Battery production temperature prediction method and device, electronic equipment and storage medium

Abstract

The invention provides a battery production temperature prediction method and device, electronic equipment and a storage medium, and relates to the technical field of batteries, and the method comprises the steps: obtaining the initial temperature of battery production and the battery parameters of a battery; according to the initial temperature, temperature distinguishing is carried out on the battery cell of the battery in each working step, and a plurality of temperature intervals of each working step are obtained; performing feature extraction on each temperature interval according to the battery parameters to obtain a feature data set of each temperature interval; performing polynomial fitting in each temperature interval according to the feature data set to obtain a polynomial coefficient of each process step in each temperature interval; determining a prediction model under different working steps in each temperature interval, and obtaining a prediction coefficient of each working step according to the polynomial coefficient and the prediction model; and constructing a temperature curve of each process step according to the prediction coefficient, and obtaining a production temperature change curve of the battery according to the temperature curves. The method can accurately predict the production temperature data of the battery, and improves the productivity and efficiency of the battery production line.

Description

Technical Field

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

[0002] As a core component of energy storage, batteries are widely used in many fields such as electric vehicles, smartphones, and renewable energy storage. Battery production needs to be carried out in an environment with constant temperature and humidity. The production temperature of the battery is a key parameter that directly affects the performance and quality of the battery. If the temperature is too high or too low, it will have a negative impact on the performance of the battery. For example, too high a temperature may accelerate the chemical reaction rate inside the battery, causing the battery to age faster; while too low a temperature may reduce the output power and performance of the battery. Therefore, accurate prediction and simulation of the battery production temperature can ensure that the quality and performance of the battery are in the best state and improve the efficiency and safety of battery use.

[0003] At present, the commonly used methods in the industry mainly include thermal management solutions based on physical models and statistical models based on data-driven. Physical modeling can accurately predict battery temperature by establishing a physical model of battery thermal characteristics and temperature changes, but this method has high computational complexity and is difficult to meet real-time requirements, so it has certain limitations in real-time applications. The data-driven prediction method uses historical data and machine learning algorithms to predict battery temperature. This method has good real-time and adaptability, but the quality and source of the data directly affect the accuracy of the model. When the data is scarce or of low quality, the prediction results may not be reliable enough. How to ensure the accuracy of battery production temperature prediction under complex environmental conditions such as production lines while achieving high computational efficiency is a technical problem that needs to be solved urgently. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides a battery production temperature prediction method, device, electronic device and storage medium, which effectively solve the problem of how to ensure the accuracy of battery production temperature prediction under complex environmental conditions such as production lines while achieving higher computing efficiency.

[0005] In a first aspect, the present invention provides a method for predicting the production temperature of a battery, the method comprising:

[0006] Obtaining an initial temperature of battery production and battery parameters of the battery;

[0007] Differentiating the temperature of the battery cells of the battery in each process step according to the initial temperature to obtain multiple temperature intervals for each process step;

[0008] Perform feature extraction on each of the temperature intervals according to the battery parameters to obtain a feature data set for each of the temperature intervals;

[0009] Performing polynomial fitting in each temperature interval according to the characteristic data set to obtain polynomial coefficients for each process step in each temperature interval;

[0010] Determine a prediction model for each of the temperature intervals under different working steps, and obtain a prediction coefficient for each of the working steps according to the polynomial coefficients and the prediction model;

[0011] A temperature curve of each of the working steps is constructed according to the prediction coefficient, and a production temperature variation curve of the battery is obtained according to the temperature curve.

[0012] Furthermore, extracting features of each temperature interval according to the battery parameters to obtain a feature data set of each temperature interval includes:

[0013] Extracting features from each of the temperature intervals according to the battery parameters to obtain an initial feature data set;

[0014] The initial feature data set is divided into a training set and a prediction set, and the temperature data in the training set and the prediction set are smoothed to obtain a feature data set.

[0015] Further, performing polynomial fitting in each temperature interval according to the characteristic data set to obtain the polynomial coefficients of each process step in each temperature interval includes:

[0016] Obtain the training set after smoothing each temperature interval, and extract the temperature data of each step in each second in the training set;

[0017] Subtract the end temperature of the previous step from the temperature data of each second of the current step to obtain a temperature difference;

[0018] Setting the order of each of the working steps, performing polynomial fitting according to the order and the temperature difference, and obtaining initial polynomial coefficients of each of the working steps in each of the temperature ranges;

[0019] Data cleaning is performed on the initial polynomial coefficients to obtain the polynomial coefficients.

[0020] Furthermore, the performing data cleaning on the initial polynomial coefficients to obtain the polynomial coefficients includes:

[0021] Sorting the initial polynomial coefficients from small to large to obtain a sequence coefficient group;

[0022] Calculating the first quartile, the median and the third quartile of the sequence coefficient group, and dividing the sequence coefficient group into four equal parts according to the first quartile, the median and the third quartile;

[0023] The interquartile range is calculated according to the first quartile and the third quartile;

[0024] Determine a first set threshold value according to the first quartile and the interquartile range, and determine a second set threshold value according to the third quartile and the interquartile range;

[0025] If the initial polynomial coefficient is less than the first set threshold or the initial polynomial coefficient is greater than the second set threshold, the initial polynomial coefficient is cleared as an abnormal value to obtain the polynomial coefficient.

[0026] Furthermore, the step of determining the prediction model for each temperature interval under different working steps and obtaining the prediction coefficient according to the polynomial coefficient and the prediction model includes:

[0027] Determine a prediction model for each of the temperature intervals under different process steps;

[0028] Using the training set of each temperature interval to train the corresponding prediction model to obtain the trained prediction model;

[0029] The prediction set of the temperature range and the polynomial coefficients are input into the trained prediction model for learning to obtain the prediction coefficients.

[0030] Furthermore, the prediction model includes at least one or more of a linear regression model, a decision tree model, a random forest model, a support vector machine model and a neural network model.

[0031] Furthermore, constructing a temperature curve for each of the process steps according to the prediction coefficient, and obtaining a production temperature change curve of the battery according to the temperature curve, includes:

[0032] Constructing a temperature curve for each working step according to the prediction coefficient and the temperature transfer between the working steps according to the working step sequence;

[0033] The temperature curves are connected end to end according to the process step sequence to obtain the production temperature change curve of the battery.

[0034] In a second aspect, the present invention provides a battery production temperature prediction device, the device comprising:

[0035] A data acquisition module, used to acquire the initial temperature of battery production and battery parameters of the battery;

[0036] A data processing module, used for performing temperature differentiation on the battery cells of the battery in each process step according to the initial temperature, so as to obtain a plurality of temperature intervals for each process step;

[0037] A feature extraction module, used to extract features of each temperature interval according to the battery parameters to obtain a feature data set of each temperature interval;

[0038] A data fitting module, used for performing polynomial fitting in each temperature interval according to the characteristic data set, to obtain polynomial coefficients of each process step in each temperature interval;

[0039] A model prediction module, determining a prediction model for each of the temperature intervals under different working steps, and obtaining a prediction coefficient for each of the working steps according to the polynomial coefficients and the prediction model;

[0040] A curve generating module is used to construct a temperature curve for each of the working steps according to the prediction coefficients, and obtain a production temperature variation curve of the battery according to the temperature curve.

[0041] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting the production temperature of a battery as described in the first aspect of the present invention.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for predicting the production temperature of a battery as described in the first aspect of the present invention.

[0043] The method, device, electronic device and storage medium for predicting the production temperature of the battery provided by the present invention predict the polynomial coefficients according to different steps in different temperature ranges and then predict the production temperature. The prediction scheme based on big data has much fewer data requirements than the physical modeling method. Combining the principles of physics and mathematics, temperature calculation and prediction are performed in a formula and fast iteration manner, which reduces the use of computing resources and improves the reliability and accuracy of the model. At the same time, the production temperature data of the battery can be accurately predicted, which can provide more accurate guidance for the manufacture, operation and control of the battery, simplify the process, improve the operability and control ability of the manufacturing process, and is conducive to optimizing the design parameters and process flow, improving the production capacity and efficiency of the battery production line, and effectively saving energy consumption and reducing the consumption of raw materials. At the same time, the quality and precision of battery products are improved, and the energy loss and heat emission during the operation of the battery are reduced, thereby reducing pollution to the environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 This is a first schematic diagram of the process of the method for predicting the production temperature of a battery provided by an embodiment of the present invention;

[0046] Figure 2 This is a second schematic diagram of the process of the method for predicting the production temperature of a battery provided by an embodiment of the present invention;

[0047] Figure 3 3 is a schematic diagram of a method for predicting the production temperature of a battery provided by an embodiment of the present invention;

[0048] Figure 4 4 is a schematic diagram of a method for predicting the production temperature of a battery provided by an embodiment of the present invention;

[0049] Figure 5 is a fifth schematic diagram of a method for predicting the production temperature of a battery provided by an embodiment of the present invention;

[0050] Figure 6 6 is a schematic diagram of a method for predicting the production temperature of a battery provided by an embodiment of the present invention;

[0051] Figure 7 Schematic diagram of the temperature curve of step 2 in the first temperature range in an embodiment of the present invention;

[0052] Figure 8 is a schematic diagram of a temperature curve of step 2 in the second temperature range in an embodiment of the present invention;

[0053] Fig. 9 1 is a schematic diagram of a production temperature variation curve of a battery in an embodiment of the present invention;

[0054] Fig.10 It is a schematic diagram of the structure of a battery production temperature prediction device provided by an embodiment of the present invention;

[0055] Fig.11 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention.

[0056] Description of main component symbols:

[0057] 700, battery production temperature prediction device; 710, data acquisition module; 720, data processing module; 730, feature extraction module; 740, data fitting module; 750, model prediction module; 760, curve generation module; 800, electronic device; 810, processor; 820, communication interface; 830, memory; 840, communication bus. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be further clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be noted that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0059] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0061] At present, the commonly used battery production temperature prediction methods in the industry mainly include thermal management solutions based on physical models and statistical models based on data-driven. Physical modeling can accurately predict battery temperature by establishing a physical model of battery thermal characteristics and temperature changes, but this method has high computational complexity and is difficult to meet real-time requirements, so it has certain limitations in real-time applications. The data-driven prediction method uses historical data and machine learning algorithms to predict battery temperature. This method has good real-time and adaptability, but the quality and source of the data directly affect the accuracy of the model. When the data is scarce or of low quality, the prediction results may not be reliable enough. How to ensure the accuracy of battery production temperature prediction while achieving high computational efficiency under complex environmental conditions such as production lines is a technical problem that needs to be solved urgently.

[0062] Example 1

[0063] The embodiment of the present invention provides a method for predicting the production temperature of a battery, which effectively solves the problem of how to ensure the accuracy of battery production temperature prediction under complex environmental conditions such as a production line while achieving higher calculation efficiency. Figure 1 FIG. 1 is a first schematic diagram of a method for predicting the production temperature of a battery provided by an embodiment of the present invention. Figure 1 As shown, the method specifically comprises the following steps:

[0064] S100: Obtaining the initial temperature of battery production and battery parameters of the battery.

[0065] In the embodiment of the present invention, the initial temperature of the battery production may be the ambient temperature at the beginning of production. For example, the first step of battery formation or capacity separation is usually to place the battery in a static state, and the first ambient temperature when the battery is in a static state is used as the initial temperature. Battery parameters include, but are not limited to, voltage, current, internal resistance, cell weight, cell density, and other parameters.

[0066] S200 , temperature differentiation of battery cells of each process step is performed according to the initial temperature to obtain multiple temperature intervals of each process step.

[0067] In the battery production process, each process step is continuous, so the initial temperature of the battery cell in each process step can be obtained based on the initial temperature of the first process step of the battery. In each process step, the temperature of the battery cell is differentiated within the range of the set temperature threshold, which can better understand and control the temperature change in the production process. In the embodiment of the present invention, the set temperature threshold can be 3-4°C.

[0068] S300 , extracting features for each temperature interval according to battery parameters to obtain a feature data set for each temperature interval.

[0069] Figure 2 FIG. 2 is a second schematic diagram of the process of the method for predicting the production temperature of a battery provided by an embodiment of the present invention. Figure 2 As shown, the acquisition of feature data set includes the following steps:

[0070] S310 , extracting features for each temperature interval according to battery parameters to obtain an initial feature data set.

[0071] According to the battery parameters, the characteristic parameters most relevant to temperature are selected, the changes of these characteristic parameters are recorded in each temperature range for statistical analysis to obtain statistics, the trend of characteristic parameters changing with temperature is analyzed to calculate the correlation, so as to identify which characteristic parameters may have an important impact on battery performance, and finally, the values ​​are extracted according to these characteristic parameters to obtain the initial characteristic data set. In the embodiment of the present invention, the values ​​extracted according to the characteristic parameters include but are not limited to the initial voltage and the end voltage of the working step, the voltage difference and the voltage difference slope of the working step, and the weight of the battery cell, etc.

[0072] S320, dividing the initial feature data set into a training set and a prediction set, and performing smoothing processing on the temperature data in the training set and the prediction set to obtain a feature data set.

[0073] In an embodiment of the present invention, 20% of the data in the initial feature data set is used as a training set, and 80% of the data is used as a prediction set. In order to reduce the volatility of the temperature data and remove the noise in the temperature data, the temperature of the training set and the prediction set is smoothed. Optionally, Gaussian filtering is used to smooth the temperature data to reduce the noise and details of the data. Gaussian filtering works by convolution with a Gaussian kernel to achieve a smoothing effect. The sigma parameter of the filter controls the degree of smoothing. The larger the value of sigma, the more obvious the smoothing effect, the wider the width of the filter, and the more data points covered by the smoothing operation. In an embodiment of the present invention, the value of sigma is 5.

[0074] S400, performing polynomial fitting in each temperature interval according to the characteristic data set to obtain polynomial coefficients of each process step in each temperature interval.

[0075] Figure 3 FIG. 3 is a third schematic diagram of the process of the method for predicting the production temperature of a battery provided by an embodiment of the present invention. Figure 3 As shown, obtaining the polynomial coefficients includes the following steps:

[0076] S410, obtaining a training set after smoothing in each temperature interval, and extracting temperature data of each step in each second in the training set.

[0077] A polynomial fitting is performed on the temperature data in the training set after smoothing. Assuming that X represents time and Y represents temperature, since the temperature changes slowly, it is recorded every second in the embodiment of the present invention.

[0078] S420, subtract the end temperature of the previous step from the temperature data of each second of the current step to obtain a temperature difference.

[0079] In the embodiment of the present invention, the temperature of each second of the current step is subtracted from the end temperature of the previous step to obtain the temperature difference as the fitting data. If the current step is the first step, the initial temperature is subtracted. By using the temperature difference as the fitting data, the intercept of the polynomial fitting can be made 0, avoiding the situation of temperature jump between different steps.

[0080] S430, setting the order of each process step, performing polynomial fitting according to the order and the temperature difference, and obtaining initial polynomial coefficients of each process step in each temperature range.

[0081] In the embodiment of the present invention, the setting standard of the order is to satisfy the determination coefficient R 2When the coefficient of determination is >0.95, the smaller the order, the better. The coefficient of determination is an indicator to measure the degree of fit of the regression model. Its value range is between 0 and 1. The closer it is to 1, the better the model fits the data and the more it can explain the changes in the dependent variable; the closer it is to 0, the worse the model fits the data and the less it can explain the changes in the dependent variable.

[0082] For example, in the formation stage of the battery cell, there are five steps of resting-charging-resting-charging-resting. The time length of each step is different. The corresponding steps are set to 4, 6, 4, 6 and 4. The determination coefficients are all over 0.95. These steps can be used in any temperature range.

[0083] S440, performing data cleaning on the initial polynomial coefficients to obtain polynomial coefficients.

[0084] After all the initial polynomial coefficients are fitted, the abnormal coefficients need to be cleaned. Figure 4 4 is a schematic diagram of the production temperature prediction method of a battery provided by an embodiment of the present invention. Figure 4 As shown, data cleaning includes the following steps:

[0085] S441. Sort the initial polynomial coefficients from small to large to obtain a sequence coefficient group.

[0086] S442. Calculate the first quartile, median and third quartile of the sequence coefficient group, and divide the sequence coefficient group into four equal parts according to the first quartile, median and third quartile.

[0087] In the embodiment of the present invention, quartiles are used to divide the sequence coefficient group into four parts, namely the first quartile Q1, i.e., the 25% quartile, the median (second quartile) Q2, i.e., the 50% quartile and the third quartile Q3, i.e., the 75% quartile.

[0088] S443. Calculate the interquartile range based on the first quartile and the third quartile.

[0089] In the embodiment of the present invention, the interquartile range IQR is the difference between the third quartile Q3 and the first quartile Q1, that is, IQR=Q3-Q1.

[0090] S444. Determine a first set threshold value according to the first quartile and the interquartile range, and determine a second set threshold value according to the third quartile and the interquartile range.

[0091] Optionally, a threshold may be set according to the quartiles and the interquartile range to determine a threshold range to identify outliers. In an embodiment of the present invention, the first set threshold may be I1=Q1-1.5IQR, and the second set threshold may be I2=Q1+1.5IQR.

[0092] S445. If the initial polynomial coefficient is less than the first set threshold or the initial polynomial coefficient is greater than the second set threshold, the initial polynomial coefficient is cleared as an abnormal value to obtain the polynomial coefficient.

[0093] In the embodiment of the present invention, the initial polynomial coefficients smaller than I1 and larger than I2 are regarded as abnormal values, and the abnormal values ​​can be regarded as null values, and filled or deleted in subsequent data processing to finally obtain the polynomial coefficients.

[0094] S500, determining a prediction model for different working steps in each temperature range, and obtaining a prediction coefficient for each working step according to the polynomial coefficient and the prediction model.

[0095] Figure 5 5 is a fifth schematic diagram of the process of the method for predicting the production temperature of a battery provided by an embodiment of the present invention. Figure 5 As shown, the acquisition of prediction coefficients includes the following steps:

[0096] S510, determining a prediction model for different process steps in each temperature range.

[0097] In an embodiment of the present invention, a prediction model is determined for each process step in each temperature interval. For example, if two temperature intervals and five process steps are divided, ten prediction models need to be determined. The prediction model includes, but is not limited to, one or more of a linear regression model, a decision tree model, a random forest model, a support vector machine model, and a neural network model. For example, the linear regression model is suitable for predicting situations where the relationship between the response variable and one or more predictor variables is approximately linear; the decision tree and random forest models perform well in dealing with nonlinear relationships and interactions, and are easy to interpret, and are particularly suitable for use in battery cell performance prediction; the support vector machine model is suitable for processing high-dimensional data, especially in battery cell life and performance prediction; the neural network model, especially the deep learning model, is suitable for complex and large-scale data analysis, such as multi-parameter prediction of battery cells, due to its powerful nonlinear modeling capabilities.

[0098] S520: Use the training set of each temperature range to train the corresponding prediction model to obtain a trained prediction model.

[0099] The training set is based on the results of previous feature extraction. The number and type of features are determined according to previous analysis. During the training process, the model parameters can be appropriately adjusted to optimize the prediction effect.

[0100] S530, input the prediction set of the temperature range and the polynomial coefficients into the trained prediction model for learning to obtain the prediction coefficients.

[0101] Optionally, in the charging step 2, a BP neural network model is used to learn the relationship between the prediction set features and the polynomial coefficients, and the coefficients learned by the output BP neural network model are A, B, C, D, E and F respectively.

[0102] S600, constructing a temperature curve for each process step according to the prediction coefficient, and obtaining a production temperature change curve of the battery according to the temperature curve.

[0103] Figure 6 6 is a schematic diagram of the method for predicting the production temperature of a battery provided by an embodiment of the present invention. Figure 6 As shown, the acquisition of the production temperature change curve includes the following steps:

[0104] S610 , constructing a temperature curve for each process step according to the process step sequence based on the prediction coefficient and the temperature transfer between the process steps.

[0105] In the embodiment of the present invention, taking the charging step 2 as an example, the polynomial formula composed of 6 coefficients learned by the BP neural network model is:

[0106] Y=AX 6 +BX 5 +CX 4 +DX 3 +EX 2 +FX

[0107] In the above formula, X represents time and Y represents temperature.

[0108] The end temperature of the static step 1 is used as the initial temperature of the step 2. Assuming that the initial temperature is K, the final polynomial formula is:

[0109] Y=AX 6 +BX 5 +CX 4 +DX 3 +EX 2 +FX+K,

[0110] Substituting the time value of each second corresponding to step 2 into the above polynomial formula, the temperature corresponding to each second can be obtained. Based on the temperature of each second combined with the temperature transfer between the steps, the temperature curve of each step can be constructed according to the step sequence.

[0111] Figure 7 is a schematic diagram of the temperature curve of the second step in the first temperature range in an embodiment of the present invention, Figure 8 is a schematic diagram of the temperature curve of step 2 in the second temperature range in an embodiment of the present invention. Figure 7 and Figure 8 As shown, the predicted temperature is in a balanced state between the real temperatures, and the prediction effect is better.

[0112] S620, connecting the temperature curves end to end according to the process step sequence to obtain a production temperature change curve of the battery.

[0113] Fig. 9 Schematic diagram of the production temperature change curve of the battery in the embodiment of the present invention. Fig. 9 As shown, during the entire process step, the actual temperature and the predicted temperature are basically consistent. The production temperature of the battery at different times can be obtained according to the production temperature change curve.

[0114] The battery production temperature prediction method, device, electronic device and storage medium provided by the present invention predict the polynomial coefficients according to different steps in different temperature ranges and then predict the production temperature. The prediction scheme based on big data has much fewer data requirements than the physical modeling method. Combining the principles of physics and mathematics, temperature calculation and prediction are performed in a formula and fast iteration manner, which reduces the use of computing resources and improves the reliability and accuracy of the model.

[0115] Example 2

[0116] Based on the same technical concept, an embodiment of the present invention provides a battery production temperature prediction device. Fig.10 Schematic diagram of the structure of the battery production temperature prediction device provided by the embodiment of the present invention. Fig.10 As shown, the battery production temperature prediction device 700 includes:

[0117] The data acquisition module 710 is used to obtain the initial temperature of the battery production and the battery parameters of the battery.

[0118] The data processing module 720 is used to differentiate the temperature of the battery cells of each process step according to the initial temperature, and obtain multiple temperature intervals of each process step.

[0119] The feature extraction module 730 is used to extract features for each temperature interval according to the battery parameters to obtain a feature data set for each temperature interval.

[0120] The data fitting module 740 is used to perform polynomial fitting in each temperature interval according to the characteristic data set to obtain the polynomial coefficients of each process step in each temperature interval.

[0121] The model prediction module 750 determines the prediction model for different working steps in each temperature range, and obtains the prediction coefficient of each working step according to the polynomial coefficient and the prediction model.

[0122] The curve generation module 760 is used to construct a temperature curve for each process step according to the prediction coefficient, and obtain a production temperature change curve of the battery according to the temperature curve.

[0123] The battery production temperature prediction device provided by the embodiment of the present invention can accurately predict the battery production temperature data, can provide more accurate guidance for the manufacture, operation and control of the battery, simplify the process, improve the operability and control ability of the manufacturing process, and is conducive to optimizing the design parameters and process flow, improving the production capacity and efficiency of the battery production line, effectively saving energy consumption and reducing the consumption of raw materials. At the same time, it improves the quality and accuracy of battery products, reduces energy loss and heat emission during the operation of the battery, and thus reduces pollution to the environment.

[0124] It can be understood that the implementation method of battery production temperature prediction described in the above embodiment 1 is also applicable to this embodiment and can achieve the same technical effect, so it will not be repeated here.

[0125] Example 3

[0126] Based on the same concept, an embodiment of the present invention further provides an electronic device, Fig.11 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Fig.11 As shown, the electronic device 800 may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the steps of the battery production temperature prediction method described in the above embodiments. For example, it includes:

[0127] S100, obtaining the initial temperature of the battery production and the battery parameters of the battery;

[0128] S200, temperature differentiation of the battery cells of each process step according to the initial temperature to obtain multiple temperature intervals for each process step;

[0129] S300, extracting features for each temperature interval according to battery parameters to obtain a feature data set for each temperature interval;

[0130] S400, performing polynomial fitting in each temperature interval according to the characteristic data set to obtain polynomial coefficients for each process step in each temperature interval;

[0131] S500, determining a prediction model for different working steps in each temperature range, and obtaining a prediction coefficient for each working step according to the polynomial coefficient and the prediction model;

[0132] S600, constructing a temperature curve for each process step according to the prediction coefficient, and obtaining a production temperature change curve of the battery according to the temperature curve.

[0133] The processor 810 may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0134] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0135] The memory 830 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0136] Example 4

[0137] Based on the same concept, an embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program, and the computer program includes at least one code segment, which can be executed by a main control device to control the main control device to implement the steps of the battery production temperature prediction method described in the above embodiments. For example, it includes:

[0138] S100, obtaining the initial temperature of the battery production and the battery parameters of the battery;

[0139] S200, temperature differentiation of the battery cells of each process step according to the initial temperature to obtain multiple temperature intervals for each process step;

[0140] S300, extracting features for each temperature interval according to battery parameters to obtain a feature data set for each temperature interval;

[0141] S400, performing polynomial fitting in each temperature interval according to the characteristic data set to obtain polynomial coefficients for each process step in each temperature interval;

[0142] S500, determining a prediction model for different working steps in each temperature range, and obtaining a prediction coefficient for each working step according to the polynomial coefficient and the prediction model;

[0143] S600, constructing a temperature curve for each process step according to the prediction coefficient, and obtaining a production temperature change curve of the battery according to the temperature curve.

[0144] Based on the same technical concept, an embodiment of the present invention further provides a computer program, which is used to implement the above method embodiment when executed by a main control device.

[0145] The computer program may be stored in whole or in part on a computer-readable storage medium packaged with the processor, or may be stored in whole or in part on a memory not packaged with the processor.

[0146] Based on the same technical concept, an embodiment of the present invention further provides a processor, which is used to implement the above method embodiment. The above processor can be a chip.

[0147] In summary, the battery production temperature prediction method, device, electronic device and storage medium provided by the present invention predict the polynomial coefficients according to different steps in different temperature ranges and then predict the production temperature. The prediction scheme based on big data has much fewer data requirements than the physical modeling method. Combining the principles of physics and mathematics to calculate and predict temperature in a formula and fast iteration manner, the use of computing resources is reduced and the reliability and accuracy of the model are improved. At the same time, the production temperature data of the battery can be accurately predicted, which can provide more accurate guidance for the manufacture, operation and control of the battery, simplify the process, improve the operability and control ability of the manufacturing process, and help optimize the design parameters and process flow, improve the production capacity and efficiency of the battery production line, and effectively save energy consumption and reduce the consumption of raw materials. At the same time, the quality and precision of battery products are improved, and the energy loss and heat emission during the operation of the battery are reduced, thereby reducing pollution to the environment.

[0148] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0149] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0150] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the production temperature of a battery, characterized in that: The method comprises: Obtaining an initial temperature of battery production and battery parameters of the battery; Differentiating the temperature of the battery cells of the battery in each process step according to the initial temperature to obtain multiple temperature intervals for each process step; Perform feature extraction on each of the temperature intervals according to the battery parameters to obtain a feature data set for each of the temperature intervals; Performing polynomial fitting in each temperature interval according to the characteristic data set to obtain polynomial coefficients for each process step in each temperature interval; Determine a prediction model for each of the temperature intervals under different working steps, and obtain a prediction coefficient for each of the working steps according to the polynomial coefficients and the prediction model; A temperature curve of each of the working steps is constructed according to the prediction coefficient, and a production temperature variation curve of the battery is obtained according to the temperature curve.

2. The method for predicting the production temperature of a battery according to claim 1, characterized in that: The extracting features of each temperature interval according to the battery parameters to obtain a feature data set of each temperature interval includes: Extracting features from each of the temperature intervals according to the battery parameters to obtain an initial feature data set; The initial feature data set is divided into a training set and a prediction set, and the temperature data in the training set and the prediction set are smoothed to obtain a feature data set.

3. The method for predicting the production temperature of a battery according to claim 2, characterized in that: The performing polynomial fitting in each temperature interval according to the characteristic data set to obtain the polynomial coefficients of each process step in each temperature interval includes: Obtain the training set after smoothing each temperature interval, and extract the temperature data of each step in each second in the training set; Subtract the end temperature of the previous step from the temperature data of each second of the current step to obtain a temperature difference; Setting the order of each of the working steps, performing polynomial fitting according to the order and the temperature difference, and obtaining initial polynomial coefficients of each of the working steps in each of the temperature ranges; Data cleaning is performed on the initial polynomial coefficients to obtain the polynomial coefficients.

4. The method for predicting the production temperature of a battery according to claim 3, characterized in that: The step of performing data cleaning on the initial polynomial coefficients to obtain the polynomial coefficients includes: Sorting the initial polynomial coefficients from small to large to obtain a sequence coefficient group; Calculating the first quartile, the median and the third quartile of the sequence coefficient group, and dividing the sequence coefficient group into four equal parts according to the first quartile, the median and the third quartile; The interquartile range is calculated according to the first quartile and the third quartile; Determine a first set threshold value according to the first quartile and the interquartile range, and determine a second set threshold value according to the third quartile and the interquartile range; If the initial polynomial coefficient is less than the first set threshold or the initial polynomial coefficient is greater than the second set threshold, the initial polynomial coefficient is cleared as an abnormal value to obtain the polynomial coefficient.

5. The method for predicting the production temperature of a battery according to claim 3, characterized in that: Determining the prediction model for each of the temperature intervals under different process steps, and obtaining the prediction coefficient of each process step according to the polynomial coefficient and the prediction model, comprises: Determine a prediction model for each of the temperature intervals under different process steps; Using the training set of each temperature interval to train the corresponding prediction model to obtain the trained prediction model; The prediction set of the temperature range and the polynomial coefficients are input into the trained prediction model for learning to obtain the prediction coefficients.

6. The method for predicting the production temperature of a battery according to claim 5, characterized in that: The prediction model includes at least one or more of a linear regression model, a decision tree model, a random forest model, a support vector machine model and a neural network model.

7. The method for predicting the production temperature of a battery according to claim 5, characterized in that: The step of constructing a temperature curve for each of the process steps according to the prediction coefficient, and obtaining a production temperature change curve of the battery according to the temperature curve, comprises: Constructing a temperature curve for each working step according to the prediction coefficient and the temperature transfer between the working steps according to the working step sequence; The temperature curves are connected end to end according to the process step sequence to obtain the production temperature change curve of the battery.

8. A battery production temperature prediction device, characterized in that: The device comprises: A data acquisition module, used to acquire the initial temperature of battery production and battery parameters of the battery; A data processing module, used for performing temperature differentiation on the battery cells of the battery in each process step according to the initial temperature, so as to obtain a plurality of temperature intervals for each process step; A feature extraction module, used to extract features of each temperature interval according to the battery parameters to obtain a feature data set of each temperature interval; A data fitting module, used for performing polynomial fitting in each temperature interval according to the characteristic data set, to obtain polynomial coefficients of each process step in each temperature interval; A model prediction module, determining a prediction model for each of the temperature intervals under different working steps, and obtaining a prediction coefficient for each of the working steps according to the polynomial coefficients and the prediction model; A curve generating module is used to construct a temperature curve for each of the working steps according to the prediction coefficients, and obtain a production temperature variation curve of the battery according to the temperature curve.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: The processor executes the computer program to implement the method for predicting the production temperature of a battery according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the production temperature of a battery according to any one of claims 1 to 7 is implemented.

Images