CN107422266A - A kind of method for diagnosing faults and device of high capacity cell energy-storage system - Google Patents

A kind of method for diagnosing faults and device of high capacity cell energy-storage system Download PDF

Info

Publication number
CN107422266A
CN107422266A CN201710153380.6A CN201710153380A CN107422266A CN 107422266 A CN107422266 A CN 107422266A CN 201710153380 A CN201710153380 A CN 201710153380A CN 107422266 A CN107422266 A CN 107422266A
Authority
CN
China
Prior art keywords
mrow
msub
msubsup
battery
neural network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201710153380.6A
Other languages
Chinese (zh)
Other versions
CN107422266B (en
Inventor
李建林
赵泽昆
马会萌
谢志佳
修晓青
惠东
田春光
吕项羽
李德鑫
常学飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
Electric Power Research Institute of State Grid Jilin Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
Electric Power Research Institute of State Grid Jilin Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, China Electric Power Research Institute Co Ltd CEPRI, Electric Power Research Institute of State Grid Jilin Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN201710153380.6A priority Critical patent/CN107422266B/en
Publication of CN107422266A publication Critical patent/CN107422266A/en
Application granted granted Critical
Publication of CN107422266B publication Critical patent/CN107422266B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/3644—Constructional arrangements
    • G01R31/3648—Constructional arrangements comprising digital calculation means, e.g. for performing an algorithm
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Secondary Cells (AREA)

Abstract

本发明涉及一种大容量电池储能系统的故障诊断方法及装置，包括获取电池储能系统的待诊断数据；将所述待诊断数据作为测试样本输入预先构建的BP神经网络模型进行故障诊断，输出故障诊断结果。本方案的提出有效解决了大容量电池储能系统故障诊断困难的问题，使得故障诊断具有较高的准确性。

The present invention relates to a method and device for fault diagnosis of a large-capacity battery energy storage system, including acquiring data to be diagnosed of the battery energy storage system; inputting the data to be diagnosed as a test sample into a pre-built BP neural network model for fault diagnosis, Output fault diagnosis results. The proposal of this scheme effectively solves the problem of difficult fault diagnosis of large-capacity battery energy storage systems, making fault diagnosis more accurate.

Description

一种大容量电池储能系统的故障诊断方法及装置Fault diagnosis method and device for a large-capacity battery energy storage system

技术领域technical field

本发明属于储能技术领域,具体涉及一种大容量电池储能系统的故障诊断方法及装置。The invention belongs to the technical field of energy storage, and in particular relates to a fault diagnosis method and device for a large-capacity battery energy storage system.

背景技术Background technique

能源危机和全球变暖等问题促使风能、太阳能等可再生能源已经深入人类生活的各个领域。为了支持绿色技术的发展，大容量电池储能系统应运而生。大容量电池储能系统一般由成千上万个电池单体串并联形成，由于电池单体数目众多，电池单体是否发生故障很难及时准确检测，电池单体的故障往往会危及整个储能系统，而储能系统的安全性与稳定性直接影响电力设备乃至整个电力系统的安全与稳定，因此对大容量电池储能系统故障诊断进行研究具有重要意义。Issues such as the energy crisis and global warming have prompted renewable energy such as wind energy and solar energy to penetrate into various fields of human life. In order to support the development of green technology, large-capacity battery energy storage systems came into being. A large-capacity battery energy storage system is generally formed by connecting thousands of battery cells in series and parallel. Due to the large number of battery cells, it is difficult to detect whether a battery cell fails in time and accurately, and the failure of a battery cell often endangers the entire energy storage system. The safety and stability of the energy storage system directly affect the safety and stability of the power equipment and the entire power system, so it is of great significance to study the fault diagnosis of the large-capacity battery energy storage system.

发明内容Contents of the invention

为了弥补上述技术空白，本发明根据大容量电池储能系统的特点，提供一种大容量电池储能系统的故障诊断方法及装置，结合遗传算法对BP神经网络进行优化，为大容量电池储能系统故障诊断提供了新的方向。In order to make up for the above-mentioned technical gap, the present invention provides a fault diagnosis method and device for a large-capacity battery energy storage system according to the characteristics of the large-capacity battery energy storage system, and optimizes the BP neural network in combination with a genetic algorithm to provide a large-capacity battery energy storage system. System fault diagnosis provides a new direction.

本发明的目的是采用下述技术方案实现的：The object of the present invention is to adopt following technical scheme to realize:

一种大容量电池储能系统的故障诊断方法，所述方法包括：A fault diagnosis method for a large-capacity battery energy storage system, the method comprising:

获取电池储能系统的待诊断数据；Obtain the data to be diagnosed of the battery energy storage system;

将所述待诊断数据作为测试样本输入预先构建的BP神经网络模型进行故障诊断，输出故障诊断结果；Using the data to be diagnosed as a test sample input pre-built BP neural network model for fault diagnosis, output fault diagnosis results;

其中，所述预先构建的BP神经网络模型是对电池单体的端电压信号电池储能系统的端电压信号Ui和电流信号Ii提取电池单体欧姆内阻的样本熵、电池组的惩罚因子Adi和电池单体端电压变化量的隶属度fknti作为训练样本进行训练得到的。Wherein, the pre-built BP neural network model is the terminal voltage signal of the battery cell The terminal voltage signal U i and current signal I i of the battery energy storage system extract the ohmic internal resistance of the battery cell The sample entropy of the battery pack, the penalty factor Ad i of the battery pack and the variation of the terminal voltage of the battery cell The degree of membership f knti is obtained as a training sample for training.

优选的，所述BP神经网络模型的构建过程为：Preferably, the construction process of the BP neural network model is:

通过采集卡采集电池单体的端电压信号电池储能系统的端电压信号Ui和电流信号Ii；Collect the terminal voltage signal of the battery cell through the acquisition card Terminal voltage signal U i and current signal I i of the battery energy storage system;

对采集到的上述信号进行特征向量提取，并对特征向量进行归一化处理；所述特征向量包括电池单体欧姆内阻的样本熵、电池组的惩罚因子Adi和电池单体端电压变化量的隶属度fknti；Extracting the eigenvectors of the above-mentioned collected signals, and normalizing the eigenvectors; the eigenvectors include the ohmic internal resistance of the battery cell The sample entropy of the battery pack, the penalty factor Ad i of the battery pack and the variation of the terminal voltage of the battery cell The degree of membership f knti ;

将归一化处理后的特征向量输入初始BP神经网络，利用遗传算法对所述初始BP神经网络的权值进行优化；The eigenvector after the normalization process is input into the initial BP neural network, and the weight value of the initial BP neural network is optimized by genetic algorithm;

对优化后的BP神经网络进行训练，得到最终的BP神经网络模型。The optimized BP neural network is trained to obtain the final BP neural network model.

进一步地，通过下式确定电池单体欧姆内阻的样本熵：Further, the sample entropy of the ohmic internal resistance of the battery cell is determined by the following formula:

式中，为第k个电池单体在第i个采样点的端电压，为第k个电池单体在第i个采样点的欧姆内阻，为的概率密度，n为采样点的个数，H(Rk)为第k个电池单体欧姆内阻的熵。In the formula, is the terminal voltage of the kth battery cell at the ith sampling point, is the ohmic internal resistance of the k-th battery cell at the i-th sampling point, for The probability density of , n is the number of sampling points, H(R k ) is the entropy of the ohmic internal resistance of the kth battery cell.

进一步地，通过下式确定电池组的惩罚因子Adi：Further, the penalty factor Ad i of the battery pack is determined by the following formula:

式中，Ii和Ui分别为电池储能系统第i个采样点的电流值和电压值。In the formula, I i and U i are the current value and voltage value of the i-th sampling point of the battery energy storage system, respectively.

进一步地，通过下式确定电池单体端电压变化量的隶属度：Further, the membership degree of battery cell terminal voltage variation is determined by the following formula:

式中，fsta为电池储能系统的状态函数，fcha为电池储能系统的外部特性函数，n为采样点的个数，C为电池储能系统外部特性的某种程度的相对系数，m为电池单体的个数；fknti表示第k个电池的第i个采样点电压变化量的隶属度。In the formula, f sta is the state function of the battery energy storage system, f cha is the external characteristic function of the battery energy storage system, n is the number of sampling points, C is a certain degree of relative coefficient of the external characteristics of the battery energy storage system, m is the number of battery cells; f knti represents the voltage variation of the i-th sampling point of the k-th battery degree of membership.

进一步地，所述对特征向量进行归一化处理包括：Further, said normalizing the eigenvectors includes:

设特征向量T＝[H(Rk),Adi,fknti]，并对其进行归一化处理，则归一化处理后的特征向量T'＝[H(Rk)/Ek,Adi/Ek,fknti/Ek]，Let feature vector T=[H(R k ),Ad i ,f knti ], and normalize it, then the feature vector after normalization T'=[H(R k )/E k , Ad i /E k , f knti /E k ],

其中，T’为归一化处理后特征向量，fknti为第k个电池的第i个采样点电压变化量的隶属度，H(Rk)为第k个电池单体欧姆内阻的熵，Adi为电池组的惩罚因子。Among them, T' is the feature vector after normalization processing, f knti is the voltage variation of the i-th sampling point of the k-th battery degree of membership, H(R k ) is the ohmic internal resistance of the kth battery cell entropy, Ad i is the penalty factor of the battery pack.

优选的，所述BP神经网络模型的输出F＝[F1,F2,F3,F4]，F1表示电池单体无故障，F2表示电池单体内阻增大，F3表示电池单体容量减小，F4表示电池单体短路，F1、F2、F3、F4的取值为0或1，1表示该故障存在，0表示该故障不存在。Preferably, the output F=[F1, F2, F3, F4] of the BP neural network model, F1 indicates that the battery cell has no fault, F2 indicates that the internal resistance of the battery cell increases, F3 indicates that the capacity of the battery cell decreases, and F4 Indicates that the battery cell is short-circuited. The values of F1, F2, F3, and F4 are 0 or 1. 1 indicates that the fault exists, and 0 indicates that the fault does not exist.

进一步地，所述利用遗传算法对所述初始BP神经网络的权值进行优化包括：Further, said utilizing genetic algorithm to optimize the weight of said initial BP neural network comprises:

确定当前种群中每个个体的适应度函数f(x)，选择适应度函数最高或最低的m个个体；初始种群包括BP神经网络模型中的初始权重值和阈值编码；Determine the fitness function f(x) of each individual in the current population, and select m individuals with the highest or lowest fitness function; the initial population includes initial weight values and threshold codes in the BP neural network model;

对所述m个个体进行遗传、交叉和变异操作，直至满足预设的终止条件并将当前满足终止条件的个体定义为最优权值阈值。Perform genetic, crossover, and mutation operations on the m individuals until the preset termination condition is met, and the individual currently meeting the termination condition is defined as the optimal weight threshold.

进一步地，所述种群中每个个体的适应度函数为f(x)＝(P'-P)2，其中，f(x)表示适应度函数，P'为测试样本集的预测值，P为测试样本集的真实值；Further, the fitness function of each individual in the population is f(x)=(P'-P) 2 , where f(x) represents the fitness function, P' is the predicted value of the test sample set, and P is the true value of the test sample set;

所述预设的终止条件为：f(x)≤δ；其中，δ表示预设的交叉和变异概率。The preset termination condition is: f(x)≤δ; wherein, δ represents a preset crossover and mutation probability.

一种大容量电池储能系统的故障诊断装置，所述装置包括：A fault diagnosis device for a large-capacity battery energy storage system, the device comprising:

模型构建模块，用于预先对以电池单体的端电压信号电池储能系统的端电压信号Ui和电流信号Ii为输入的训练样本进行训练，得到BP神经网络模型；Model building blocks for pre-sampling battery cell terminal voltage signals The terminal voltage signal U i and current signal I i of the battery energy storage system are trained as input training samples to obtain a BP neural network model;

获取模块，用于获取电池储能系统的待诊断数据；An acquisition module, configured to acquire the data to be diagnosed of the battery energy storage system;

诊断模块，用于将所述待诊断数据作为测试样本输入所述预先构建的BP神经网络模型进行故障诊断，输出故障诊断结果。The diagnostic module is used to input the data to be diagnosed as a test sample into the pre-built BP neural network model for fault diagnosis, and output a fault diagnosis result.

优选的，所述模型构建模块包括：Preferably, the model building blocks include:

采集单元，用于通过采集卡采集电池单体的端电压信号电池储能系统的端电压信号Ui和电流信号Ii；The acquisition unit is used to acquire the terminal voltage signal of the battery cell through the acquisition card Terminal voltage signal U i and current signal I i of the battery energy storage system;

处理单元，用于对采集到的上述信号进行特征向量提取，并对特征向量进行归一化处理；所述特征向量包括电池单体欧姆内阻的样本熵、电池组的惩罚因子Adi和电池单体端电压变化量的隶属度fknti；The processing unit is used to extract the eigenvectors of the above-mentioned collected signals, and perform normalization processing on the eigenvectors; the eigenvectors include the ohmic internal resistance of the battery cell The sample entropy of the battery pack, the penalty factor Ad i of the battery pack and the variation of the terminal voltage of the battery cell The degree of membership f knti ;

优化单元，用于将归一化处理后的特征向量输入初始BP神经网络，利用遗传算法对所述初始BP神经网络的权值进行优化；An optimization unit, configured to input the normalized eigenvector into the initial BP neural network, and optimize the weights of the initial BP neural network using a genetic algorithm;

训练单元，用于对优化后的BP神经网络进行训练，得到最终的BP神经网络模型。The training unit is used to train the optimized BP neural network to obtain the final BP neural network model.

与最接近的现有技术相比，本发明的有益效果为：Compared with the closest prior art, the beneficial effects of the present invention are:

本发明方案一种大容量电池储能系统的故障诊断方法及装置，根据电池储能系统的特点，将归一化处理后的电池单体欧姆内阻的样本熵、电池组的惩罚因子和电池单体端电压变化量的隶属度作为初始BP神经网络的输入，利用遗传算法(Genetic algorithm,GA)对初始BP神经网络的权值进行优化，是解决大容量电池储能系统故障诊断问题的重要研究方向。The present invention proposes a fault diagnosis method and device for a large-capacity battery energy storage system. According to the characteristics of the battery energy storage system, the normalized sample entropy of the ohmic internal resistance of the battery cell, the penalty factor of the battery pack, and the battery The membership degree of the change of the cell terminal voltage is used as the input of the initial BP neural network, and the weight value of the initial BP neural network is optimized by using the genetic algorithm (Genetic algorithm, GA). research direction.

其次，对优化后的BP神经网络进行训练，最终得到BP神经网络模型；使得该BP神经网络模型具备了同时诊断多种故障的能力，能够实现以判断电池储能系统故障的特征量作为测试样本的故障诊断，并输出准确的诊断结果。为大容量电池储能系统故障诊断提供了重要的技术支撑；从而解决大容量电池储能系统故障诊断困难的问题，使得故障诊断具有较高的准确性。Secondly, the optimized BP neural network is trained, and finally the BP neural network model is obtained; the BP neural network model has the ability to diagnose multiple faults at the same time, and can realize the feature quantity for judging the fault of the battery energy storage system as a test sample fault diagnosis, and output accurate diagnosis results. It provides important technical support for the fault diagnosis of large-capacity battery energy storage systems; thereby solving the problem of difficult fault diagnosis of large-capacity battery energy storage systems, making fault diagnosis more accurate.

附图说明Description of drawings

图1为本发明实施例中提供的大容量电池储能系统的故障诊断方法流程图；Fig. 1 is a flowchart of a fault diagnosis method for a large-capacity battery energy storage system provided in an embodiment of the present invention;

图2为本发明实施例中提供的利用遗传算法对初始BP神经网络的权值进行优化方法流程图；Fig. 2 is the flow chart of the method for optimizing the weights of the initial BP neural network using a genetic algorithm provided in an embodiment of the present invention;

图3为本发明实施例中提供的BP神经网络模型示意图。Fig. 3 is a schematic diagram of a BP neural network model provided in an embodiment of the present invention.

具体实施方式：detailed description:

一种大容量电池储能系统的故障诊断方法，如图1所示，所述方法包括：A method for fault diagnosis of a large-capacity battery energy storage system, as shown in Figure 1, said method comprising:

获取电池储能系统的待诊断数据；Obtain the data to be diagnosed of the battery energy storage system;

将所述待诊断数据作为测试样本输入预先构建的BP神经网络模型进行故障诊断，输出故障诊断结果。The data to be diagnosed is input into the pre-built BP neural network model as a test sample for fault diagnosis, and the fault diagnosis result is output.

其中，(一)BP神经网络模型的构建过程为：Among them, (1) the construction process of BP neural network model is:

1、通过采集卡采集电池单体的端电压信号电池储能系统的端电压信号Ui和电流信号Ii；1. Collect the terminal voltage signal of the battery cell through the acquisition card Terminal voltage signal U i and current signal I i of the battery energy storage system;

2、对采集到的上述信号进行特征向量提取，并对特征向量进行归一化处理；所述特征向量包括电池单体欧姆内阻的样本熵、电池组的惩罚因子Adi和电池单体端电压变化量的隶属度fknti；2. Extract the eigenvectors of the above-mentioned collected signals, and normalize the eigenvectors; the eigenvectors include the ohmic internal resistance of the battery cell The sample entropy of the battery pack, the penalty factor Ad i of the battery pack and the variation of the terminal voltage of the battery cell The degree of membership f knti ;

通过下式确定电池单体欧姆内阻的样本熵：The sample entropy of the ohmic internal resistance of the battery cell is determined by the following formula:

式中，为第k个电池单体在第i个采样点的端电压，为第k个电池单体在第i个采样点的欧姆内阻，为的概率密度，n为采样点的个数，H(Rk)为第k个电池单体欧姆内阻的熵。In the formula, is the terminal voltage of the kth battery cell at the ith sampling point, is the ohmic internal resistance of the k-th battery cell at the i-th sampling point, for The probability density of , n is the number of sampling points, H(R k ) is the entropy of the ohmic internal resistance of the kth battery cell.

通过下式确定电池组的惩罚因子Adi：The penalty factor Ad i of the battery pack is determined by the following formula:

式中，Ii和Ui分别为电池储能系统第i个采样点的电流值和电压值。In the formula, I i and U i are the current value and voltage value of the i-th sampling point of the battery energy storage system, respectively.

通过下式确定电池单体端电压变化量的隶属度：The degree of membership of the battery cell terminal voltage variation is determined by the following formula:

式中，fsta为电池储能系统的状态函数，fcha为电池储能系统的外部特性函数，n为采样点的个数，C为电池储能系统外部特性的某种程度的相对系数，m为电池单体的个数；fknti表示第k个电池的第i个采样点电压变化量的隶属度。In the formula, f sta is the state function of the battery energy storage system, f cha is the external characteristic function of the battery energy storage system, n is the number of sampling points, C is a certain degree of relative coefficient of the external characteristics of the battery energy storage system, m is the number of battery cells; f knti represents the voltage variation of the i-th sampling point of the k-th battery degree of membership.

3、将归一化处理后的特征向量输入初始BP神经网络，利用遗传算法对所述初始BP神经网络的权值进行优化；3. Input the normalized eigenvector into the initial BP neural network, and optimize the weight of the initial BP neural network by genetic algorithm;

设特征向量T＝[H(Rk),Adi,fknti]，并对其进行归一化处理，则归一化处理后的特征向量T'＝[H(Rk)/Ek,Adi/Ek,fknti/Ek]，Let feature vector T=[H(R k ),Ad i ,f knti ], and normalize it, then the feature vector after normalization T'=[H(R k )/E k , Ad i /E k , f knti /E k ],

其中，T’为归一化处理后特征向量，fknti为第k个电池的第i个采样点电压变化量的隶属度，H(Rk)为第k个电池单体欧姆内阻的熵，Adi为电池组的惩罚因子。Among them, T' is the feature vector after normalization processing, f knti is the voltage variation of the i-th sampling point of the k-th battery degree of membership, H(R k ) is the ohmic internal resistance of the kth battery cell entropy, Ad i is the penalty factor of the battery pack.

如图2所示，利用遗传算法对所述初始BP神经网络的权值进行优化包括：As shown in Figure 2, using genetic algorithm to optimize the weights of the initial BP neural network includes:

确定当前种群中每个个体的适应度函数f(x)，选择适应度函数最高或最低的m个个体；初始种群包括BP神经网络模型中的初始权重值和阈值编码；Determine the fitness function f(x) of each individual in the current population, and select m individuals with the highest or lowest fitness function; the initial population includes initial weight values and threshold codes in the BP neural network model;

对所述m个个体进行遗传、交叉和变异操作，直至满足预设的终止条件并将当前满足终止条件的个体定义为最优权值阈值。Perform genetic, crossover, and mutation operations on the m individuals until the preset termination condition is met, and the individual currently meeting the termination condition is defined as the optimal weight threshold.

种群中每个个体的适应度函数为f(x)＝(P'-P)2，其中，f(x)表示适应度函数，P'为测试样本集的预测值，P为测试样本集的真实值；The fitness function of each individual in the population is f(x)=(P'-P) 2 , where f(x) represents the fitness function, P' is the predicted value of the test sample set, and P is the test sample set actual value;

所述预设的终止条件为：f(x)≤δ，δ＝0.05；其中，δ表示预设的交叉和变异概率。The preset termination condition is: f(x)≤δ, δ=0.05; wherein, δ represents a preset crossover and mutation probability.

4、对优化后的BP神经网络进行训练，得到最终的BP神经网络模型，如图3所示。其中，构建的BP神经网络模型是对电池单体的端电压信号电池储能系统的端电压信号Ui和电流信号Ii提取电池单体欧姆内阻的样本熵、电池组的惩罚因子Adi和电池单体端电压变化量的隶属度fknti作为训练样本进行训练得到的。4. Train the optimized BP neural network to obtain the final BP neural network model, as shown in FIG. 3 . Among them, the constructed BP neural network model is the terminal voltage signal of the battery cell The terminal voltage signal U i and current signal I i of the battery energy storage system extract the ohmic internal resistance of the battery cell The sample entropy of the battery pack, the penalty factor Ad i of the battery pack and the variation of the terminal voltage of the battery cell The degree of membership f knti is obtained as a training sample for training.

(二)最终利用BP神经网络模型进行故障诊断，输出故障诊断结果F＝[F1,F2,F3,F4]，F1表示电池单体无故障，F2表示电池单体内阻增大，F3表示电池单体容量减小，F4表示电池单体短路，F1、F2、F3、F4的取值为0或1，1表示该故障存在，0表示该故障不存在。(2) Finally, the BP neural network model is used for fault diagnosis, and the output fault diagnosis result is F=[F1, F2, F3, F4]. When the battery capacity decreases, F4 indicates that the battery cell is short-circuited. The values of F1, F2, F3, and F4 are 0 or 1. 1 indicates that the fault exists, and 0 indicates that the fault does not exist.

基于同一发明构思，本发明还提出一种大容量电池储能系统的故障诊断装置，包括：Based on the same inventive concept, the present invention also proposes a fault diagnosis device for a large-capacity battery energy storage system, including:

模型构建模块，用于预先对以电池单体的端电压信号电池储能系统的端电压信号Ui和电流信号Ii为输入的训练样本进行训练，得到BP神经网络模型；Model building blocks for pre-sampling battery cell terminal voltage signals The terminal voltage signal U i and current signal I i of the battery energy storage system are trained as input training samples to obtain a BP neural network model;

获取模块，用于获取电池储能系统的待诊断数据；An acquisition module, configured to acquire the data to be diagnosed of the battery energy storage system;

诊断模块，用于将所述待诊断数据作为测试样本输入所述预先构建的BP神经网络模型进行故障诊断，输出故障诊断结果。The diagnostic module is used to input the data to be diagnosed as a test sample into the pre-built BP neural network model for fault diagnosis, and output a fault diagnosis result.

其中，模型构建模块包括：Among them, the model building blocks include:

采集单元，用于通过采集卡采集电池单体的端电压信号电池储能系统的端电压信号Ui和电流信号Ii；The acquisition unit is used to acquire the terminal voltage signal of the battery cell through the acquisition card Terminal voltage signal U i and current signal I i of the battery energy storage system;

处理单元，用于对采集到的上述信号进行特征向量提取，并对特征向量进行归一化处理；所述特征向量包括电池单体欧姆内阻的样本熵、电池组的惩罚因子Adi和电池单体端电压变化量的隶属度fknti；The processing unit is used to extract the eigenvectors of the above-mentioned collected signals, and perform normalization processing on the eigenvectors; the eigenvectors include the ohmic internal resistance of the battery cell The sample entropy of the battery pack, the penalty factor Ad i of the battery pack and the variation of the terminal voltage of the battery cell The degree of membership f knti ;

优化单元，用于将归一化处理后的特征向量输入初始BP神经网络，利用遗传算法对所述初始BP神经网络的权值进行优化；An optimization unit, configured to input the normalized eigenvector into the initial BP neural network, and optimize the weights of the initial BP neural network using a genetic algorithm;

训练单元，用于对优化后的BP神经网络进行训练，得到最终的BP神经网络模型。The training unit is used to train the optimized BP neural network to obtain the final BP neural network model.

本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。The present application is described with reference to flowcharts and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

最后应当说明的是：以上实施例仅用以说明本申请的技术方案而非对其保护范围的限制，尽管参照上述实施例对本申请进行了详细的说明，所属领域的普通技术人员应当理解：本领域技术人员阅读本申请后依然可对申请的具体实施方式进行种种变更、修改或者等同替换，这些变更、修改或者等同替换，其均在其申请待批的权利要求范围之内。Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application rather than to limit its protection scope. Although the present application has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: After reading this application, those skilled in the art can still make various changes, modifications or equivalent replacements to the specific implementation methods of the application. These changes, modifications or equivalent replacements are all within the scope of the pending claims of the application.

Claims (11)

1. A fault diagnosis method for a high-capacity battery energy storage system is characterized by comprising the following steps:
acquiring data to be diagnosed of the battery energy storage system;
inputting the data to be diagnosed as a test sample into a pre-constructed BP neural network model for fault diagnosis, and outputting a fault diagnosis result;
wherein the pre-constructed BP neural network model is terminal voltage signal of the battery cellTerminal voltage signal U of battery energy storage systemiAnd a current signal IiExtracting the ohmic internal resistance of the battery monomerSample entropy of (1), penalty factor Ad of battery packiAnd cell terminal voltage variationDegree of membership fkntiObtained by training as a training sample.
2. The method of claim 1, wherein the BP neural network model is constructed by:
collecting terminal voltage signals of battery monomers through collection cardTerminal voltage signal U of battery energy storage systemiAnd a current signal Ii；
Extracting a characteristic vector of the collected signals, and normalizing the characteristic vector; the characteristic vector comprises the ohmic internal resistance of the battery cellSample entropy of (1), penalty factor Ad of battery packiAnd cell terminal voltage variationDegree of membership fknti；
Inputting the normalized feature vector into an initial BP neural network, and optimizing the weight of the initial BP neural network by using a genetic algorithm;
and training the optimized BP neural network to obtain a final BP neural network model.
3. The method of claim 2, wherein the sample entropy of the ohmic internal resistance of the cell is determined by:
<mrow> <msubsup> <mi>R</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>=</mo> <mfrac> <msubsup> <mi>U</mi> <mi>i</mi> <mi>k</mi> </msubsup> <msub> <mi>I</mi> <mi>i</mi> </msub> </mfrac> </mrow>
<mrow> <mi>H</mi> <mrow> <mo>(</mo> <msup> <mi>R</mi> <mi>k</mi> </msup> <mo>)</mo> </mrow> <mo>=</mo> <mo>-</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <mi>p</mi> <mrow> <mo>(</mo> <msubsup> <mi>R</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>)</mo> </mrow> <mi>log</mi> <mi> </mi> <mi>p</mi> <mrow> <mo>(</mo> <msubsup> <mi>R</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>)</mo> </mrow> </mrow>
in the formula,for the terminal voltage of the kth cell at the ith sampling point,for the ohmic internal resistance of the kth cell at the ith sampling point,is composed ofN is the number of sample points, H (R)k) The entropy of the k-th cell ohmic internal resistance.
4. The method of claim 2, wherein the penalty factor Ad for a battery is determined by the following equationi：
<mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <msub> <mi>Ad</mi> <mi>i</mi> </msub> <mo>=</mo> <mrow> <mo>(</mo> <msub> <mi>U</mi> <mi>i</mi> </msub> <mo>-</mo> <msub> <mi>U</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <msub> <mi>I</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>-</mo> <mrow> <mo>(</mo> <msub> <mi>U</mi> <mi>i</mi> </msub> <mo>-</mo> <msub> <mi>U</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <msub> <mi>I</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>|</mo> <mi>tanh</mi> <mrow> <mo>(</mo> <msub> <mi>&amp;Delta;I</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>|</mo> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>tanh</mi> <mrow> <mo>(</mo> <msub> <mi>&amp;Delta;I</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <mrow> <mi>sinh</mi> <mrow> <mo>(</mo> <msub> <mi>&amp;Delta;I</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> </mrow> <mrow> <mi>cosh</mi> <mrow> <mo>(</mo> <msub> <mi>&amp;Delta;I</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> </mrow> </mfrac> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>&amp;Delta;I</mi> <mi>i</mi> </msub> <mo>=</mo> <msub> <mi>I</mi> <mi>i</mi> </msub> <mo>-</mo> <msub> <mi>I</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> </mrow> </mtd> </mtr> </mtable> </mfenced>
In the formula IiAnd UiThe current value and the voltage value of the ith sampling point of the battery energy storage system are respectively.
5. The method of claim 2, wherein the degree of membership of the amount of change in terminal voltage of the battery cell is determined by:
<mrow> <msub> <mi>f</mi> <mrow> <mi>k</mi> <mi>n</mi> <mi>t</mi> <mi>i</mi> </mrow> </msub> <mo>=</mo> <msub> <mi>f</mi> <mrow> <mi>s</mi> <mi>t</mi> <mi>a</mi> </mrow> </msub> <mo>*</mo> <msub> <mi>f</mi> <mrow> <mi>c</mi> <mi>h</mi> <mi>a</mi> </mrow> </msub> <mrow> <mo>(</mo> <msubsup> <mi>&amp;Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>)</mo> </mrow> </mrow>1
<mrow> <msub> <mi>f</mi> <mrow> <mi>c</mi> <mi>h</mi> <mi>a</mi> </mrow> </msub> <mrow> <mo>(</mo> <msubsup> <mi>&amp;Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>)</mo> </mrow> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mi>n</mi> <mo>*</mo> <mfrac> <mrow> <msubsup> <mi>&amp;Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> </mrow> <mrow> <mi>C</mi> <munderover> <mi>&amp;Sigma;</mi> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>m</mi> </munderover> <msubsup> <mi>&amp;Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> </mrow> </mfrac> <mn>...</mn> <msubsup> <mi>&amp;Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>&amp;le;</mo> <mfrac> <mrow> <mi>C</mi> <munderover> <mi>&amp;Sigma;</mi> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>m</mi> </munderover> <msubsup> <mi>&amp;Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> </mrow> <mi>n</mi> </mfrac> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mn>1...</mn> <msubsup> <mi>&amp;Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>&gt;</mo> <mfrac> <mrow> <mi>C</mi> <munderover> <mi>&amp;Sigma;</mi> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>m</mi> </munderover> <msubsup> <mi>&amp;Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> </mrow> <mi>n</mi> </mfrac> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>
in the formula (f)staAs a function of the state of the battery energy storage system, fchaThe method comprises the following steps of taking an external characteristic function of the battery energy storage system, wherein n is the number of sampling points, C is a relative coefficient of a certain degree of the external characteristic of the battery energy storage system, and m is the number of single batteries; f. ofkntiIndicating voltage variation of ith sampling point of kth batteryDegree of membership.
6. The method of claim 2, wherein the normalizing the feature vectors comprises:
let the feature vector T ═ H (R)k),Adi,fknti]And the normalized feature vector T' is [ H (R) ]k)/Ek,Adi/Ek,fknti/Ek]，
Wherein,fkntivoltage variation of ith sampling point for kth cellDegree of membership of H (R)k) Ohmic internal resistance of kth battery cellEntropy of (1), AdiIs a penalty factor for the battery.
7. The method of claim 1, wherein an output F of the BP neural network model is [ F1, F2, F3, F4], F1 indicates no fault in the battery cell, F2 indicates an increase in internal resistance of the battery cell, F3 indicates a decrease in capacity of the battery cell, F4 indicates a short circuit in the battery cell, F1, F2, F3, F4 take a value of 0 or 1, 1 indicates the existence of the fault, and 0 indicates the absence of the fault.
8. The method of claim 2, wherein the optimizing the weights of the initial BP neural network using a genetic algorithm comprises:
determining a fitness function f (x) of each individual in the current population, and selecting m individuals with the highest or lowest fitness functions; the initial population comprises an initial weight value and a threshold value code in the BP neural network model;
and carrying out inheritance, crossover and mutation operations on the m individuals until a preset termination condition is met, and defining the individuals meeting the termination condition at present as an optimal weight threshold.
9. The method of claim 8, wherein the fitness function for each individual in the population is f (x) ═ P' -P2Wherein, f (x) represents a fitness function, P' is a predicted value of the test sample set, and P is a true value of the test sample set;
the preset termination condition is as follows: f, less than or equal to (x); wherein preset crossover and mutation probabilities are represented.
10. A fault diagnosis device for a high capacity battery energy storage system, the device comprising:
a model building module for pre-aligning the terminal voltage signal of the battery cellTerminal voltage signal U of battery energy storage systemiAnd a current signal IiTraining an input training sample to obtain a BP neural network model;
the acquisition module is used for acquiring data to be diagnosed of the battery energy storage system;
and the diagnosis module is used for inputting the data to be diagnosed as a test sample into the pre-constructed BP neural network model for fault diagnosis and outputting a fault diagnosis result.
11. The apparatus of claim 10, wherein the model building module comprises:
a collecting unit for collecting terminal voltage signals of the battery cells via a collecting cardTerminal voltage signal U of battery energy storage systemiAnd a current signal Ii；
The processing unit is used for extracting the characteristic vector of the collected signal and normalizing the characteristic vector; the characteristic vector comprises the ohmic internal resistance of the battery cellSample entropy of (1), penalty factor Ad of battery packiAnd cell terminal voltage variationDegree of membership fknti；
The optimization unit is used for inputting the normalized feature vector into an initial BP neural network and optimizing the weight of the initial BP neural network by using a genetic algorithm;
and the training unit is used for training the optimized BP neural network to obtain a final BP neural network model.
CN201710153380.6A 2017-03-15 2017-03-15 A fault diagnosis method and device for a large-capacity battery energy storage system Active CN107422266B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710153380.6A CN107422266B (en) 2017-03-15 2017-03-15 A fault diagnosis method and device for a large-capacity battery energy storage system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710153380.6A CN107422266B (en) 2017-03-15 2017-03-15 A fault diagnosis method and device for a large-capacity battery energy storage system

Publications (2)

Publication Number Publication Date
CN107422266A true CN107422266A (en) 2017-12-01
CN107422266B CN107422266B (en) 2021-04-16

Family

ID=60423468

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710153380.6A Active CN107422266B (en) 2017-03-15 2017-03-15 A fault diagnosis method and device for a large-capacity battery energy storage system

Country Status (1)

Country Link
CN (1) CN107422266B (en)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108363016A (en) * 2018-02-22 2018-08-03 上海理工大学 Battery micro-short circuit quantitative Diagnosis method based on artificial neural network
CN109061495A (en) * 2018-08-07 2018-12-21 中国电建集团福建省电力勘测设计院有限公司 A kind of hybrid energy-storing battery failure diagnostic method
CN109085507A (en) * 2018-07-31 2018-12-25 中国电力科学研究院有限公司 A kind of method and system for assessing energy-storage battery health status
CN109283469A (en) * 2018-09-21 2019-01-29 四川长虹电器股份有限公司 Battery management system failure prediction method, device and readable storage medium storing program for executing
CN109375116A (en) * 2018-08-09 2019-02-22 上海国际汽车城（集团）有限公司 A method for identifying abnormal battery in battery system based on self-encoder
CN109840593A (en) * 2019-01-28 2019-06-04 华中科技大学鄂州工业技术研究院 Diagnose the method and apparatus of solid oxide fuel battery system failure
CN109991556A (en) * 2019-04-08 2019-07-09 洛阳理工学院 A diagnostic method for short-term failure of lithium iron phosphate power battery
CN110286333A (en) * 2019-06-18 2019-09-27 哈尔滨理工大学 Fault diagnosis method for lithium power battery system
CN110703109A (en) * 2019-10-25 2020-01-17 山东大学 A method and system for multi-fault diagnosis of battery strings based on corrected sample entropy
CN112858917A (en) * 2021-01-15 2021-05-28 哈尔滨工业大学（威海） Battery system multi-fault diagnosis method based on genetic algorithm optimization neural network
CN113325317A (en) * 2021-07-08 2021-08-31 山东大学 Power battery fault diagnosis method and system based on improved RBF neural network
CN113376534A (en) * 2021-05-12 2021-09-10 山东大学 Phase plane diagnosis method for early fault of power battery and advanced early warning system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090112395A1 (en) * 2007-10-31 2009-04-30 Toyota Motor Engineering & Manufacturing North America, Inc.. System for detecting a battery malfunction and performing battery mitigation for an hev
CN105223510A (en) * 2015-09-01 2016-01-06 国家电网公司 A kind of battery pack based on internal resistance Information Entropy falls behind cell method of discrimination
CN106226700A (en) * 2016-07-17 2016-12-14 安徽卓越电气有限公司 Lithium battery detection platform system and method for testing
CN106482938A (en) * 2016-10-14 2017-03-08 温州大学 Brake fluid system multi-source fusion fault predicting method based on GA BP network

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090112395A1 (en) * 2007-10-31 2009-04-30 Toyota Motor Engineering & Manufacturing North America, Inc.. System for detecting a battery malfunction and performing battery mitigation for an hev
CN105223510A (en) * 2015-09-01 2016-01-06 国家电网公司 A kind of battery pack based on internal resistance Information Entropy falls behind cell method of discrimination
CN106226700A (en) * 2016-07-17 2016-12-14 安徽卓越电气有限公司 Lithium battery detection platform system and method for testing
CN106482938A (en) * 2016-10-14 2017-03-08 温州大学 Brake fluid system multi-source fusion fault predicting method based on GA BP network

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ZUCHANG GAO等: "Genetic Algorithm based Back-Propagation Neural Network approach for fault diagnosis in lithium-ion battery system", 《2015 6TH INTERNATIONAL CONFERENCE ON POWER ELECTRONICS SYSTEMS AND APPLICATIONS》 *

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108363016A (en) * 2018-02-22 2018-08-03 上海理工大学 Battery micro-short circuit quantitative Diagnosis method based on artificial neural network
CN109085507A (en) * 2018-07-31 2018-12-25 中国电力科学研究院有限公司 A kind of method and system for assessing energy-storage battery health status
CN109085507B (en) * 2018-07-31 2022-04-15 中国电力科学研究院有限公司 Method and system for evaluating health state of energy storage battery
CN109061495A (en) * 2018-08-07 2018-12-21 中国电建集团福建省电力勘测设计院有限公司 A kind of hybrid energy-storing battery failure diagnostic method
CN109375116B (en) * 2018-08-09 2021-12-14 上海国际汽车城（集团）有限公司 A method for identifying abnormal battery in battery system based on self-encoder
CN109375116A (en) * 2018-08-09 2019-02-22 上海国际汽车城（集团）有限公司 A method for identifying abnormal battery in battery system based on self-encoder
CN109283469A (en) * 2018-09-21 2019-01-29 四川长虹电器股份有限公司 Battery management system failure prediction method, device and readable storage medium storing program for executing
CN109840593A (en) * 2019-01-28 2019-06-04 华中科技大学鄂州工业技术研究院 Diagnose the method and apparatus of solid oxide fuel battery system failure
CN109840593B (en) * 2019-01-28 2023-09-05 华中科技大学鄂州工业技术研究院 Method and device for diagnosing solid oxide fuel cell system faults
CN109991556B (en) * 2019-04-08 2021-03-19 洛阳理工学院 A diagnostic method for short-term failure of lithium iron phosphate power battery
CN109991556A (en) * 2019-04-08 2019-07-09 洛阳理工学院 A diagnostic method for short-term failure of lithium iron phosphate power battery
CN110286333B (en) * 2019-06-18 2021-09-24 哈尔滨理工大学 A kind of fault diagnosis method of lithium power battery system
CN110286333A (en) * 2019-06-18 2019-09-27 哈尔滨理工大学 Fault diagnosis method for lithium power battery system
CN110703109A (en) * 2019-10-25 2020-01-17 山东大学 A method and system for multi-fault diagnosis of battery strings based on corrected sample entropy
CN110703109B (en) * 2019-10-25 2020-07-07 山东大学 A method and system for multi-fault diagnosis of battery strings based on corrected sample entropy
US11959973B2 (en) 2019-10-25 2024-04-16 Shandong University Multi-fault diagnosis method and system for battery packs based on corrected sample entropy
CN112858917A (en) * 2021-01-15 2021-05-28 哈尔滨工业大学（威海） Battery system multi-fault diagnosis method based on genetic algorithm optimization neural network
CN113376534A (en) * 2021-05-12 2021-09-10 山东大学 Phase plane diagnosis method for early fault of power battery and advanced early warning system
CN113376534B (en) * 2021-05-12 2022-04-05 山东大学 Phase plane diagnosis method for early fault of power battery and advanced early warning system
CN113325317A (en) * 2021-07-08 2021-08-31 山东大学 Power battery fault diagnosis method and system based on improved RBF neural network

Also Published As

Publication number Publication date
CN107422266B (en) 2021-04-16

Similar Documents

Publication Publication Date Title
CN107422266B (en) A fault diagnosis method and device for a large-capacity battery energy storage system
CN106785178B (en) Battery module reuse detection, screening and matching method and device
CN113052464B (en) Reliability evaluation method and system for battery energy storage system
CN114818831B (en) Bidirectional lithium ion battery fault detection method and system based on multi-source perception
CN113866642A (en) Lithium ion battery fault diagnosis method based on gradient lifting tree
Jiang et al. Sorting and grouping optimization method for second-use batteries considering aging mechanism
CN114280479B (en) Retired battery rapid sorting method based on electrochemical impedance spectroscopy
CN107192953B (en) A kind of energy-storage battery soft fault diagnosis method based on GA-Elman
CN112327189B (en) Comprehensive judging method for health state of energy storage battery based on KNN algorithm
CN109613446B (en) A Lithium Battery Aging Detection Method Based on Time Series Analysis
CN114280490B (en) Lithium ion battery state of charge estimation method and system
CN116930788B (en) Energy storage power station lithium battery capacity estimation method based on stacking model
CN104502844A (en) Power lithium battery deterioration degree diagnosis method based on AC impedance
CN108303649A (en) A kind of cell health state recognition methods
CN111814826B (en) Rapid detection and rating method for residual energy of retired power batteries
CN112686380A (en) Neural network-based echelon power cell consistency evaluation method and system
CN111208436A (en) An overcharge diagnosis method of energy storage battery based on IMF energy moment and genetic algorithm optimization of SVM
CN114580496A (en) A method for self-detection of lithium-ion battery cell failure
CN114545275A (en) An indirect prediction method for the remaining service life of lithium-ion batteries
CN112327190B (en) A method for identifying the state of health of an energy storage battery
CN115980588A (en) Lithium ion battery health state estimation method based on self-encoder extraction features
CN117805616A (en) Abnormal cell identification method for lithium ion energy storage system
CN115146723A (en) Electrochemical model parameter identification method based on deep learning and heuristic algorithm
CN118305097A (en) Rapid retired power battery sorting method based on interval frequency electrochemical impedance spectrum
CN117741443A (en) Energy storage lithium battery SOC estimation method based on A-CNN-LSTM

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant