CN-122022137-A - Battery echelon utilization method, system, equipment and medium based on digital twin

CN122022137ACN 122022137 ACN122022137 ACN 122022137ACN-122022137-A

Abstract

The invention relates to a battery echelon utilization method, a system, equipment and a medium based on digital twin. The state evaluation reliability of the current battery echelon utilization method is low, multi-factor comprehensive evaluation is not performed, scene matching is unreasonable, and a monitoring means is lacked. The method comprises the steps of collecting full life cycle data of the retired power battery, preprocessing, establishing a digital twin body model of the retired battery from a physical layer, a data layer, a model layer and an application layer, carrying out accurate SOH prediction on capacity, reliability and cycle life of the retired battery according to voltage, current, temperature, internal resistance and consistency of the retired battery through deep learning, carrying out echelon division on the retired battery through establishing a echelon division standard, and carrying out analog simulation on the retired battery through the digital twin body model to realize high-level interaction between an application scene and the echelon utilization battery. The invention has high reliability of state evaluation, multi-factor comprehensive evaluation, reasonable scene matching and monitoring means.

Inventors

HE CHUNYANG
Jia Cuncheng
Lan Qiaolixue
Xie xinfu
HAN YING
YANG WANXIN
HOU LEI
HUANG DENGQIANG
CHEN RUNWEN
MA LIHUA

Assignees

兰州铁道设计院有限公司

Dates

Publication Date: 20260512
Application Date: 20260116

Claims (10)

1. The battery cascade utilization method based on digital twin is characterized by comprising the following steps: Collecting full life cycle data of the retired power battery, and preprocessing the full life cycle data to obtain a data set; Establishing a digital twin model of the retired battery pack from a physical layer, a data layer, a model layer and an application layer through the data set, and correcting and perfecting parameters of the digital twin model; through the multi-field coupling characteristics of the digital twin body model and by combining deep learning, carrying out accurate SOH prediction on the capacity, reliability and cycle life of the retired battery pack according to the voltage, current, temperature, internal resistance and consistency of the retired battery pack; Performing echelon division on the retired battery pack by establishing a echelon division standard according to the capacity, the reliability and the cycle life of the retired battery pack; And combining industry standards, the voltage, the current, the temperature, the internal resistance and the consistency of the echelon battery, performing analog simulation through the digital twin body model, realizing the high-level interaction of an application scene and the echelon utilization battery, and performing self-adaptive correction and optimization on the digital twin body model through the measurement data of the actual retired battery pack to realize strategy matching under the condition of full flow.
2. The digital twin based battery cascade utilization method of claim 1, wherein: The full life cycle data comprises original factory data, service process data and retirement detection data.
3. The digital twin based battery cascade utilization method of claim 2, wherein: The original factory data comprise manufacturers, battery models, production batches, rated voltages, rated currents and material parameters, the service process data comprise cycle times, charge-discharge parameters, working temperature intervals and fault parameters, and the decommissioning detection data comprise appearance detection, internal resistance, capacity, consistency and cycle times.
4. The digital twin based battery cascade utilization method of claim 1, wherein: the preprocessing comprises denoising, screening, normalizing and normalizing the full life cycle data according to a set standard.
5. The digital twin based battery cascade utilization method of claim 1, wherein: the physical layer corresponds to the retired power battery entity, the data layer comprises full life cycle standardized data, the model layer integrates an electrochemical model, a thermal model, an attenuation model and a machine learning prediction model, and the application layer provides state evaluation, grading and scene matching.
6. The digital twin based battery cascade utilization method of claim 1, wherein: the deep learning adopts an LSTM neural network based on an attention mechanism, a Kalman filtering algorithm is fused to correct a prediction result, and the error of SOH prediction is not more than 3%.
7. The digital twin based battery cascade utilization method of claim 1, wherein: the gradient dividing standard is divided into five stages, wherein one stage corresponds to a high SOH battery (SOH is more than or equal to 80%), the gradient dividing standard is suitable for a distributed energy storage scene, the second stage corresponds to a medium-high SOH battery (SOH is more than or equal to 60% and is suitable for a common electric vehicle scene, the third stage corresponds to a medium SOH battery (SOH is more than or equal to 45% and is suitable for a non-primary site emergency power source scene, the fourth stage corresponds to a medium-low SOH battery (SOH is more than or equal to 30% and is suitable for a mobile power source and a street lamp scene, and the fifth stage corresponds to a low SOH battery (SOH is more than 30%), and the gradient utilization is not considered, so that a recovery flow is directly carried out.
8. The battery cascade utilization system based on digital twin is characterized by comprising the following components: the data acquisition and preprocessing module is used for acquiring various data of the retired power battery and preprocessing the various data to obtain a data set; the modeling and correction module is used for establishing a digital twin model of the retired battery pack from a physical layer, a data layer, a model layer and an application layer through the data set, and correcting and perfecting parameters of the digital twin model; the battery health state prediction module is used for carrying out accurate SOH prediction on the capacity, reliability and cycle life of the retired battery pack according to the voltage, current, temperature, internal resistance and consistency of the retired battery pack through the multi-field coupling characteristic of the digital twin body model and by combining deep learning; The echelon grade division module is used for carrying out echelon division on the retired battery pack by establishing a echelon division standard according to the capacity, the reliability and the cycle life of the retired battery pack; The scene matching and optimizing scheduling module is used for combining industry standards and the voltage, the current, the temperature, the internal resistance and the consistency of the echelon battery, performing analog simulation through the digital twin body model, realizing the high-level interaction of an application scene and the echelon utilization battery, performing self-adaptive correction and optimization on the digital twin body model through the measurement data of the actual retired battery pack, and realizing strategy matching under the condition of full flow.
9. A battery cascade utilization device based on digital twinning, characterized by comprising a processor (1), a memory (5), a user interface (3) and a network interface (4), the memory (5) being used for storing instructions, the user interface (3) and the network interface (4) being used for communicating to other devices, the processor (1) being used for executing the instructions stored in the memory (5) for causing an electronic device to perform the method according to any of claims 1-7.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed, perform the method of any of claims 1-7.

Description

Battery echelon utilization method, system, equipment and medium based on digital twin Technical Field The invention relates to the technical field of battery management, in particular to a battery echelon utilization method, system, equipment and medium based on digital twin. Background At present, the first new energy electric automobile carries the battery pack to achieve the updating iteration period, and the quantity of the retired battery packs can be rapidly increased along with the subsequent iteration updating of more battery packs, and because the batteries belong to high-pollution materials, in order to realize resource circulation and reduce pollution, the retired battery packs are secondarily utilized, and the retired battery packs are required to be subjected to gradient utilization design according to a certain classification rule. The problems of the traditional battery in the market are not related to unified standards, different places and enterprises are inconsistent in State evaluation methods and indexes of the retired battery, partial test data have a plurality of problems of single test, insufficient data volume, insufficient realization cycle times and the like, so that the judgment deviation of the battery Health State (State of Health, SOH) is large, meanwhile, the instruction manual in different places is inconsistent in parameters aiming at the gradient dividing process, some enterprises adopt single factor evaluation methods, the single factor evaluation methods cannot comprehensively evaluate the stability evaluation standards of the prepared retired battery from a plurality of factors such as capacity, voltage, internal resistance and consistency, the reliability evaluation standards of the prepared retired battery have uncertainty, the gradient dividing principle and scheme are not careful, so that the retired battery is wasted in the secondary utilization process, and the problem is that the retired battery is lack of related monitoring means in the gradient utilization process, the analysis and judgment of operation data are not standardized, the normalization is effectively judged, so that partial fault points are not found in time, so that the reliability evaluation standards of the retired battery is seriously hindered, the gradient utilization of the safety and the reliability of the industrial scale are severely developed, and the reliability of the retired battery is severely developed, and the reliability of the industrial scale is restricted. Therefore, there is a need for a battery cascade utilization method with high reliability of state evaluation, multi-factor comprehensive evaluation, reasonable scene matching, and monitoring means. Disclosure of Invention The invention aims to provide a battery cascade utilization method, a system, equipment and a medium based on digital twinning, which at least solve the problems that the state evaluation reliability of the current battery cascade utilization method is low, multi-factor comprehensive evaluation is not performed, scene matching is unreasonable and a monitoring means is lacked. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows: the battery echelon utilization method based on digital twin comprises the following steps: Collecting full life cycle data of the retired power battery, and preprocessing the full life cycle data to obtain a data set; Establishing a digital twin model of the retired battery pack from a physical layer, a data layer, a model layer and an application layer through a data set, and correcting and perfecting parameters of the digital twin model; Through the multi-field coupling characteristic of the digital twin body model and by combining deep learning, carrying out accurate SOH prediction on the capacity, reliability and cycle life of the retired battery pack according to the voltage, current, temperature, internal resistance and consistency of the retired battery pack; performing echelon division on the retired battery pack by establishing a echelon division standard according to the capacity, reliability and cycle life of the retired battery pack; by combining industry standards and voltage, current, temperature, internal resistance and consistency of the echelon battery, analog simulation is carried out through the digital twin body model, so that high inter-matching of an application scene and the echelon utilization battery is realized, and the digital twin body model is adaptively corrected and optimized through measurement data of an actual retired battery pack, so that strategy matching under the condition of full flow is realized. Further, the full life cycle data includes original factory data, service process data and retirement detection data. Further, the original factory data comprise manufacturers, battery models, production batches, rated voltages, rated currents and material parameters, the service process data comprise cycle