Lithium Battery Performance Score Calculation Method and System

Abstract

Disclosed are a method and a system for calculating a lithium battery performance score. The method includes: obtaining data information in the operation process of a lithium battery and uploading the data to a lithium battery performance score database; constructing a lithium battery performance score system from three dimensions of battery nameplate attributes, operation attributes, and environmental attributes using the lithium battery performance score database; and constructing a battery performance score calculation model using the fuzzy comprehensive evaluation method and calculating the performance index scores of each item of the lithium battery.

Description

Technical Field

[0001] This application is provided based on a Chinese patent application with an application number of 2022107257073 and an application date of June 24, 2022. The priority of the Chinese patent application is claimed, and all the contents of the Chinese patent application are incorporated herein by reference. The present disclosure relates to the field of energy storage, and more specifically, to a method and system for calculating the performance score of a lithium battery.

Background Art

[0002] With the further development of the energy storage industry, many new energy power generations such as wind energy and solar power generation choose to store electrical energy. Lithium batteries are widely used in energy storage because of their advantages such as high energy density, stable electrochemical properties, low pollution, and long cycle life, and at the same time, they promote the sustainable and rapid development of the economy. However, with the increase in the number of charge and discharge cycles of energy storage, lithium batteries gradually experience an irreversible aging phenomenon in performance, which directly affects aspects such as the practicality, economy, and safety of lithium batteries. Therefore, being able to accurately and quickly evaluate the real-time performance state of lithium batteries can not only improve the safety of related fields but also save a lot of funds and time for the energy storage field. Therefore, researching a method that can accurately evaluate the performance state of lithium batteries has important significance for its actual application.

[0003] Conventional methods for evaluating the performance state of lithium batteries have a large degree of fuzziness, one-sided evaluation indicators, the existence of human influence, and cannot accurately and comprehensively reflect the performance state of lithium batteries, and the persuasiveness of the evaluation results is poor.

Summary of the Invention

Problems to be Solved by the Invention

[0004] The lithium battery performance score calculation method and system provided by the present disclosure solve the problems that in at least related technologies, the fuzziness of the lithium battery performance state evaluation method is large, the evaluation indicators are one-sided, there are artificial influences, and the performance state of the lithium battery cannot be accurately and comprehensively reflected, and the persuasiveness of the evaluation result is poor.

Means for Solving the Problems

[0005] An embodiment of the first aspect of the present disclosure provides a lithium battery performance score calculation method, acquiring data information in the operation process of the lithium battery and uploading the data to the lithium battery performance score database; constructing a lithium battery performance score system from three dimensions of battery nameplate attributes, operation attributes, and environmental attributes using the lithium battery performance score database; constructing a battery performance score calculation model using the fuzzy comprehensive evaluation method.

[0006] An embodiment of the second aspect of the present disclosure provides a lithium battery performance score calculation system, an acquisition module that acquires data information in the operation process of the lithium battery and uploads the data to the lithium battery performance score database; a construction module that constructs a lithium battery performance score system from three dimensions of battery nameplate attributes, operation attributes, and environmental attributes using the lithium battery performance score database; a calculation module that constructs a battery performance score calculation model using the fuzzy comprehensive evaluation method and calculates the performance index scores of each item of the lithium battery.

[0007] An embodiment of the third aspect of the present disclosure provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable by the processor. When the processor executes the computer program, the lithium battery performance score calculation method of the first aspect of the present disclosure is realized.

[0008] An embodiment of the fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium storing a computer program, which, when executed by a processor, implements the lithium battery performance score calculation method according to the first aspect of the present disclosure.

[0009] An embodiment of the fifth aspect of the present disclosure provides a computer program product including a computer program, which, when executed by a processor, implements the lithium battery performance score calculation method described in the embodiment of the first aspect of the present disclosure.

[0010] An embodiment of the sixth aspect of the present disclosure provides a computer program including computer program code, which, when executed on a computer, causes the computer to execute the lithium battery performance score calculation method described in the embodiment of the first aspect of the present disclosure.

Advantages of the Invention

[0011] The technical solutions provided by the embodiments of the present disclosure have at least the following beneficial effects: The present disclosure provides a lithium battery performance score calculation method and system. The method includes: acquiring data information in the operation process of a lithium battery and uploading the data to a lithium battery performance score database; constructing a lithium battery performance score system from three dimensions of battery nameplate attributes, operation attributes, and environmental attributes using the lithium battery performance score database; and constructing a battery performance score calculation model using the fuzzy comprehensive evaluation method and calculating the performance index scores of each item of the lithium battery. The method realizes real-time, rapid, and accurate calculation of the performance of the lithium battery, thereby evaluating the performance state of the lithium battery, improving the maintenance and inspection efficiency of the lithium battery, and ensuring the safe and stable operation of the lithium battery.

[0012] Additional features and advantages of the present disclosure will be shown in part in the following description, become apparent in part from the description, or can be understood by the practice of the present invention.

Brief Description of the Drawings

[0013] The above-mentioned and / or additional features and advantages of the present disclosure will become apparent and be more easily understood from the description of the embodiments with reference to the following attached drawings.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Modes for Carrying Out the Invention

[0014] Hereinafter, embodiments of the present disclosure will be described in detail. Examples of this embodiment are shown in the drawings, and the same or similar reference numerals from beginning to end represent the same or similar elements, or elements having the same or similar functions. The embodiments described below with reference to the drawings are illustrative for explaining the present disclosure and should not be construed as a limitation of the present disclosure.

[0015] A lithium battery performance score calculation method and system provided by the present disclosure, the method includes: obtaining data information in the operation process of a lithium battery and uploading the data to a lithium battery performance score database; using the lithium battery performance score database to construct a lithium battery performance score system from three dimensions of battery nameplate attributes, operation attributes, and environmental attributes; constructing a battery performance score calculation model using the fuzzy comprehensive evaluation method and calculating the performance index scores of each item of the lithium battery, realizing the real-time, rapid, and accurate calculation of the performance of the lithium battery, evaluating the performance state of the lithium battery, improving the efficiency of lithium battery maintenance and inspection, and ensuring the safe and stable operation of the lithium battery.

[0016] Hereinafter, with reference to the drawings, a lithium battery performance score calculation method and system according to an embodiment of the present disclosure will be described.

[0017] Embodiment 1 FIG. 1 is a flowchart of a lithium battery performance score calculation method provided by an embodiment of the present disclosure. As shown in FIG. 1, the method includes steps 1-3.

[0018] Step 1: Obtain data information in the operation process of a lithium battery and upload the data to a lithium battery performance score database.

[0019] The data information in the operation process of the lithium battery includes lithium battery operation power, voltage, current, temperature, etc.

[0020] FIG. 2 is a specific flowchart of a lithium battery performance score calculation method provided by an embodiment of the present disclosure. As shown in FIG. 2, after uploading the data to the lithium battery performance score database, the method further includes performing a cleaning process on the lithium battery performance data in the lithium battery performance score database.

[0021] The step of performing a cleaning process on the lithium battery performance data in the lithium battery performance score database includes filling missing values, processing outliers, etc. Filling missing values means that when the number of missing values is 5 or more, the data for the current day is removed, and when the number of missing values is less than 5, the average value of the data for the previous and next 3 times is used for filling. Processing outliers means constructing an index outlier identification method for outliers by means of statistical analysis, box plot method, etc., and deleting or filling according to requirements.

[0022] Step 2: Use the lithium battery performance state evaluation to construct a lithium battery performance score system from three dimensions of battery nameplate attributes, operation attributes, and environmental attributes using the lithium battery performance score database.

[0023] In an embodiment of the present disclosure, before constructing a lithium battery performance score system from three dimensions of battery nameplate attributes, operation attributes, and environmental attributes using the lithium battery performance score database, it further includes the step of constructing lithium battery index characteristics related to the lithium battery. The method of constructing lithium battery index characteristics related to the lithium battery includes descriptive statistics, correlation analysis, data conversion, data encoding, binning, feature combination, etc.

[0024] Furthermore, the nameplate attributes include battery model number, battery capacity, battery shipping date, lot, manufacturer, and location, etc. The operation attributes include total operating power, total voltage, total current, maximum and minimum voltage, and maximum and minimum temperature, etc. The environmental attributes include external maximum and minimum temperature, maximum and minimum humidity, and meteorological data, etc.

[0025] Step 3: Use the fuzzy comprehensive evaluation method to construct a battery performance score calculation model.

[0026] Figure 3 is a schematic diagram of the principle of the fuzzy comprehensive evaluation model in the lithium battery performance score calculation method provided by an embodiment of the present disclosure. The steps of constructing a battery performance score calculation model using the fuzzy comprehensive evaluation method specifically include the following steps: F1: Classify the lithium battery performance score system into levels, and the classifications are battery cell level, module level, battery cluster level, and battery tank level.

[0027] It should be noted that the conventional performance evaluation of lithium batteries only focuses on the performance evaluation at the battery cell level. As an energy storage power plant, which is a huge power system, there is an integrated operation of a large number of battery cells. Therefore, the method of the present disclosure not only performs hierarchical evaluation on the battery cell level, but also conducts hierarchical evaluation on the upper-level module level, battery cluster level, and battery tank level, and comprehensively evaluates the overall performance of the energy storage power plant.

[0028] F2: Classify the characteristic indicators of each item of lithium batteries at different levels into different types of membership functions.

[0029] It should be noted that each single-item indicator of a lithium battery can be classified into different types of membership functions, and the membership functions include "parabolic type", "positive S type", and "linear type", etc.

[0030] F3: Put the characteristic indicators of each single-item lithium battery into the corresponding membership function to calculate the membership degree, and combine to obtain the single-element evaluation matrix A of lithium batteries at each level.

[0031] Furthermore, the calculation formula of the parabolic membership function is as follows:

Equation

[0032] Specifically, based on the membership function and the set index critical value, substitute the measured value of the index into the formula of the corresponding membership function to calculate the membership degree, that is, the calculated values of the parabolic membership function, the positive S-shaped membership function, and the linear membership function constitute a single-element evaluation matrix A, [Number] In the formula: A is a matrix of m rows and n columns, m is the number of lithium battery samples, n is the number of lithium battery indicators, μis the membership degree of the first feature of the first battery sample, μ 1n is the membership degree of the nth feature of the first battery sample, μ mn is the membership degree of the nth feature of the mth battery sample.

[0033] F4: Use the multiple linear regression method to calculate the weight coefficients of each item index feature of the lithium battery, and construct a weight coefficient matrix R by constructing the weight coefficients that affect the lithium battery performance.

[0034] F5: Using the fuzzy comprehensive evaluation method, multiply the single-element evaluation matrix by the transposed weight coefficient matrix to calculate the comprehensive evaluation index, construct a battery performance score calculation model, and calculate and obtain the scores of the performance indicators of each item of the lithium battery, so as to obtain the comprehensive score results of the performance indicators of each item of lithium batteries at different levels, and realize an accurate evaluation of the performance state of the lithium battery.

[0035] The steps of calculating the weight coefficient of each item index feature of the lithium battery using the multiple linear regression method, constructing a weight coefficient matrix R by composing the weight coefficients that affect the lithium battery performance, and using the fuzzy comprehensive evaluation method to multiply the single-element evaluation matrix by the transposed weight coefficient matrix to calculate the comprehensive evaluation index and construct a battery performance score calculation model specifically include the following steps: H1: The k-th index of the lithium battery

Number

Number

Number

Number

Number

Number

Number

Number

[0036] It should be noted that since the weight acquisition methods such as the analytic hierarchy process are affected by artificial factors, this method uses the multiple linear regression method to calculate the weight coefficients of lithium battery indicators. Its principle is to determine the indicator weights based on the strength of the collinearity between each indicator of the lithium battery and other indicators, and there is no influence of artificial factors

[0037] Calculate the weight coefficients of lithium battery indicators using the multiple linear regression method, and determine the weights of the indicators based on the strength of the collinearity between each indicator of the lithium battery and other indicators. That is, the larger the complex correlation coefficient Z between a certain indicator and other indicators, the stronger the collinear relationship between the said indicator and other indicators, the easier it is to be represented by a linear combination of other indicators, and the more duplicate information, the smaller the weight of the said indicator should be

[0038] In the embodiments of the present disclosure, the lithium battery performance score calculation method is Steps to classify the performance health status of lithium batteries based on evaluation results and divide them into four levels: healthy (excellent), sub-healthy (good), unhealthy (relatively bad), and severely unhealthy (bad), and Steps to draw a visualization interface for the performance status of lithium batteries, are further included.

[0039] The visualization interface includes the number of lithium battery devices, distribution topology, temperature, and performance status results, and is used to provide lithium battery non-health warnings to the operation inspection department.

[0040] Specifically, Table 1 shows the health status corresponding to the evaluation score. As shown in Table 1,

Table 1

[0041] It should be noted that for lithium batteries in a non-health state, further focus on dimensions such as the input age, load capacity ratio, and number of heavy overloads, perform score analysis from this dimension, incorporate the dimension with a low score into the equipment inspection scope, assist in fault positioning, and improve inspection efficiency.

[0042] Perform score analysis from the comprehensive evaluation results, incorporate those with low scores into the equipment inspection scope, assist in fault positioning, and improve inspection efficiency. Utilize big data technology to develop real-time monitoring warnings for the performance status of lithium batteries, enable comprehensive interaction between relevant staff and equipment, and realize holographic perception of the lithium battery status.

[0043] As described above, the embodiments of the present disclosure provide a method for calculating the lithium battery performance score. The method includes the steps of obtaining data information in the operation process of the lithium battery and uploading the data to the lithium battery performance score database; constructing a lithium battery performance score system from three dimensions of battery nameplate attributes, operation attributes, and environmental attributes using the lithium battery performance score database; constructing a battery performance score calculation model using the fuzzy comprehensive evaluation method and calculating the performance index scores of each item of the lithium battery. The method realizes the evaluation of the performance state of the lithium battery in real time, quickly, and accurately, improves the efficiency of lithium battery maintenance and inspection, ensures the safe and stable operation of the lithium battery, realizes the accurate evaluation of the lithium battery performance state, develops a lithium battery performance state visualization scene, and is used to intuitively display the real-time operation status of the lithium battery in the energy storage unit. The present disclosure can be used to assist in formulating the inspection plan strategy of the lithium battery and guiding autonomous repair.

[0044] Embodiment 2 FIG. 5 is a configuration diagram of a lithium battery performance score calculation system provided by an embodiment of the present disclosure. As shown in FIG. 5, the system includes an acquisition module 100, a construction module 200, and a calculation module 300. The acquisition module 100 obtains data information in the operation process of the lithium battery and uploads the data to the lithium battery performance score database. The construction module 200 constructs a lithium battery performance score system from three dimensions of battery nameplate attributes, operation attributes, and environmental attributes using the lithium battery performance score database. The calculation module 300 constructs a battery performance score calculation model using the fuzzy comprehensive evaluation method and calculates the performance index scores of each item of the lithium battery.

[0045] The system further includes a cleaning unit, which is used to perform cleaning processing on the lithium battery performance data uploaded to the lithium battery performance score database, specifically including filling missing values, processing abnormal values, etc.

[0046] As described above, according to the lithium battery performance score calculation system provided by the embodiments of the present disclosure, it is possible to realize real-time, rapid, and accurate calculation and evaluation of the performance state of lithium batteries.

[0047] Example 3 To implement the above embodiments, this embodiment further provides an electronic device.

[0048] The electronic device provided by this embodiment includes a memory, a processor, and a computer program stored in the memory and executable by the processor. When the processor executes the computer program, the lithium battery performance score calculation method of Example 1 is realized.

[0049] Example 4 To implement the above embodiments, this embodiment further provides a non-transitory computer-readable storage medium.

[0050] The non-transitory computer-readable storage medium storing the computer program provided by this embodiment realizes the lithium battery performance score calculation method of Example 1 when the computer program is executed by a processor.

[0051] Example 5 To implement the above embodiments, this embodiment further provides a computer program product.

[0052] The computer program product provided by this embodiment includes a computer program, and when the computer program is executed by a processor, the lithium battery performance score calculation method of Example 1 is realized.

[0053] Example 6 To implement the above embodiments, this embodiment further provides a computer program.

[0054] The computer program provided by this embodiment includes computer program code. When the computer program code is executed by a computer, the computer is caused to execute the lithium battery performance score calculation method of Embodiment 1.

[0055] It should be noted that the analysis and description of the foregoing embodiments of the lithium battery performance score calculation method are also applicable to the lithium battery performance score calculation system, electronic device, non-transitory computer-readable storage medium, computer program product, and computer program in Embodiments 2 to 6 of the present disclosure, and will not be described further here.

[0056] In the description of this specification, descriptions with reference to descriptions such as "one embodiment", "some embodiments", "exemplary", "specific examples", or "some examples" mean that the specific features, structures, materials, or features described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the exemplary descriptions of the above terms do not necessarily indicate the same embodiment or example. Also, the specific features, structures, materials, or features described can be appropriately combined in any one or more embodiments or examples. It should be noted that, as long as there is no contradiction, those skilled in the art can appropriately combine the different embodiments and examples described in the present invention, and the features of different embodiments and examples.

[0057] The description of a flowchart or any process or method described herein in another manner represents one or more modules, fragments, or portions of executable instruction code including steps for implementing a custom logic function or process. Also, the scope of the preferred embodiments of the present disclosure includes other implementations and includes performing functions basically simultaneously or in a reverse order based on related functions, rather than in the order illustrated or discussed, which should be understood by those skilled in the art of the technical field to which the examples of the present disclosure pertain.

Claims

1. A method for calculating a lithium battery performance score, comprising: acquiring data information in the operation process of a lithium battery and uploading the data to a lithium battery performance score database; constructing a lithium battery performance score system from three dimensions of battery nameplate attributes, operation attributes, and environmental attributes by using the lithium battery performance score database; constructing a battery performance score calculation model by using the fuzzy comprehensive evaluation method and calculating the performance index scores of each item of the lithium battery; A method for calculating a lithium battery performance score, including the above steps.

2. After uploading the data to the lithium battery performance score database, the method further includes performing a cleaning process on the lithium battery performance data in the lithium battery performance score database, The step of performing a cleaning process on the lithium battery performance data in the lithium battery performance score database includes filling missing values and processing abnormal values. The lithium battery performance score calculation method according to Claim 1.

3. Before constructing a lithium battery performance score system from three dimensions of battery nameplate attributes, operation attributes, and environmental attributes by using the lithium battery performance score database, the method further includes constructing lithium battery index features related to lithium battery performance, The method for constructing the lithium battery index features related to lithium battery performance includes descriptive statistics, correlation analysis, data transformation, data encoding, binning, and feature combination. The nameplate attributes include battery model number, battery capacity, battery shipping date, lot, manufacturer, and location. The operation attributes include total operation power, total voltage, total current, maximum and minimum voltages, and maximum and minimum temperatures. The environmental attributes include external maximum and minimum temperatures, maximum and minimum humidity, and weather data. The lithium battery performance score calculation method according to Claim 1 or 2.

4. The step of constructing a battery performance score calculation model by using the fuzzy comprehensive evaluation method and calculating the performance index scores of each item of the lithium battery includes: a step of level-dividing the lithium battery performance score system, where the division levels are battery cell level, module level, battery cluster level, and battery tank level; a step of classifying the index features of each item of lithium batteries at different levels into different types of membership functions; Putting each single - item lithium - battery index feature into the corresponding membership function to calculate the membership degree, and obtaining by combining each level of single - element evaluation matrix A of the lithium - battery; Calculating the weight coefficients of each item index feature of the lithium - battery using the multiple linear regression method, constructing a weight coefficient matrix R by composing the weight coefficients that affect the lithium - battery performance; Calculating the comprehensive evaluation index by multiplying the single - element evaluation matrix and the transposed weight coefficient matrix using the fuzzy comprehensive evaluation method, constructing a battery performance score calculation model, and calculating and obtaining the score results of different levels of lithium - battery performance indicators, including; The lithium - battery performance score calculation method according to any one of claims 1 to 3, wherein the membership function type includes a parabolic membership function, a positive S - shaped membership function, and a linear membership function.

5. The calculation formula of the parabolic membership function is as follows: 【Number 1】 In the formula: u1(x) is the value of the parabolic membership function, and x １ represents the numerical lower limit, and x ２ represents the optimal numerical lower limit, and x ３ represents the optimal numerical upper limit, and x ４ represents the numerical upper limit, The calculation formula of the positive S - shaped membership function is as follows: 【Number 2】 In the formula: u2(x) represents the positive S-shaped membership function value, and x １ represents the numerical lower limit, and x ４ represents the numerical upper limit, The calculation formula of the linear membership function is as follows: 【Number 3】 In the formula: u3(x) represents the linear membership function value; 【Number 4】 x ４ represents the numerical upper limit, and x １ represents the numerical lower limit, and The calculation values of the parabolic membership function, the positive S - shaped membership function, and the linear membership function constitute the single - element evaluation matrix A; 【Number 5】 In the formula: A is a matrix of m rows and n columns, m is the number of lithium battery samples, n is the number of lithium battery indicators, μ １１ is the membership degree of the first feature of the first battery sample, μ １ｎ is the membership degree of the nth feature of the first battery sample, μ ｍｎ is the membership degree of the nth feature of the mth battery sample. The lithium battery performance score calculation method according to claim 4.

6. The steps of calculating the weight coefficients of each item index feature of the lithium - battery using the multiple linear regression method, constructing a weight coefficient matrix R by composing the weight coefficients that affect the lithium - battery performance, and calculating the comprehensive evaluation index by multiplying the single - element evaluation matrix and the transposed weight coefficient matrix using the fuzzy comprehensive evaluation method, and constructing a battery performance score calculation model specifically include the following steps: H1: The k - th index of the lithium - battery 【Number 6】 Constructing a linear regression equation with other indexes, 【Number 6】 The calculation formula of which is as follows: 【Number 7】 In the formula: 【Number 8】 is a constant term, n is the number of lithium battery indicators, and x １ , x 2 ……x n are in the lithium battery indicators 【Number 9】 Other indexes except; H2: Calculating the complex correlation coefficient of the index, Complex correlation coefficient \(Z\) of the \(k\) - th index ｋ The calculation formula is as follows: 【Number 10】 In the formula, 【Number 11】 is the average value of X ｋ and H3: Constructing an index weight coefficient matrix, The reciprocal (1 / Z ｋ ) of the complex correlation coefficient of each index is normalized, and then the weight coefficient r of each item index is obtained to construct the weight coefficient matrix R. 【Number 12】 In the formula, r 1 is the weight coefficient of the first lithium battery indicator, and r ｎ is the weight coefficient of the nth lithium battery indicator, H4: Calculating the comprehensive evaluation index B using fuzzy matrix synthesis; 【Number 13】 In the formula: Y １ is the overall score of the performance state of the first lithium battery sample, and Y ｍ is the overall score of the m-th lithium battery sample, where m is the number of lithium battery samples. The lithium battery performance score calculation method according to claim 4

7. The method further includes: Classifying the health state of the lithium - battery performance based on the evaluation result, and dividing it into four levels: healthy, sub - healthy, unhealthy, and severely unhealthy; Drawing a visualization interface of the lithium - battery performance state. The visualization interface includes the number of lithium battery devices, distribution topology, temperature, and performance status results, and is used to provide a lithium battery non-health warning to the operation inspection department for the lithium battery performance score calculation method according to any one of claims 1 to 6.

8. A lithium battery performance score calculation system, comprising: An acquisition module that acquires data information in the operation process of the lithium battery and uploads the data to the lithium battery performance score database; A construction module that constructs a lithium battery performance score system from three dimensions of battery nameplate attributes, operation attributes, and environmental attributes using the lithium battery performance score database; A calculation module that constructs a battery performance score calculation model using the fuzzy comprehensive evaluation method and calculates the performance index scores of each item of the lithium battery; A lithium battery performance score calculation system including the above.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable by the processor. When the processor executes the program, it realizes the lithium battery performance score calculation method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, wherein: When the program is executed by a processor, it realizes the lithium battery performance score calculation method according to any one of claims 1 to 7.

11. A computer program product, comprising: A computer program. When the computer program is executed by a processor, it realizes the lithium battery performance score calculation method according to any one of claims 1 to 7.

12. A computer program, wherein: The computer program includes computer program code. When the computer program code is executed by a computer, it causes the computer to execute the lithium battery performance score calculation method according to any one of claims 1 to 7.

Images