment value from the third intermediate result.

10. The method according to claim 9, characterized in that The determining of the adjustment value according to the subtraction value corresponding to the working condition whose cumulative identifier is the second value includes: Determine the subtraction value corresponding to the working condition in which the cumulative mark indicates that the second value is discontinuous as the adjustment value; The subtraction value corresponding to the last operating condition among the operating conditions whose cumulative identifications are continuous second values ​​is determined as the adjustment value.

11. The method according to claim 9, characterized in that Subtracting the adjustment value from the third intermediate result to obtain the evaluation result includes: Subtracting the adjustment value from the third intermediate result to obtain an initial evaluation result; In response to the initial evaluation result being greater than or equal to an upper limit value, taking the upper limit value as an evaluation result; In response to the initial evaluation result being greater than a lower limit value and less than an upper limit value, taking the initial evaluation result as an evaluation result; In response to the initial evaluation result being less than or equal to a lower limit value, the lower limit value is used as the evaluation result.

12. The method according to claim 1, characterized in that The characteristic factors include one or more of temperature difference change trend, health status, capacity attenuation change trend, single working condition temperature rise, expansion force, and system extreme difference.

13. A battery evaluation device, characterized in that: The device comprises: An initial data set acquisition unit, used to acquire an initial data set of a target battery; a quantization value acquisition unit, configured to acquire a quantization value corresponding to each characteristic factor in each working condition according to the initial data set; A first intermediate result obtaining unit, configured to determine a first intermediate result for each operating condition according to the quantized value corresponding to each characteristic factor in each operating condition; a second intermediate result obtaining unit, configured to perform forgetting processing on the first intermediate result to obtain a second intermediate result corresponding to each working condition; a cumulative flag determining unit, configured to determine a cumulative flag according to the first intermediate result and a predetermined threshold; An evaluation result determining unit is configured to determine an evaluation result of the target battery according to the second intermediate result and the cumulative identifier.

14. An electronic device comprising a memory and a processor, characterized in that: The memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1 to 12.

15. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: The computer program instructions implement the method according to any one of claims 1 to 12 when executed by a processor.

Images