[go: up one dir, main page]

CN115219912B - Early fault diagnosis and safety advanced early warning method and system for energy storage battery - Google Patents

Early fault diagnosis and safety advanced early warning method and system for energy storage battery Download PDF

Info

Publication number
CN115219912B
CN115219912B CN202210872812.XA CN202210872812A CN115219912B CN 115219912 B CN115219912 B CN 115219912B CN 202210872812 A CN202210872812 A CN 202210872812A CN 115219912 B CN115219912 B CN 115219912B
Authority
CN
China
Prior art keywords
fault diagnosis
energy storage
fault
early
battery
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.)
Active
Application number
CN202210872812.XA
Other languages
Chinese (zh)
Other versions
CN115219912A (en
Inventor
张承慧
李京伦
商云龙
顾鑫
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.)
Shandong University
Original Assignee
Shandong University
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 Shandong University filed Critical Shandong University
Publication of CN115219912A publication Critical patent/CN115219912A/en
Application granted granted Critical
Publication of CN115219912B publication Critical patent/CN115219912B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/367Software therefor, e.g. for battery testing using modelling or look-up tables
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/378Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] specially adapted for the type of battery or accumulator
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02EREDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02E60/10Energy storage using batteries

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Secondary Cells (AREA)
  • Tests Of Electric Status Of Batteries (AREA)

Abstract

The invention discloses an early fault diagnosis and safety advanced early warning method and system for an energy storage battery, comprising the following steps: acquiring a voltage signal of an energy storage battery; based on the voltage signal, performing a preliminary fault diagnosis result by adopting a plurality of fault diagnosis methods; mapping the preliminary fault diagnosis results of the multiple fault diagnosis methods into a characteristic value sequence; performing convex function processing on the characteristic value sequence, and adding bias; and integrating the processed characteristic value sequence with respect to time to obtain an early fault diagnosis result of the energy storage battery. Compared with the traditional fault diagnosis method, the fault diagnosis method has the advantages of low missed diagnosis risk and low misdiagnosis probability. Under the same misdiagnosis rate, the missed diagnosis number is obviously reduced compared with the traditional fault diagnosis algorithm. For early-stage micro faults of the battery, the diagnosis precision and the diagnosis speed of the method are far superior to those of the traditional fault diagnosis method, so that the method can more effectively sense the risk of potential malignant accidents and realize safety advanced early warning.

Description

一种储能电池早期故障诊断与安全超前预警方法及系统A method and system for early fault diagnosis and safety advance warning of energy storage batteries

技术领域Technical Field

本发明涉及锂电池故障诊断技术领域,尤其涉及一种储能电池早期故障诊断与安全超前预警方法及系统。The present invention relates to the technical field of lithium battery fault diagnosis, and in particular to an energy storage battery early fault diagnosis and safety advance warning method and system.

背景技术Background Art

本部分的陈述仅仅是提供了与本发明相关的背景技术信息,不必然构成在先技术。The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

锂离子电池作为一种环境敏感,噪声敏感的复杂非线性系统,故障类型众多、故障特征隐蔽、个体差异极大,其故障诊断面临误诊率高,漏诊率高的双重挑战,准确发现并定位故障的难度极大。另外,锂离子电池故障的发展速度极快,以电池的内短路为例,该故障会导致电池短时间内大量放能产热,直至燃烧爆炸。为避免此类恶性事故发生,电池管理系统(BMS)必须具备发现和甄别早期故障的能力,缩短故障诊断时间,实现安全超前预警,以尽可能减少电池故障造成的风险。这在算法设计和系统结构层面对BMS的故障诊断子系统提出了要求。As a complex nonlinear system that is sensitive to the environment and noise, lithium-ion batteries have many types of faults, hidden fault characteristics, and great individual differences. Their fault diagnosis faces the dual challenges of high misdiagnosis rate and high missed diagnosis rate, and it is extremely difficult to accurately discover and locate faults. In addition, lithium-ion battery failures develop very quickly. Taking the internal short circuit of the battery as an example, this fault will cause the battery to release a large amount of energy and generate heat in a short period of time until it burns and explodes. In order to avoid such vicious accidents, the battery management system (BMS) must have the ability to detect and identify early faults, shorten the fault diagnosis time, and achieve safe advance warning to minimize the risks caused by battery failures. This puts forward requirements for the fault diagnosis subsystem of the BMS at the algorithm design and system structure levels.

但锂离子电池故障的隐蔽性在故障早期尤为突出,该阶段的故障往往只会引起电池参数极小的变动。以磷酸铁锂带电池为例,故障早期,其电压变化往往不会超过额定电压的3%,这与环境噪声引起的参数变动十分相似。However, the hidden nature of lithium-ion battery failure is particularly prominent in the early stages of failure, and failures at this stage often only cause very small changes in battery parameters. Taking lithium iron phosphate batteries as an example, in the early stages of failure, its voltage change often does not exceed 3% of the rated voltage, which is very similar to the parameter changes caused by environmental noise.

现有的大部分故障诊断算法均采用阈值式诊断方法。故障诊断系统在故障引起的电池异常特征值突破预设的阈值时,进行故障报警。实际应用中,传统诊断算法往往采取较为保守的高阈值设定,以避免环境噪声造成的故障误诊。但同时,早期故障由于特征隐蔽而被漏诊的风险也会较高。若降低阈值来减少故障遗漏率,较低的阈值又会被环境噪声导致的异常特征值频繁触及,引起频发的误诊现象,影响电池系统正常作业。可见,传统的基于阈值的故障诊断方法不能解决误诊与漏诊之间的矛盾。Most of the existing fault diagnosis algorithms use threshold diagnosis methods. When the abnormal characteristic value of the battery caused by the fault exceeds the preset threshold, the fault diagnosis system will issue a fault alarm. In practical applications, traditional diagnostic algorithms often adopt a more conservative high threshold setting to avoid misdiagnosis of faults caused by environmental noise. But at the same time, the risk of early faults being missed due to hidden characteristics will also be high. If the threshold is lowered to reduce the fault omission rate, the lower threshold will be frequently touched by the abnormal characteristic values caused by environmental noise, causing frequent misdiagnosis and affecting the normal operation of the battery system. It can be seen that the traditional threshold-based fault diagnosis method cannot solve the contradiction between misdiagnosis and missed diagnosis.

现有技术公开了基于样本熵的电池故障诊断方法,该方法以电池电压序列的样本熵为基础,用与故障类型相关的电压特征进行修正得到对故障类型敏感的修正样本熵值,并以此作为故障诊断的依据。在故障特征明显,负载平稳运行,环境噪声较小的前提下,该方法的故障诊断效果良好。但若电池故障较轻、环境噪声较大、负载变化多样,该算法就会面对漏诊率和误诊率无法同时较低的矛盾,难以实现预期的诊断效果。The prior art discloses a battery fault diagnosis method based on sample entropy. This method is based on the sample entropy of the battery voltage sequence, and uses the voltage characteristics related to the fault type to correct the corrected sample entropy value that is sensitive to the fault type, and uses this as the basis for fault diagnosis. Under the premise that the fault characteristics are obvious, the load runs smoothly, and the environmental noise is small, the fault diagnosis effect of this method is good. However, if the battery fault is minor, the environmental noise is large, and the load changes are diverse, the algorithm will face the contradiction that the missed diagnosis rate and the misdiagnosis rate cannot be low at the same time, and it is difficult to achieve the expected diagnostic effect.

现有技术公开的故障诊断方法通过小波变化等信号处理手段得到了故障关系密切的特征参数。该参数仍需以阈值比较的方式判断故障与否。此外,虽然其特征提取过程中的滤波手段抑制了部分环境噪声的影响,但该处理过程对早期故障的特征也有削弱作用,仍然不能摆脱漏诊率、误诊率无法两全的困境。The fault diagnosis method disclosed in the prior art obtains characteristic parameters closely related to the fault through signal processing means such as wavelet transformation. The parameter still needs to be judged by threshold comparison to determine whether there is a fault. In addition, although the filtering means in the feature extraction process suppresses the influence of some environmental noise, the processing process also weakens the characteristics of early faults, and still cannot get rid of the dilemma of being unable to achieve both missed diagnosis rate and misdiagnosis rate.

这一类基于特征阈值的电池故障诊断方法诊断方式过于简单,只能在特征层面发现异常,并利用阈值区分故障和噪声。这决定了它们对微小、与噪声类似的故障难以辨别,无法诊断。这也导致这类故障诊断算法无法在早期发现电池故障,因而无法真正做到有降低电池系统的事故风险。现有技术水平下,只有从诊断方式出发,在电池故障和环境噪声的本质上对其进行区分,才能取得较好的诊断效果,达到规避风险的目的。This type of battery fault diagnosis method based on characteristic thresholds is too simple in its diagnostic method. It can only detect anomalies at the characteristic level and use thresholds to distinguish between faults and noise. This determines that they are difficult to distinguish and cannot diagnose small faults that are similar to noise. This also leads to the inability of such fault diagnosis algorithms to detect battery faults in the early stages, and therefore cannot truly reduce the accident risk of the battery system. Under the current technical level, only by starting from the diagnostic method and distinguishing between battery faults and environmental noise in their essence can we achieve better diagnostic results and achieve the purpose of risk avoidance.

此外,单一角度的诊断难以应对电池系统可能发生的所有故障类型,如基于样本熵的故障诊断方法对引起电池参数急剧变化的故障类型十分敏感,而对漏电故障等使电池参数缓慢改变的故障类型效果不佳。基于相关系数的故障诊断方法则对发生于电池单体的故障类型效果显著,但对电池组故障难以处理。因此,单一角度的诊断难无法保证多种类型故障的诊断效果。In addition, a single-angle diagnosis is difficult to deal with all possible fault types that may occur in the battery system. For example, the fault diagnosis method based on sample entropy is very sensitive to fault types that cause rapid changes in battery parameters, but is not effective for fault types such as leakage faults that cause slow changes in battery parameters. The fault diagnosis method based on correlation coefficient is effective for fault types that occur in battery cells, but is difficult to handle battery pack faults. Therefore, a single-angle diagnosis cannot guarantee the diagnostic effect of multiple types of faults.

发明内容Summary of the invention

为了解决上述问题,本发明提出了一种储能电池早期故障诊断与安全超前预警方法及系统,通过时序依赖的故障诊断策略和分级式系统结构,克服了噪声等的影响,实现了电池早期微小故障的高精度、高灵敏度诊断;通过对微小异常的积累和放大,实现对潜在故障的监测,进一步降低恶性故障风险,取得了较好的安全超前预警效果。In order to solve the above problems, the present invention proposes a method and system for early fault diagnosis and safety advance warning of energy storage batteries. Through a timing-dependent fault diagnosis strategy and a hierarchical system structure, the influence of noise and the like is overcome, and high-precision and high-sensitivity diagnosis of early minor faults of the battery is achieved; through the accumulation and amplification of minor anomalies, potential faults are monitored, the risk of malignant failures is further reduced, and better safety advance warning effects are achieved.

在一些实施方式中,采用如下技术方案:In some embodiments, the following technical solutions are adopted:

一种储能电池早期故障诊断与安全超前预警方法,包括:A method for early fault diagnosis and safety advance warning of energy storage batteries, comprising:

获取储能电池的电压信号;Obtaining voltage signal of energy storage battery;

基于所述电压信号,采用多种故障诊断方法进行初步故障诊断结果;Based on the voltage signal, a plurality of fault diagnosis methods are used to obtain preliminary fault diagnosis results;

将多种故障诊断方法的初步故障诊断结果映射为特征值序列;Mapping preliminary fault diagnosis results of multiple fault diagnosis methods into feature value sequences;

对所述特征值序列进行凸函数处理,并添加偏置;Performing convex function processing on the eigenvalue sequence and adding a bias;

对处理后的特征值序列进行关于时间的积分,得到储能电池早期故障诊断结果。The processed eigenvalue sequence is integrated with respect to time to obtain the early fault diagnosis result of the energy storage battery.

在另一些实施方式中,采用如下技术方案:In other embodiments, the following technical solutions are adopted:

一种储能电池早期故障诊断与安全超前预警系统,包括:An energy storage battery early fault diagnosis and safety advance warning system, comprising:

数据获取模块,用于获取储能电池的电压信号;A data acquisition module, used to acquire a voltage signal of an energy storage battery;

故障初步诊断模块,用于基于所述电压信号,采用多种故障诊断方法进行初步故障诊断结果;A preliminary fault diagnosis module, used to obtain preliminary fault diagnosis results based on the voltage signal using a variety of fault diagnosis methods;

初步故障诊断结果处理模块,用于将多种故障诊断方法的初步故障诊断结果映射为特征值序列;对所述特征值序列进行凸函数处理,并添加偏置;A preliminary fault diagnosis result processing module is used to map the preliminary fault diagnosis results of multiple fault diagnosis methods into a characteristic value sequence; perform convex function processing on the characteristic value sequence and add a bias;

早期故障诊断模块,用于对处理后的特征值序列进行关于时间的积分,得到储能电池早期故障诊断结果。The early fault diagnosis module is used to integrate the processed eigenvalue sequence with respect to time to obtain the early fault diagnosis result of the energy storage battery.

在另一些实施方式中,采用如下技术方案:In other embodiments, the following technical solutions are adopted:

一种终端设备,其包括处理器和存储器,处理器用于实现各指令;存储器用于存储多条指令,所述指令适于由处理器加载并执行上述的储能电池早期故障诊断与安全超前预警方法。A terminal device includes a processor and a memory, wherein the processor is used to implement various instructions; the memory is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and executing the above-mentioned energy storage battery early fault diagnosis and safety advance warning method.

在另一些实施方式中,采用如下技术方案:In other embodiments, the following technical solutions are adopted:

一种计算机可读存储介质,其中存储有多条指令,所述指令适于由终端设备的处理器加载并执行上述的储能电池早期故障诊断与安全超前预警方法。A computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor of a terminal device and executing the above-mentioned energy storage battery early fault diagnosis and safety advance warning method.

与现有技术相比,本发明的有益效果是:Compared with the prior art, the present invention has the following beneficial effects:

(1)本发明故障诊断方法相比传统故障诊断方法漏诊风险小,误诊概率低。相同误诊率下,漏诊数比传统故障诊断算法减少明显。对于电池早期微小故障,该方法的诊断精度和诊断速度也远优于传统的故障诊断方法。(1) The fault diagnosis method of the present invention has a lower risk of missed diagnosis and a lower probability of misdiagnosis than the traditional fault diagnosis method. Under the same misdiagnosis rate, the number of missed diagnoses is significantly reduced compared with the traditional fault diagnosis algorithm. For early minor battery faults, the diagnostic accuracy and speed of this method are also far superior to traditional fault diagnosis methods.

(2)本发明方法从多角度故障分析使可诊断的故障类型增多,进一步降低故障遗漏的风险;算法复杂度低,实用性强,有较大的应用空间。(2) The method of the present invention increases the number of fault types that can be diagnosable by analyzing faults from multiple angles, further reducing the risk of missed faults; the algorithm has low complexity, strong practicality, and a large application space.

(3)本发明可对电池故障和噪声进行特异性区分,解决了漏诊率和误诊率的矛盾,也为电池早期微小故障的诊断提供了可能。(3) The present invention can specifically distinguish between battery faults and noise, thus resolving the contradiction between missed diagnosis rate and misdiagnosis rate, and also providing the possibility for diagnosing minor battery faults in the early stage.

本发明的其他特征和附加方面的优点将在下面的描述中部分给出,部分将从下面的描述中变得明显,或通过本方面的实践了解到。Other features and advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through the practice of the present invention.

附图说明BRIEF DESCRIPTION OF THE DRAWINGS

图1为本发明实施例中的基于异常值累积的储能电池早期故障诊断方法示意图;FIG1 is a schematic diagram of an energy storage battery early fault diagnosis method based on abnormal value accumulation in an embodiment of the present invention;

图2为本发明实施例中的四节电池单体的电压曲线示意图;FIG2 is a schematic diagram of voltage curves of four battery cells in an embodiment of the present invention;

图3(a)和图3(b)为本发明实施例中的用样本熵方法和相关系数法分别对四节单体进行故障检测的参数曲线;FIG. 3( a ) and FIG. 3( b ) are parameter curves for fault detection of four cells using the sample entropy method and the correlation coefficient method, respectively, in an embodiment of the present invention;

图4(a)和图4(b)为采用本实施例方法的故障诊断结果;FIG. 4( a ) and FIG. 4( b ) are fault diagnosis results using the method of this embodiment;

图5为三种故障诊断算法的ROC曲线。Figure 5 shows the ROC curves of three fault diagnosis algorithms.

具体实施方式DETAILED DESCRIPTION

应该指出,以下详细说明都是例示性的,旨在对本申请提供进一步的说明。除非另有指明,本发明使用的所有技术和科学术语具有与本申请所属技术领域的普通技术人员通常理解的相同含义。It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

需要注意的是,这里所使用的术语仅是为了描述具体实施方式,而非意图限制根据本申请的示例性实施方式。如在这里所使用的,除非上下文另外明确指出,否则单数形式也意图包括复数形式,此外,还应当理解的是,当在本说明书中使用术语“包含”和/或“包括”时,其指明存在特征、步骤、操作、器件、组件和/或它们的组合。It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and/or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and/or combinations thereof.

实施例一Embodiment 1

在一个或多个实施方式中,公开了一种储能电池早期故障诊断与安全超前预警方法,结合图1,具体包括如下内容:In one or more embodiments, a method for early fault diagnosis and safety advance warning of an energy storage battery is disclosed, which specifically includes the following contents in conjunction with FIG1:

(1)获取储能电池的电压信号;(1) Obtaining the voltage signal of the energy storage battery;

具体地,通过传感器采集储能电池的电压信号。Specifically, the voltage signal of the energy storage battery is collected by a sensor.

(2)基于所述电压信号,采用多种故障诊断方法进行初步故障诊断结果;(2) Based on the voltage signal, a plurality of fault diagnosis methods are used to obtain preliminary fault diagnosis results;

本实施例中,所选取的故障诊断方法的诊断结果均以数值形式的电池特征值呈现,并且取值范围应包含于非负数域,与故障概率正相关。In this embodiment, the diagnosis results of the selected fault diagnosis method are all presented in the form of battery characteristic values in numerical form, and the value range should be included in the non-negative number domain and positively correlated with the fault probability.

本实施例选取的故障诊断方法包括:样本熵法、相关系数法和电流、电压及温度综合比较法;其中,样本熵法将一定时间尺度内电池电压序列的样本熵作为诊断依据的电池特征值,通过窗口的滑动实时计算最近时段内电池电压序列的样本熵。此时t时刻电压序列的样本熵即为该算法诊断结果。相关系数法,在一定的时间尺度内计算串联电池单体电压间的相关系数,以此作为故障诊断的电池特征依据。此时t时刻电池单体间电压相关系数即为该算法诊断结果。电流、电压及温度综合比较法,统计电池运行过程中电流、电压、温度的平均值,以待诊断时刻电池的上述三种参数组成的向量与平均值组成的向量间的欧式距离作为故障诊断的电池特征依据,该欧氏距离即为该算法诊断结果。The fault diagnosis methods selected in this embodiment include: sample entropy method, correlation coefficient method and current, voltage and temperature comprehensive comparison method; among them, the sample entropy method uses the sample entropy of the battery voltage sequence within a certain time scale as the battery characteristic value for diagnosis, and calculates the sample entropy of the battery voltage sequence in the most recent period in real time by sliding the window. At this time, the sample entropy of the voltage sequence at time t is the diagnosis result of the algorithm. The correlation coefficient method calculates the correlation coefficient between the voltages of the battery cells in series within a certain time scale, and uses this as the battery characteristic basis for fault diagnosis. At this time, the voltage correlation coefficient between the battery cells at time t is the diagnosis result of the algorithm. The current, voltage and temperature comprehensive comparison method counts the average values of the current, voltage and temperature during the operation of the battery, and uses the Euclidean distance between the vector composed of the above three parameters of the battery at the time to be diagnosed and the vector composed of the average values as the battery characteristic basis for fault diagnosis, and the Euclidean distance is the diagnosis result of the algorithm.

当然,本领域技术人员也可以根据需要选择其他的故障诊断方法进行计算。Of course, those skilled in the art may also select other fault diagnosis methods for calculation as needed.

样本熵法和电流、电压及温度综合比较法的故障诊断结果均为与故障概率正相关的数值结果,可直接使用;相关系数法的诊断结果为值域为[0,1]的与故障概率负相关的数值,需将其依照以下规则映射:The fault diagnosis results of the sample entropy method and the current, voltage and temperature comprehensive comparison method are both numerical results that are positively correlated with the fault probability and can be used directly; the diagnosis result of the correlation coefficient method is a numerical value with a range of [0, 1] that is negatively correlated with the fault probability and needs to be mapped according to the following rules:

di′(t)=-di(t)+1d i ′(t)=-d i (t)+1

其中,di(t)为采用相关系数法在t时刻的故障诊断结果,di′(t)为映射之后的结果,将映射后的di′(t)代替di(t)作为后续整合处理U的输入。经过映射后,变为值域包含于非负数域,且与故障概率正相关的函数值。Among them, d i (t) is the fault diagnosis result at time t using the correlation coefficient method, d i ′(t) is the result after mapping, and the mapped d i ′(t) replaces d i (t) as the input of the subsequent integration process U. After mapping, it becomes a function value whose value range is contained in the non-negative number domain and is positively correlated with the fault probability.

(3)将多种故障诊断方法的初步故障诊断结果映射为关于时间的特征值序列;(3) Mapping the preliminary fault diagnosis results of multiple fault diagnosis methods into a time-dependent feature value sequence;

具体地,Specifically,

u(t)=U(d1(t),d2(t),…,dn(t))u(t)=U(d 1 (t),d 2 (t),…,d n (t))

其中,di(t)表示第i种故障诊断算法在t时刻的故障诊断结果,u(t)为特征参数di(t)整合处理的结果,U为该整合方法的抽象。具体到本实施例中,i=1,2,3。Wherein, d i (t) represents the fault diagnosis result of the i-th fault diagnosis algorithm at time t, u(t) is the result of the integration processing of the characteristic parameter d i (t), and U is the abstraction of the integration method. Specifically in this embodiment, i=1, 2, 3.

本实施例中,U根据应用场景有两种计算方式可供选择:In this embodiment, U has two calculation methods to choose from according to the application scenario:

①倾向于保证低漏诊率,同时对初诊断环节中各算法效果较为了解时,可采用附加权重的均方根形式,即,① When we tend to ensure a low missed diagnosis rate and have a good understanding of the effects of various algorithms in the initial diagnosis stage, we can use the root mean square form of additional weights, that is,

其中,a1,a2,…,an为权重参数,由先验经验确定。Among them, a 1 , a 2 ,…, a n are weight parameters determined by prior experience.

②注重系统稳定性,倾向确保低误诊率时则可采用极值形式,此时② When the system stability is emphasized and the misdiagnosis rate is low, the extreme value form can be used.

u(t)=max[a1·d1(t),a2·d2(t),…,an·dn]u(t)=max[a 1 ·d 1 (t),a 2 ·d 2 (t),…,a n ·d n ]

其中,常数a1,a2,…,an的作用为规范化di(t),使其取值接近。Among them, the role of the constants a 1 , a 2 ,…, an is to normalize d i (t) so that its values are close.

由于被整合的诊断结果均与故障概率正相关,因此整合后,u(t)为与t时刻故障概率正相关的特征量。Since the integrated diagnosis results are all positively correlated with the failure probability, after integration, u(t) is a feature quantity that is positively correlated with the failure probability at time t.

(4)对所述特征值序列进行凸函数处理,并添加偏置;(4) performing convex function processing on the eigenvalue sequence and adding a bias;

本实施例中,凸函数处理的过程如下:In this embodiment, the process of convex function processing is as follows:

c(t)=C(u(t))+bc(t)=C(u(t))+b

C为对特征u(t)进行凸函数化处理并添加偏置b的映射函数,经C处理后,特征u(t)映射为与故障概率相关的凸函数c(t)。C is a mapping function that performs convex function processing on the feature u(t) and adds a bias b. After processing by C, the feature u(t) is mapped to a convex function c(t) related to the fault probability.

本实施例中,C有两种可选择的形式:In this embodiment, C has two optional forms:

①用于工作状态多变的电池系统时,为保证系统稳定性,选用幂函数作为C的具体化:① When used in a battery system with variable working conditions, in order to ensure system stability, a power function is selected as the embodiment of C:

c(t)=u(t)e+bc(t)=u(t) e +b

其中,e为常数,且e越大凸函数化效果越明显,应用中e应大于1。Among them, e is a constant, and the larger the e is, the more obvious the convex function effect is. In applications, e should be greater than 1.

②用于工作状态较为恒定的电池系统时,为敏锐发现异常,选用指数函数作为C的具体化,有,② When used in a battery system with a relatively constant working state, in order to detect abnormalities sensitively, an exponential function is selected as the embodiment of C, which is:

c(t)=eu(t)+bc(t)= eu(t) +b

其中,e为常数,且e越大凸函数化效果越明显,应用中e应大于1。Among them, e is a constant, and the larger the e is, the more obvious the convex function effect is. In applications, e should be greater than 1.

b为偏置常数,偏置后c(t)的值域跨过零点,包含负值部分。由于凸函数的特点,故障概率上升时,c(t)的值会以越来越大的速率上升,这有利于危险故障的快速诊断,而偏置的引入使得电池工作状态正常时c(t)的值为负,在后续积分中使积分值下降。b is the bias constant. After the bias, the value range of c(t) crosses the zero point and includes negative values. Due to the characteristics of convex functions, when the probability of failure increases, the value of c(t) will increase at an increasing rate, which is conducive to the rapid diagnosis of dangerous failures. The introduction of the bias makes the value of c(t) negative when the battery is working normally, which reduces the integral value in the subsequent integration.

(5)对处理后的特征值序列进行关于时间的积分,得到储能电池早期故障诊断结果。(5) Integrate the processed eigenvalue sequence with respect to time to obtain the early fault diagnosis results of the energy storage battery.

具体地,Specifically,

其中,o(t)为u(t)关于时间的积分值,也是该框架的输出值。Among them, o(t) is the integral value of u(t) with respect to time, which is also the output value of the framework.

当o(t)的值超过预设的阈值时,认为电池发生了故障。对于锂离子电池的故障诊断而言,发现故障往往比判断故障类型更为重要。因此,本实施例更注重故障的检测。当故障引起o(t)突破阈值时,可根据故障发现之前时段内o(t)的曲线形状大致判断故障类型。若曲线斜度较大,且在上升过程中稍有转折,可初步诊断电池发生了内短路故障。若曲线上升过程伴随波动,并存在短时间的下降现象,可初步诊断电池发生了接触不良故障。若曲线极具上升且快速达到阈值,可初步诊断电池传感器出现了故障。When the value of o(t) exceeds a preset threshold, it is considered that the battery has failed. For fault diagnosis of lithium-ion batteries, discovering the fault is often more important than determining the type of fault. Therefore, this embodiment pays more attention to fault detection. When a fault causes o(t) to break through the threshold, the type of fault can be roughly determined based on the shape of the curve of o(t) in the period before the fault is discovered. If the slope of the curve is large and there is a slight turn during the rising process, it can be preliminarily diagnosed that the battery has an internal short circuit fault. If the rising process of the curve is accompanied by fluctuations and there is a short-term decline, it can be preliminarily diagnosed that the battery has a poor contact fault. If the curve rises very fast and reaches the threshold quickly, it can be preliminarily diagnosed that the battery sensor has a fault.

下面以本实施例方法在电动汽车电池包故障诊断中的应用为例进行说明,考虑电池包的故障特点,用样本熵方法和相关系数法对其进行初诊断。其中样本熵方法中r的取值定为0.15,两种算法的窗口大小均选为20。The following is an example of the application of the method of this embodiment in the fault diagnosis of an electric vehicle battery pack. Considering the fault characteristics of the battery pack, the sample entropy method and the correlation coefficient method are used to perform an initial diagnosis. The value of r in the sample entropy method is set to 0.15, and the window size of the two algorithms is selected to be 20.

选择附加权重的均方根作为整合方法,权重a1,a2的取值分别为20,15,即,The root mean square of the additional weights is selected as the integration method, and the values of weights a 1 and a 2 are 20 and 15 respectively, that is,

选择指数形式对u(t)进行凸函数化处理,其中a的取值为3.5,b的取值为0.5。即:Select the exponential form to process u(t) into a convex function, where a is 3.5 and b is 0.5. That is:

c(t)=3.5u(t)-0.5c(t)=3.5 u(t) -0.5

以上参数只针对本实施例的真实实验条件,应用去其他场景需进行必要的参数调整。The above parameters are only for the actual experimental conditions of this embodiment. If applied to other scenarios, necessary parameter adjustments need to be made.

现有电动汽车电池包中四节串联电池单体的电压数据(模拟实验获得)。图2描绘了该四节电池单体的电压曲线。其中,左框圈出部分单体4发生故障,中框圈出部分电池包整体发生故障,导致所有电池单体的电压信号均产生异常。右框圈出区间内,单体4受负载波动影响,电压信号也存在异常,但此时单体4并未发生故障,异常均为噪声导致。Voltage data of four series-connected battery cells in an existing electric vehicle battery pack (obtained from simulation experiments). Figure 2 depicts the voltage curves of the four battery cells. Among them, the left frame circled part of the single cell 4 has failed, and the middle frame circled part of the battery pack has failed as a whole, resulting in abnormal voltage signals of all battery cells. In the interval circled in the right frame, single cell 4 is affected by load fluctuations, and the voltage signal is also abnormal, but at this time single cell 4 has not failed, and the abnormalities are all caused by noise.

用样本熵方法和相关系数法分别对四节单体进行故障检测,得到的参数曲线如图3(a)和图3(b)所示。从图3(a)可见,样本熵方法诊断了中框所指示的电池包整体故障,但对左框标记的电池单体故障反应明显。且在右框指示的噪声发生时,样本熵做出了明显的反应,可见样本熵方法无法对电池故障和噪声做出明显区分。The sample entropy method and the correlation coefficient method were used to detect the faults of the four cells respectively, and the obtained parameter curves are shown in Figure 3(a) and Figure 3(b). As can be seen from Figure 3(a), the sample entropy method diagnosed the overall fault of the battery pack indicated by the middle box, but it reacted significantly to the single cell fault marked by the left box. And when the noise indicated by the right box occurred, the sample entropy reacted significantly, which shows that the sample entropy method cannot make a clear distinction between battery faults and noise.

相关系数法存在类似的问题,图3(b)曲线为电池单体电压与四节电池平均电压的相关系数曲线。从中可见,电压曲线图中左框圈出的故障造成了相关系数的下降,被该方法准确识别,但是中框指示的发生在电池包,对所有电池单体造成相同影响的故障无法被有效识别。噪声造成的参数异常也引起了电池见相关系数的下降,被当作故障处理。The correlation coefficient method has similar problems. The curve in Figure 3(b) is the correlation coefficient curve between the battery cell voltage and the average voltage of four batteries. It can be seen that the fault circled in the left box of the voltage curve caused the correlation coefficient to drop, which was accurately identified by this method. However, the fault indicated by the middle box occurred in the battery pack and had the same impact on all battery cells. It could not be effectively identified. The parameter abnormality caused by noise also caused the battery correlation coefficient to drop, and was treated as a fault.

图4(a)为基于本发明公开方法对相同故障电池单体的故障诊断结果;由图可知,两种不同的故障均被算法识别,且在故障持续期间,基于异常积累型故障诊断算法的诊断指标均达到预设峰值,这表明该算法兼具了样本熵方法和相关系数法的可诊断故障类型,具有更大的诊断范围。此外,最大噪声影响不足以使得诊断指标达到预设峰值,这表明噪声对故障诊断的影响在异常值累计过程中被稀释,使得故障诊断系统整体的抗噪声能力提高。图4(b)为正常电池与故障电池在噪声环境下的诊断结果对比,其中电池1,3为正常电池,电池2为故障电池;由图可知,受强噪声影响,所有电池的诊断指标均有所上升,但只有故障电池2最终触及预设阈值触发故障报警,正常电池的诊断指标则随着噪声强度衰减呈下降趋势。对比图3(a)和图3(b),本实施例算法有效屏蔽了噪声干扰,具有远超常规诊断算法的故障甄别能力。FIG4(a) is a fault diagnosis result of a battery cell with the same fault based on the method disclosed in the present invention; it can be seen from the figure that two different faults are identified by the algorithm, and during the duration of the fault, the diagnostic indicators based on the abnormal accumulation type fault diagnosis algorithm reach the preset peak value, which indicates that the algorithm has both the diagnosable fault types of the sample entropy method and the correlation coefficient method, and has a larger diagnostic range. In addition, the maximum noise impact is not enough to make the diagnostic index reach the preset peak value, which indicates that the impact of noise on fault diagnosis is diluted in the process of abnormal value accumulation, so that the overall anti-noise ability of the fault diagnosis system is improved. FIG4(b) is a comparison of the diagnostic results of normal batteries and faulty batteries in a noisy environment, where batteries 1 and 3 are normal batteries and battery 2 is a faulty battery; it can be seen from the figure that under the influence of strong noise, the diagnostic indicators of all batteries have increased, but only the faulty battery 2 finally reaches the preset threshold to trigger a fault alarm, and the diagnostic indicators of normal batteries show a downward trend as the noise intensity decays. Comparing FIG3(a) and FIG3(b), the algorithm of this embodiment effectively shields noise interference and has a fault discrimination ability far exceeding that of conventional diagnostic algorithms.

重复进行多组类似实验,以算法诊断结果的假正例率为横坐标,真正例率为纵坐标的曲线即为该故障诊断算法的ROC曲线。图5绘制了三种算法的ROC曲线,本实施例基于异常值累积的故障诊断算法的ROC曲线完全包括了其他两种故障诊断算法的曲线。AUG(曲线包围区域)面积差别明显,可见本实施例提出的故障诊断算法相较传统故障诊断算法提升明显。Repeat multiple groups of similar experiments, and the curve with the false positive rate of the algorithm diagnosis result as the horizontal axis and the true positive rate as the vertical axis is the ROC curve of the fault diagnosis algorithm. Figure 5 plots the ROC curves of the three algorithms. The ROC curve of the fault diagnosis algorithm based on the accumulation of abnormal values in this embodiment completely includes the curves of the other two fault diagnosis algorithms. The area of AUG (area surrounded by the curve) is significantly different, which shows that the fault diagnosis algorithm proposed in this embodiment is significantly improved compared with the traditional fault diagnosis algorithm.

实施例二Embodiment 2

在一个或多个实施方式中,公开了一种储能电池早期故障诊断与安全超前预警系统,包括:In one or more embodiments, a system for early fault diagnosis and safety advance warning of energy storage batteries is disclosed, comprising:

数据获取模块,用于获取储能电池的电压信号;A data acquisition module, used to acquire a voltage signal of an energy storage battery;

故障初步诊断模块,用于基于所述电压信号,采用多种故障诊断方法进行初步故障诊断结果;A preliminary fault diagnosis module, used to obtain preliminary fault diagnosis results based on the voltage signal using a variety of fault diagnosis methods;

初步故障诊断结果处理模块,用于将多种故障诊断方法的初步故障诊断结果映射为特征值序列;对所述特征值序列进行凸函数处理,并添加偏置;A preliminary fault diagnosis result processing module is used to map the preliminary fault diagnosis results of multiple fault diagnosis methods into a characteristic value sequence; perform convex function processing on the characteristic value sequence and add a bias;

早期故障诊断模块,用于对处理后的特征值序列进行关于时间的积分,得到储能电池早期故障诊断结果。The early fault diagnosis module is used to integrate the processed eigenvalue sequence with respect to time to obtain the early fault diagnosis result of the energy storage battery.

需要说明的是,上述各模块的具体实现方式已经在实施例一中进行了详细的说明,此处不再详述。It should be noted that the specific implementation methods of the above modules have been described in detail in Example 1 and will not be described in detail here.

实施例三Embodiment 3

在一个或多个实施方式中,公开了一种终端设备,包括服务器,所述服务器包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,所述处理器执行所述程序时实现实施例一中的储能电池早期故障诊断与安全超前预警方法。为了简洁,在此不再赘述。In one or more embodiments, a terminal device is disclosed, including a server, the server including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the energy storage battery early fault diagnosis and safety advance warning method in embodiment 1 when executing the program. For the sake of brevity, it will not be described here.

应理解,本实施例中,处理器可以是中央处理单元CPU,处理器还可以是其他通用处理器、数字信号处理器DSP、专用集成电路ASIC,现成可编程门阵列FPGA或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

存储器可以包括只读存储器和随机存取存储器,并向处理器提供指令和数据、存储器的一部分还可以包括非易失性随机存储器。例如,存储器还可以存储设备类型的信息。The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

在实现过程中,上述方法的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software.

实施例四Embodiment 4

在一个或多个实施方式中,公开了一种计算机可读存储介质,其中存储有多条指令,所述指令适于由终端设备的处理器加载并执行实施例一中的储能电池早期故障诊断与安全超前预警方法。In one or more embodiments, a computer-readable storage medium is disclosed, in which a plurality of instructions are stored, wherein the instructions are suitable for being loaded by a processor of a terminal device and executing the energy storage battery early fault diagnosis and safety advance warning method in Example 1.

上述虽然结合附图对本发明的具体实施方式进行了描述,但并非对本发明保护范围的限制,所属领域技术人员应该明白,在本发明的技术方案的基础上,本领域技术人员不需要付出创造性劳动即可做出的各种修改或变形仍在本发明的保护范围以内。Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims (9)

1.一种储能电池早期故障诊断与安全超前预警方法,其特征在于,包括:1. A method for early fault diagnosis and safety advance warning of energy storage batteries, characterized by comprising: 获取储能电池的电压信号;Obtaining voltage signal of energy storage battery; 基于所述电压信号,采用多种故障诊断方法进行初步故障诊断结果;Based on the voltage signal, a plurality of fault diagnosis methods are used to obtain preliminary fault diagnosis results; 将多种故障诊断方法的初步故障诊断结果映射为特征值序列;Mapping preliminary fault diagnosis results of multiple fault diagnosis methods into feature value sequences; 具体为:Specifically: u(t)=U(d1(t),d2(t),…,dn(t))u(t)=U(d 1 (t),d 2 (t),…,d n (t)) 其中,di(t)表示第i种故障诊断算法在t时刻的故障诊断结果,i=1,2,…,n;u(t)为对特征参数di(t)整合处理后的特征量;Wherein, d i (t) represents the fault diagnosis result of the i-th fault diagnosis algorithm at time t, i = 1, 2, …, n; u(t) is the characteristic quantity after the integration of the characteristic parameter d i (t); 对所述特征值序列进行凸函数处理,并添加偏置;Performing convex function processing on the eigenvalue sequence and adding a bias; 对处理后的特征值序列进行关于时间的积分,得到储能电池早期故障诊断结果;Integrate the processed eigenvalue sequence with respect to time to obtain the early fault diagnosis result of the energy storage battery; 具体地,Specifically, 其中,o(t)为u(t)关于时间的积分值,也是该框架的输出值,c(t)为凸函数;Among them, o(t) is the integral value of u(t) with respect to time, which is also the output value of the framework, and c(t) is a convex function; 当o(t)的值超过预设的阈值时,认为电池发生了故障;当故障引起o(t)突破阈值时,可根据故障发现之前时段内o(t)的曲线形状大致判断故障类型。When the value of o(t) exceeds the preset threshold, it is considered that the battery has a fault; when the fault causes o(t) to exceed the threshold, the fault type can be roughly determined based on the curve shape of o(t) in the period before the fault is discovered. 2.如权利要求1所述的一种储能电池早期故障诊断与安全超前预警方法,其特征在于,采用多种故障诊断方法进行初步故障诊断结果,所述故障诊断方法包括:样本熵法、相关系数法、以及电流、电压、温度综合比较法。2. A method for early fault diagnosis and safety advance warning of energy storage batteries as described in claim 1, characterized in that a plurality of fault diagnosis methods are used to obtain preliminary fault diagnosis results, and the fault diagnosis methods include: sample entropy method, correlation coefficient method, and current, voltage, and temperature comprehensive comparison method. 3.如权利要求1所述的一种储能电池早期故障诊断与安全超前预警方法,其特征在于,对特征参数di(t)整合处理,具体为:3. The method for early fault diagnosis and safety advance warning of energy storage batteries according to claim 1, characterized in that the characteristic parameter d i (t) is integrated and processed as follows: 其中,a1,a2,…,an为权重参数。Among them, a 1 ,a 2 ,…,a n are weight parameters. 4.如权利要求1所述的一种储能电池早期故障诊断与安全超前预警方法,其特征在于,对特征参数di(t)整合处理,具体为:4. The method for early fault diagnosis and safety advance warning of energy storage batteries according to claim 1, characterized in that the characteristic parameter d i (t) is integrated and processed as follows: u(t)=max[a1·d1(t),a2·d2(t),…,an·dn(t)]u(t)=max[a 1 ·d 1 (t),a 2 ·d 2 (t),…,a n ·d n (t)] 其中,a1,a2,…,an为权重参数。Among them, a 1 ,a 2 ,…,a n are weight parameters. 5.如权利要求1所述的一种储能电池早期故障诊断与安全超前预警方法,其特征在于,对所述特征值序列进行凸函数处理,并添加偏置;具体包括:5. The method for early fault diagnosis and safety advance warning of energy storage batteries according to claim 1, characterized in that convex function processing is performed on the eigenvalue sequence and a bias is added; specifically comprising: c(t)=u(t)e+bc(t)=u(t) e +b 其中,c(t)为凸函数,b为偏置。Among them, c(t) is a convex function and b is a bias. 6.如权利要求1所述的一种储能电池早期故障诊断与安全超前预警方法,其特征在于,对所述特征值序列进行凸函数处理,并添加偏置;具体包括:6. The method for early fault diagnosis and safety advance warning of energy storage batteries according to claim 1, characterized in that convex function processing is performed on the eigenvalue sequence and a bias is added; specifically comprising: c(t)=eu(t)+bc(t)= eu(t) +b 其中,c(t)为凸函数,b为偏置。Among them, c(t) is a convex function and b is a bias. 7.一种储能电池早期故障诊断与安全超前预警系统,其特征在于,包括:7. An energy storage battery early fault diagnosis and safety advance warning system, characterized by comprising: 数据获取模块,用于获取储能电池的电压信号;A data acquisition module, used to acquire a voltage signal of an energy storage battery; 故障初步诊断模块,用于基于所述电压信号,采用多种故障诊断方法进行初步故障诊断结果;A preliminary fault diagnosis module, used to obtain preliminary fault diagnosis results based on the voltage signal using a variety of fault diagnosis methods; 初步故障诊断结果处理模块,用于将多种故障诊断方法的初步故障诊断结果映射为特征值序列;A preliminary fault diagnosis result processing module, used for mapping preliminary fault diagnosis results of multiple fault diagnosis methods into a feature value sequence; 具体为:Specifically: u(t)=U(d1(t),d2(t),…,dn(t))u(t)=U(d 1 (t),d 2 (t),…,d n (t)) 其中,di(t)表示第i种故障诊断算法在t时刻的故障诊断结果,i=1,2,…,n;u(t)为对特征参数di(t)整合处理后的特征量;Wherein, d i (t) represents the fault diagnosis result of the i-th fault diagnosis algorithm at time t, i = 1, 2, …, n; u(t) is the characteristic quantity after the integration of the characteristic parameter d i (t); 对所述特征值序列进行凸函数处理,并添加偏置;Performing convex function processing on the eigenvalue sequence and adding a bias; 早期故障诊断模块,用于对处理后的特征值序列进行关于时间的积分,得到储能电池早期故障诊断结果;An early fault diagnosis module is used to integrate the processed characteristic value sequence with respect to time to obtain the early fault diagnosis result of the energy storage battery; 具体地,Specifically, 其中,o(t)为u(t)关于时间的积分值,也是该框架的输出值,c(t)为凸函数;Among them, o(t) is the integral value of u(t) with respect to time, which is also the output value of the framework, and c(t) is a convex function; 当o(t)的值超过预设的阈值时,认为电池发生了故障;当故障引起o(t)突破阈值时,可根据故障发现之前时段内o(t)的曲线形状大致判断故障类型。When the value of o(t) exceeds the preset threshold, it is considered that the battery has a fault; when the fault causes o(t) to exceed the threshold, the fault type can be roughly determined based on the curve shape of o(t) in the period before the fault is discovered. 8.一种终端设备,其包括处理器和存储器,处理器用于实现各指令;存储器用于存储多条指令,其特征在于,所述指令适于由处理器加载并执行权利要求1-6任一项所述的储能电池早期故障诊断与安全超前预警方法。8. A terminal device, comprising a processor and a memory, the processor being used to implement various instructions; the memory being used to store multiple instructions, characterized in that the instructions are suitable for being loaded by the processor and executing the energy storage battery early fault diagnosis and safety advance warning method described in any one of claims 1-6. 9.一种计算机可读存储介质,其中存储有多条指令,其特征在于,所述指令适于由终端设备的处理器加载并执行权利要求1-6任一项所述的储能电池早期故障诊断与安全超前预警方法。9. A computer-readable storage medium storing a plurality of instructions, wherein the instructions are suitable for being loaded by a processor of a terminal device and executing the energy storage battery early fault diagnosis and safety advance warning method according to any one of claims 1 to 6.
CN202210872812.XA 2022-04-24 2022-07-21 Early fault diagnosis and safety advanced early warning method and system for energy storage battery Active CN115219912B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN2022104548965 2022-04-24
CN202210454896 2022-04-24

Publications (2)

Publication Number Publication Date
CN115219912A CN115219912A (en) 2022-10-21
CN115219912B true CN115219912B (en) 2024-10-29

Family

ID=83613087

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210872812.XA Active CN115219912B (en) 2022-04-24 2022-07-21 Early fault diagnosis and safety advanced early warning method and system for energy storage battery

Country Status (1)

Country Link
CN (1) CN115219912B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116125290A (en) * 2023-03-23 2023-05-16 广州汇锦能效科技有限公司 Power battery fault diagnosis method based on probability analysis
CN117007971B (en) * 2023-07-05 2024-10-15 湖南行必达网联科技有限公司 Battery fault diagnosis method, device and system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105954616A (en) * 2016-05-05 2016-09-21 江苏方天电力技术有限公司 Photovoltaic module fault diagnosis method based on external characteristic electrical parameters
CN109165242A (en) * 2018-08-01 2019-01-08 西安西热电站信息技术有限公司 A kind of fault diagnosis and method for early warning based on entropy sequence and space-time analysis

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101937207B (en) * 2010-08-27 2012-09-05 上海交通大学 Intelligent visualized monitoring and diagnosing method of mechanical equipment state
EP3232282B1 (en) * 2016-04-12 2018-09-12 Siemens Aktiengesellschaft Diagnostic device and method for monitoring the operation of a technical plant
CN110069810B (en) * 2019-03-11 2023-04-07 北京百度网讯科技有限公司 Battery failure prediction method, device, equipment and readable storage medium
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
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
CN110864902B (en) * 2019-12-24 2021-03-23 安徽工业大学 A method for early fault detection of rolling bearings based on fractional scatter entropy
CN112379295B (en) * 2020-09-29 2023-08-04 合肥工业大学 Method, system and storage medium for predicting the state of health of power battery
CN112949198B (en) * 2021-03-10 2024-04-12 阳光电源股份有限公司 Method and device for detecting faults of photovoltaic string and computer storage medium
CN113433468A (en) * 2021-05-12 2021-09-24 山东大学 Early fault fusion diagnosis method and safety early warning system for energy storage battery
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
CN113567874B (en) * 2021-06-08 2022-07-12 北京科技大学 Method and device for monitoring and detecting safety state of power battery
CN113419187B (en) * 2021-06-08 2022-05-31 上海交通大学 A Lithium-ion Battery Health Estimation Method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105954616A (en) * 2016-05-05 2016-09-21 江苏方天电力技术有限公司 Photovoltaic module fault diagnosis method based on external characteristic electrical parameters
CN109165242A (en) * 2018-08-01 2019-01-08 西安西热电站信息技术有限公司 A kind of fault diagnosis and method for early warning based on entropy sequence and space-time analysis

Also Published As

Publication number Publication date
CN115219912A (en) 2022-10-21

Similar Documents

Publication Publication Date Title
CN114430080B (en) A method for identifying abnormal self-discharge of power battery cells based on operating data
Yuan et al. Early stage internal short circuit fault diagnosis for lithium-ion batteries based on local-outlier detection
CN115219912B (en) Early fault diagnosis and safety advanced early warning method and system for energy storage battery
WO2021078257A1 (en) Method and system for diagnosing multiple faults of battery pack based on corrected sample entropy
CN112098850B (en) Lithium ion battery voltage fault diagnosis method and system based on SDO algorithm
US20220236338A1 (en) Method For Diagnosing Internal Short Circuit Of Battery Based On Relaxation Voltage
CN112924885B (en) Method for quantitatively diagnosing short circuit in battery based on peak height of incremental capacity curve
CN115684942B (en) Battery short circuit fault detection method, device, computer equipment and medium
CN115097319B (en) A method and system for online diagnosis of power battery pack fault
CN109991556B (en) A diagnostic method for short-term failure of lithium iron phosphate power battery
CN111458648A (en) Online detection method for health state of lithium ion battery
CN114062930B (en) Method, device and equipment for detecting abnormal contact of battery cell tab
CN114523878A (en) Lithium ion battery lithium separation safety early warning method and device
CN109521315A (en) Method and device for detecting internal short circuit of battery and automobile
CN113433468A (en) Early fault fusion diagnosis method and safety early warning system for energy storage battery
CN110874693A (en) Determination method, detection method and device for abnormal working condition of battery pack
CN115621584A (en) Method and system for diagnosing internal short circuit abnormality of lithium battery pack
CN119291512A (en) Battery fault diagnosis method and system based on clustering and random abnormal selection
CN118795207A (en) A power box and a method for high-precision early warning in outdoor environment
CN118777904A (en) Method, device and electronic device for determining the starting point of lithium deposition of battery
CN118688671A (en) Early internal short circuit fault diagnosis method for lithium-ion battery pack
CN116400231B (en) Battery multiple fault detection methods, devices and electronic equipment for energy storage systems
CN118169578A (en) New energy automobile power battery fault diagnosis method and fault battery positioning method
CN114264961B (en) Method and device for detecting short circuit in battery cell and electronic equipment
CN116930764A (en) Fault diagnosis and risk prediction method for lithium battery energy storage system integrating power electronics

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