A battery production resource allocation method and system based on optimization theory

Abstract

The application discloses a battery production resource configuration method and system based on optimization theory, and relates to the technical field of resource configuration; the system comprises a monitoring module and an analysis module; the monitoring module monitors running data of batteries in application scenarios under different production resource configurations; the analysis module scores the batteries according to the running data; a posterior distribution of battery scores is obtained based on Bayesian model analysis; a selection factor delta is determined according to the range of the battery scores; the optimal distribution of the battery scores is selected from the posterior distribution according to the selection factor delta; corresponding samples are collected in the optimal distribution of the battery scores; and optimal battery production resource configuration is obtained through calculation.

Description

TECHNICAL FIELD

[0001] The application discloses a method and system, relates to the technical field of resource configuration, and in particular relates to a battery production resource configuration method and system based on optimization theory. BACKGROUND

[0002] Under the current energy trend, the application prospect of new energy batteries is broader than ever. New energy batteries are needed to support new energy vehicles, new energy photovoltaics and other new industrial fields. In addition, the development of material science and the innovation of factory production chains provide more choices for manufacturing new energy batteries. However, there is still no perfect method in the prior art to select appropriate battery production resources according to the corresponding application scenarios and to configure resources to improve battery production. SUMMARY

[0003] The application provides a battery production resource configuration method and system based on optimization theory, which has the characteristics of strong universality, simple implementation and the like, and has a wide application prospect.

[0004] The specific scheme provided by the application is as follows:

[0005] A battery production resource configuration system based on optimization theory comprises a monitoring module and an analysis module,

[0006] The monitoring module monitors the running data of batteries in application scenarios under different production resource configurations, and the analysis module scores the batteries according to the running data, obtains the posterior distribution of battery scores based on Bayesian model analysis, determines a selection factor δ according to the range of the battery scores, selects the optimal distribution of the battery scores from the posterior distribution according to the selection factor δ, collects corresponding samples in the optimal distribution of the battery scores, and calculates to obtain an optimized battery production resource configuration.

[0007] Preferably, the analysis module scores the batteries according to the running data in the battery production resource configuration system based on optimization theory, and the scoring comprises the following steps.

[0008] The following formula is used:

[0009]

[0010] The battery score is obtained, wherein the final battery health degree is obtained by dividing the final battery maximum capacity by the initial battery maximum capacity, the total test time is the running time of the battery in the application scenario, and the normal working time is the running time of the battery within the voltage threshold and the current threshold.

[0011] Preferably, the analysis module in the battery production resource allocation system based on optimization theory obtains a posterior distribution of the battery score, comprising:

[0012] obtaining a prior distribution of the battery score based on the historical operation data of the battery according to a Bayesian model, and obtaining a posterior distribution of the battery score through analysis and calculation based on the prior distribution.

[0013] The application also provides a battery production resource allocation method based on optimization theory, which monitors operation data of a battery in an application scenario under different production resource allocations, performs battery scoring according to the operation data,

[0014] obtains a posterior distribution of the battery score based on Bayesian model analysis,

[0015] determines a selection factor δ according to the range of the battery score, selects an optimal distribution of the battery score from the posterior distribution according to the selection factor δ, collects corresponding samples in the optimal distribution of the battery score, and calculates an optimized battery production resource allocation.

[0016] Preferably, the battery scoring according to the operation data in the battery production resource allocation method based on optimization theory comprises:

[0017] using the following formula:

[0018]

[0019] performing battery scoring, wherein the final battery health degree is obtained by dividing the final battery maximum capacity by the initial battery maximum capacity, the total test time is the operation time of the battery in the application scenario, and the normal operation time is the operation time of the battery within the voltage threshold and the current threshold.

[0020] Preferably, the posterior distribution of the battery score in the battery production resource allocation method based on optimization theory comprises:

[0021] obtaining a prior distribution of the battery score based on the historical operation data of the battery according to a Bayesian model, and obtaining a posterior distribution of the battery score through analysis and calculation based on the prior distribution.

[0022] The application provides a battery production resource allocation device based on optimization theory, comprising at least one memory and at least one processor.

[0023] The at least one memory is used to store a machine-readable program.

[0024] The at least one processor is used to call the machine-readable program and execute the battery production resource allocation method based on optimization theory.

[0025] The application also provides a computer readable medium, wherein computer instructions are stored on the computer readable medium, and the computer instructions, when executed by a processor, cause the processor to perform the battery production resource configuration method based on optimization theory.

[0026] The application has the following advantages:

[0027] The application provides a battery production resource configuration method based on optimization theory, wherein by collecting various operation data of batteries in application scenarios under different production resource configurations, a score of the batteries is obtained, an optimal distribution in a posterior distribution of the battery score is selected by using a Bayesian model, and a sample in the optimal distribution is selected to analyze and obtain an optimal battery production resource configuration. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0029] Figure 1 is a schematic diagram of the method flow of the present application. DETAILED DESCRIPTION

[0030] The present application will be further described below in combination with the drawings and specific embodiments, so that those skilled in the art can better understand the present application and implement it, but the embodiments are not limiting to the present application.

[0031] The application provides a battery production resource configuration method based on optimization theory, wherein the operation data of batteries in application scenarios under different production resource configurations are monitored, the batteries are scored according to the operation data,

[0032] The posterior distribution of the battery score is analyzed based on a Bayesian model,

[0033] The selection factor δ is determined according to the range of the battery score, the optimal distribution of the battery score is selected from the posterior distribution according to the selection factor δ, the corresponding sample is collected in the optimal distribution of the battery score, and the optimal battery production resource configuration is calculated and obtained.

[0034] In some embodiments of the method of the present application, the battery production resource is configured based on optimization theory, and the specific process is as follows:

[0035] Step 1: Monitor the running data of the battery produced under different resource configurations in the application scenario environment by using sensors, and record relevant data such as voltage, current, charge amount, etc.

[0036] Set a threshold value, if the fluctuation of voltage and current is less than the threshold value, it is normal working time, at the same time, record the final maximum charge amount of the battery, divide the final maximum capacity of the battery by the initial maximum capacity of the battery to get the final battery health degree, use the following formula:

[0037]

[0038] Carry out battery scoring;

[0039] Step 2: Obtain the posterior distribution of the battery score based on the Bayesian model analysis, wherein the prior distribution of the battery score under different production resource configurations is inferred from historical data. For convenience of description, it is assumed that there are K different production resource configurations, and the posterior distribution of the battery score under various resource configurations is calculated through the prior distribution;

[0040] Step 3: Use importance sampling to extract n0sample numbers from the posterior distribution of the battery score of each resource configuration, and record the samples extracted in the kth configuration as y1(θ k ),…,y n0 (θ k ), calculate the mean and variance of the three samples, respectively:

[0041]

[0042]

[0043]

[0044]

[0045] Set selection factor δ and critical value α, wherein δ is determined according to the range of the battery score, and the smaller the critical value α, the higher the reliability of the result, and generally set to 0.05,

[0046] And calculate t represents a multivariate t distribution, then through the formula:

[0047]

[0048] Extract n-n0samples from the posterior distribution of the battery score of each resource configuration by using importance sampling, and select the same random seed when extracting,

[0049] The n0 samples and n-n0 samples are combined to calculate by the formula:

[0050]

[0051] The minimum The corresponding is the optimal battery production resource allocation.

[0052] In the above embodiment, the operation data indicators of the battery can be collected by the sensor, and the battery score, i.e., the negative score, is calculated based on the collected data indicators. The lower the negative score is, the better the operation of the battery is. Meanwhile, the prior distribution of the negative score of the battery is calculated based on the historical data that can be collected. If the prior distribution is not good to calculate, the non-informative prior distribution can also be adopted. Then, the posterior distribution of the negative score of the battery is obtained according to the Bayes formula. Then, the two-stage indifference zone selection method is used. n0 samples are extracted from the posterior distribution in an importance sampling manner. The selection of n0 can be somewhat arbitrary. Then, appropriate delta and critical value alpha are selected to calculate the parameters required by the two-stage indifference zone selection method, and the minimum The corresponding production allocation is the optimal battery production allocation.

[0053] The application also provides a battery production resource allocation system based on the optimization theory, which comprises a monitoring module and an analysis module,

[0054] The monitoring module monitors the operation data of the battery in the application scenario under different production resource allocations, and the analysis module scores the battery based on the operation data. The posterior distribution of the battery score is obtained based on the Bayes model analysis. The selection factor delta is determined according to the range of the battery score. The optimal distribution of the battery score is selected from the posterior distribution according to the selection factor delta. The corresponding samples are collected in the optimal distribution of the battery score, and the optimal battery production resource allocation is obtained by calculation.

[0055] The information interaction and execution process between the modules in the above device are based on the same concept as the method embodiment of the application, and the specific content can be referred to the description in the method embodiment of the application, which will not be described here.

[0056] Similarly, the system of the application can collect the operation data of the battery in the application scenario under different production resource allocations, obtain the score of the battery, filter the optimal distribution in the posterior distribution of the battery score through the Bayes model, select the samples in the optimal distribution, and analyze the optimal battery production resource allocation. The optimal battery production resource allocation of the corresponding scenario is obtained by the method of the application, which can be further applied to the battery production and improve the battery production process.

[0057] The application also provides a battery production resource allocation device based on optimization theory, comprising at least one memory and at least one processor.

[0058] The at least one memory is configured to store machine-readable programs.

[0059] The at least one processor is configured to call the machine-readable programs and execute the battery production resource allocation method based on optimization theory.

[0060] The information interaction of the processor in the device, the execution of the readable programs and the like are based on the same concept as the method embodiments of the application, and the specific content can be referred to the description in the method embodiments of the application, which will not be described here. Similarly, the device of the application can obtain the scores of the batteries by collecting various operation data of the batteries in application scenarios under different production resource allocations, filter the optimal distribution in the posterior distribution of the battery scores through the Bayesian model, select samples in the optimal distribution, and analyze to obtain the optimized battery production resource allocation. The optimized battery production resource allocation in the corresponding scenario obtained through the method of the application can be further applied to battery production and improve the battery production process.

[0061] The application also provides a computer readable medium having computer instructions stored thereon, wherein the computer instructions, when executed by a processor, cause the processor to execute the battery production resource allocation method based on optimization theory. Specifically, a system or device equipped with a storage medium can be provided, wherein the storage medium stores software program codes for realizing the functions of any one of the above embodiments, and the computer (or CPU or MPU) of the system or device reads and executes the program codes stored in the storage medium.

[0062] In this case, the program codes read from the storage medium can realize the functions of any one of the above embodiments, and thus the program codes and the storage medium storing the program codes constitute a part of the application.

[0063] The storage medium for providing the program codes includes floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards and ROMs. Alternatively, the program codes can be downloaded from a server computer through a communication network.

[0064] In addition, it should be clear that not only the program codes read by the computer can be executed, but also the operating system and the like operating on the computer can be instructed based on the program codes to complete part or all of the actual operations, so as to realize the functions of any one of the above embodiments.

[0065] Further, it is understood that the programs read out from the storage medium can be written to the memories of an expansion board inserted into the computer or an expansion unit connected to the computer, and the CPU or the like mounted on the expansion board or the expansion unit is caused to perform part or all of the actual operations based on the instructions of the programs, thereby realizing the functions of any of the above-described embodiments.

[0066] It should be noted that not all the steps and modules in the above-described preferred embodiments of the processes and system structures are necessary, and some steps or modules can be omitted according to actual needs. The execution order of the steps is not fixed and can be adjusted according to needs. The system structures described in the above-described embodiments can be physical structures or logical structures, i.e., some modules can be implemented by the same physical entity, or some modules can be implemented by multiple physical entities, or some modules can be implemented by some components in multiple independent devices together.

[0067] The above-described embodiments are merely preferred embodiments of the present application for fully describing the present application, and the protection scope of the present application is not limited thereto. Any equivalent substitutions or transformations made by those skilled in the art based on the present application are within the protection scope of the present application. The protection scope of the present application is defined by the claims.

Claims

1. A battery production resource allocation system based on optimization theory, characterized by: Includes monitoring and analysis modules. The monitoring module monitors the battery's operational data under different production resource configurations in application scenarios, and the analysis module scores the battery based on the operational data, including: Use the following formula: A battery rating is performed, wherein the final battery health is obtained by dividing the final maximum battery capacity by the initial maximum battery capacity, the total test time is the operating time of the battery in the application scenario, and the normal operating time is the operating time of the battery within the voltage threshold and current threshold. Based on Bayesian model analysis, the posterior distribution of battery scores is obtained. A selection factor δ is determined according to the range of battery scores. The optimal distribution of battery scores is selected from the posterior distribution based on the selection factor δ. Samples are collected from the optimal distribution of battery scores to calculate the optimal battery production resource allocation. Specifically, importance sampling is used to extract n0 samples from the posterior distribution of battery scores for each resource allocation. The sample extracted from the k-th allocation is denoted as... Calculate the three sample means and sample variances as follows: A selection factor δ and a critical value α are set, where δ is determined based on the range of battery scores, and the smaller the critical value α, the higher the reliability of the results; it is generally set to 0.

05. And calculate t represents a multivariate t-distribution, and then the formula is used: From the posterior distribution of battery scores for each resource allocation, n-n0 samples are drawn using importance sampling, with the same random seed used during the sampling. The calculation combines n0 samples and n-n0 samples using the formula: Find the minimum This corresponds to the optimal allocation of battery production resources.

2. A resource allocation method for battery production based on optimization theory, characterized by: Monitor battery operating data under different production resource configurations in application scenarios, and score the batteries based on the operating data, including: Use the following formula: A battery rating is performed, wherein the final battery health is obtained by dividing the final maximum battery capacity by the initial maximum battery capacity, the total test time is the operating time of the battery in the application scenario, and the normal operating time is the operating time of the battery within the voltage threshold and current threshold. The posterior distribution of battery scores was obtained based on Bayesian model analysis. A selection factor δ is determined based on the range of battery scores. The optimal distribution of battery scores is selected from the posterior distribution based on the selection factor δ. Samples are collected from the optimal distribution of battery scores, and the optimal battery production resource allocation is calculated. Specifically, importance sampling is used to extract n0 samples from the posterior distribution of battery scores for each resource allocation. The sample extracted from the k-th allocation is denoted as... Calculate the three sample means and sample variances as follows: A selection factor δ and a critical value α are set, where δ is determined based on the range of battery scores, and the smaller the critical value α, the higher the reliability of the results; it is generally set to 0.

05. And calculate t represents a multivariate t-distribution, and then the formula is used: From the posterior distribution of battery scores for each resource allocation, n-n0 samples are drawn using importance sampling, with the same random seed used during the sampling. The calculation combines n0 samples and n-n0 samples using the formula: Find the minimum This corresponds to the optimal allocation of battery production resources.

3. A battery production resource allocation device based on optimization theory, characterized in that: include: At least one memory and at least one processor; The at least one memory is used to store a machine-readable program; The at least one processor is used to call the machine-readable program to execute the battery production resource allocation method based on optimization theory as described in claim 2.

4. A computer-readable medium, characterized in that The computer-readable medium stores computer instructions that, when executed by a processor, cause the processor to perform the battery production resource allocation method based on optimization theory as described in claim 2.

Images