WO2024016500A1 - 一种动力电池包的温度实时检测方法 - Google Patents

一种动力电池包的温度实时检测方法 Download PDF

Info

Publication number
WO2024016500A1
WO2024016500A1 PCT/CN2022/126342 CN2022126342W WO2024016500A1 WO 2024016500 A1 WO2024016500 A1 WO 2024016500A1 CN 2022126342 W CN2022126342 W CN 2022126342W WO 2024016500 A1 WO2024016500 A1 WO 2024016500A1
Authority
WO
WIPO (PCT)
Prior art keywords
temperature
battery pack
neural network
real
deep neural
Prior art date
Application number
PCT/CN2022/126342
Other languages
English (en)
French (fr)
Inventor
周宇
Original Assignee
厦门宇电自动化科技有限公司
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 厦门宇电自动化科技有限公司 filed Critical 厦门宇电自动化科技有限公司
Priority to ZA2024/00107A priority Critical patent/ZA202400107B/en
Publication of WO2024016500A1 publication Critical patent/WO2024016500A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G06F17/13—Differential equations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/094—Adversarial learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/04—Constraint-based CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/08—Thermal analysis or thermal optimisation
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M10/00—Secondary cells; Manufacture thereof
    • H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
    • H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
    • Y—GENERAL 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02E60/10—Energy storage using batteries

Definitions

  • the invention relates to, in particular, a real-time temperature detection method for a power battery pack.
  • 18650 cylindrical battery is the most widely used standard battery, where 18 means 18mm in diameter, 65 means 65mm in length, and 0 means cylindrical battery.
  • the advantages of the 18650 battery pack include large capacity, high safety performance, small internal resistance, fixed size, large capacity selection range, mature welding process, etc., and are increasingly favored by people in the industry.
  • thermodynamics Simulation methods for measuring and monitoring the temperature of power battery packs can be roughly divided into two categories.
  • One type uses optical fiber, infrared imaging, surface acoustic waves or directly uses temperature sensitive components for temperature monitoring, which can be called external temperature monitoring methods; the other type uses the self-generated characteristics and parameters of the battery or convection and turbulence models to conduct thermodynamics Simulation, this type can be called internal temperature monitoring method.
  • the sensor is placed close to the measured object and reflects the temperature of the measured object through the thermal balance theorem. This temperature measurement method is often used in situations where fewer temperature measurement points are needed. If the number of sampling points is increased, the engineering difficulty such as sensor layout, wiring placement, and circuit interface design will increase exponentially, making it difficult to implement too many temperature sensors.
  • the internal temperature measurement method is mainly implemented by establishing a corresponding model.
  • the impedance-based temperature measurement method is one of the internal temperature measurement methods, and this method requires a large amount of experimental data [3].
  • the object of the present invention is to provide a real-time detection method for the temperature of a power battery pack.
  • the present invention aims to solve the problem of accuracy of real-time temperature detection of battery packs.
  • a real-time temperature detection method for a power battery pack including:
  • the deep neural network model is called to predict the temperature at other locations through the temperature of the sampling point in the battery pack, and a three-dimensional space corrected temperature field that is close to the real temperature field is obtained.
  • the deep neural network model is a three-dimensional convolutional neural network, and its convolution algorithm formula is:
  • x is the input three-dimensional matrix
  • y is the output three-dimensional matrix
  • i, j, k are the coordinates of the three dimensions
  • U, V, W are the three-dimensional sizes of the convolution kernel, taking an odd number
  • ⁇ is the element value of the convolution kernel .
  • the real-time temperature detection method also includes training the deep neural network model.
  • the deep neural network training method for the deep neural network model includes:
  • the discriminator outputs a judgment result and feeds the judgment result back to the deep neural network model
  • the deep neural network model is optimized based on the determination results and generates a new corrected temperature field
  • the discriminator is a two-class classifier, and outputs a result determined to be an actual measured temperature value or an estimated temperature value.
  • Q P I 2 R ⁇
  • C cell is the battery specific heat capacity
  • T cell is the battery temperature
  • t is the charge and discharge time
  • ⁇ is the thermal conductivity
  • R is the battery radius
  • Q S is the reversible reaction heat
  • Q P is the battery polarization reaction Heat and Joule heat
  • V battery volume I battery charge and discharge current
  • E emf is the battery open circuit voltage
  • R ⁇ is the battery equivalent internal resistance.
  • k) a ⁇ i (k
  • the mean square prediction error equation is:
  • k) a 2 P(k
  • a is the state transition parameter
  • c is the measurement gain
  • both are constants
  • ⁇ represents the delay time from temperature sampling to result output.
  • it also includes establishing a sensor network for battery packs of specified models.
  • the present invention uses the actual measured temperature of limited sampling points.
  • This invention draws on the idea of the deep learning generative adversarial network (GAN) model, innovatively introduces a three-dimensional convolutional neural network model, and incorporates the Kalman prediction model into the
  • the core parameter solution is also incorporated into the deep learning iterative training process of the neural network model, so that the model has three-dimensional spatial correlation and stronger real-time performance.
  • GAN deep learning generative adversarial network
  • the present invention uses the temperature of limited sampling points, the voltage parameters and current parameters of the battery pack as constraints of the battery pack temperature field model to derive the current theoretical temperature field of the battery pack, which has a wide application range.
  • This invention draws on the idea of generative adversarial network models and uses temperature measurement, voltage and current values of a small number of discrete points in three-dimensional space to effectively invert the three-dimensional temperature field of the power battery pack.
  • the present invention deduces a three-dimensional convolutional neural network from conventional deep learning two-dimensional convolution, converts limited-time measured data into a three-dimensional theoretical temperature field through the battery pack temperature field model, and then converts the three-dimensional theoretical temperature field through the three-dimensional
  • the convolutional neural network generates a three-dimensional space corrected temperature field that is closer to the real temperature field, thereby retaining the correlation of the three-dimensional space information and obtaining more realistic information about the three-dimensional space of the battery pack.
  • Figure 1 is a flow chart of a real-time temperature detection method for a power battery pack provided by an embodiment of the present invention
  • Figure 2 is an algorithm block diagram of the Kalman prediction model provided by the embodiment of the present invention.
  • Figure 3 is a flow chart of a real-time temperature detection method for a power battery pack provided by an embodiment of the present invention, including a neural network training process;
  • Figure 4 is a measured distribution diagram of the temperature field of the 18650 power battery pack provided by the embodiment of the present invention.
  • (a) is the measured temperature distribution diagram of the middle layer temperature sensor
  • (b) is the measured temperature distribution diagram of the bottom layer temperature sensor;
  • Figure 5 is a three-dimensional structural modeling diagram of an 18650 power battery pack provided by an embodiment of the present invention.
  • Figure 6 is a schematic diagram of the meshing of the 18650 power battery pack model provided by the embodiment of the present invention.
  • Figure 7 is a three-dimensional temperature field distribution diagram of an 18650 power battery pack provided by an embodiment of the present invention. (a) is the theoretical temperature field in three-dimensional space, and (b) is the corrected temperature field in three-dimensional space.
  • a real-time temperature detection method for a power battery pack includes:
  • the Kalman prediction model 12 is the optimal estimate of random signals, and its filtering process involves predicting the signal ⁇ i (k) at time k through the signal at time k-1.
  • i is an integer and can be 1.
  • n is the number of sampling points.
  • the mathematical model of the random signal to be estimated is a first-order recursive process driven by the white noise sequence ⁇ w(k) ⁇ , and its dynamic equation is:
  • ⁇ i (k) a ⁇ i (k-1)+w(k-1)
  • Kalman prediction model 12 a is the state transition parameter, c is the measurement gain, both are constants.
  • w(k-1) is process noise, also known as system noise, and v(k) is measurement noise.
  • Their square mathematical expectations are ⁇ w 2 and ⁇ v 2 respectively. Both are constants and are unknown variables in the training model. They need to Continuously optimize the solution in iterative operations.
  • k) a ⁇ i (k
  • k) a 2 P(k
  • ⁇ represents the delay from temperature sampling to result output. Because the prediction algorithm takes a certain amount of time to run, the temperature field output result actually has a delay of period ⁇ , so it is necessary to predict the result of a period ⁇ forward.
  • the Kalman prediction model 12 can adaptively change according to the motion state and can achieve the optimal filtering effect. Cleverly integrating measured data and estimated data, closed-loop management of errors can effectively limit random errors, thereby achieving optimal estimation results.
  • the formula of battery pack temperature field model 2 is:
  • C cell is the battery specific heat capacity
  • T cell is the battery temperature
  • t is the charge and discharge time
  • ⁇ is the thermal conductivity
  • R is the battery radius
  • Q S is the reversible reaction heat
  • Q P is the battery polarization reaction heat and Joule heat
  • V Battery volume I battery charge and discharge current
  • E emf is the battery open circuit voltage
  • R ⁇ is the battery equivalent internal resistance.
  • Deep neural network model 4 is a generative neural network, which can be an autoencoder/decoder, U-net, Transformer, etc., or an ordinary neural network, such as a fully connected network.
  • the formula of deep neural network model 4 is as follows:
  • x is the input three-dimensional matrix
  • y is the calculation result, which is also a three-dimensional matrix
  • i, j, k are the coordinates of the three dimensions
  • U, V, W are the three-dimensional sizes of the convolution kernel, taking an odd number
  • ⁇ is the convolution kernel element value.
  • the deep neural network model 4 is continuously optimized to make the mapping relationship between the theoretical temperature field 3 in the three-dimensional space and the real temperature field more accurate.
  • the steps to optimize a deep neural network model are as follows:
  • the discriminator 9 is a classifier, here is a two-class classification, which can be in the form of LDA, SVM, KNN, Decision Tree, Random Forest, Bayes, ANN, etc.
  • the discriminator 9 outputs the judgment result and feeds the judgment result back to the deep neural network model 4.
  • the discriminator 9 outputs a result that is determined to be the actual measured temperature value 11 or the estimated temperature value 10, which must be one of the two.
  • the deep neural network model 4 is optimized according to the determination result and generates a new corrected temperature field 5.
  • the 18650 battery pack includes 7 series and 7 parallel cells, a total of 49 battery cells.
  • the 18650 battery cell model is Panasonic NCR18650BD, weighs 46.8g, and each cell has a nominal voltage of 3.7V and a capacity of 3200mAh.
  • the battery pack model consists of a total of 49 18650 battery cells. Each battery cell is cylindrical with a diameter of 18mm and a height of 65mm.
  • the temperature of each point in the battery pack after the battery is discharged for a certain period of time is calculated, and the battery pack temperature field model is used to further construct a theoretical temperature field in three-dimensional space.
  • the deep neural network model 4 in this embodiment adopts a U-net structure.
  • the three-dimensional space of the battery pack is divided into a temperature field simulation node every 1mm. Each node has a volume of 1mm 3 .
  • the battery pack temperature field processes three-dimensional information to more completely preserve the associated information in the three-dimensional space of the temperature field.
  • the discriminator 9 is a fully connected ANN structure with a total of 7 layers.
  • the first 6 layers are linear operations.
  • the number of nodes is: 32, 16, 8, 4, 2, 1.
  • the last layer is an activation function.
  • This The activation function is a step function, which is a nonlinear operation.
  • the output is divided into two states: 0 and 1. 0 indicates that the sampling point is determined to be the estimated temperature, and 1 indicates that the sampling point is determined to be the measured temperature.
  • the measured temperature value is used to train the deep neural network model according to the method in Figure 3, and then the three-dimensional spatial temperature field of the 18650 battery pack is obtained according to the real-time temperature detection method of the power battery pack in Figure 1, as shown in Figure 7,
  • (a) is the three-dimensional theoretical temperature field of the power battery pack calculated by the battery pack temperature field model.
  • (b) is the three-dimensional space corrected temperature field of the power battery pack output by the deep neural network model 4, in which the relatively high temperature area is circled, and Fig. Comparing the measured temperature distribution diagram of 4, it can be seen that the corrected temperature distribution is closer to the actual thermal field distribution.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Hardware Design (AREA)
  • Secondary Cells (AREA)
  • Algebra (AREA)
  • Geometry (AREA)
  • Operations Research (AREA)

Abstract

本发明提供了一种动力电池包的温度实时检测方法，来实现对动力电池包的温度检测与热场分析，利用动力电池包的电流、电压信息及材料热力学参数对其温度场进行模拟仿真，并用离散实测温度数据通过深度神经网络和卡尔曼滤波器进行修正，使所建立的温度场模型能更真实地反映电池包实际的温度场分布。

Description

一种动力电池包的温度实时检测方法 技术领域
本发明涉及，特别涉及一种动力电池包的温度实时检测方法。
背景技术
大力推动新能源是当今时代发展的主题之一。由动力电池单体通过串联、并联、混联等方式组成的电池包已经在电动自行车、电动汽车、工业电力系统等行业广泛应用。然而，动力电池包存在老化、鼓包甚至着火等问题，严重阻碍了它的推广。电池包的热场失衡问题备受业内关注。因此，建立准确有效的动力电池包温度场模型将有利于有效评估电池温度场的分布特点和变化情况，是当前电池热管理的一个重要研究方向。
动力电池种类繁多，锂电池以其能量密度高、使用寿命长等优势被广泛应用。锂电池中，18650柱状电池是应用最为广泛的标准电池，其中18表示直径为18mm，65表示长度为65mm，0表示为圆柱形电池。18650电池包的优点包括容量大、安全性能高、内阻小、尺寸固定、容量选择范围大、焊接工艺成熟等，越来越受到业内人士的青睐。
目前，对于测量监控动力电池包的温度方法大致可分为两类。一类是利用光纤、红外成像、声表面波或直接利用温度敏感元件进行温度监测，这类可称为外部温度监测方法；另一类是利用电池的自生特性和参数或对流、湍流模型进行热力学仿真，这类可称为内部温度监测方法。将传感器紧贴被测物体，通过热平衡定理，来反映出被测对象的温度，此种测温方法往往应用于只需较少测温点的场合。若增加采样点数，传感器的布局、走线的安放、电路接口的设计等工程难度都将呈几何级数上升，布置太多的温度传感器难以实现。相对于电池的外部测温方法，内部测温方法主要通过建立相应的模型实现。例如，基于阻抗的测温方法是内部测温方法中的一种，这种方法需要大量的实验数据[3]。也有利用计算流体力学及有限元分析软件，通过引入传导和对流等模型来进行 数值计算和热力学仿真的方法。电池热力学模型与电池实际发热/传热的差异，比热、传导等参数的误差，都会导致电池包温度场计算的偏差。
有鉴于此，如何提高电池包温度场计算的准确度为本领域需要解决的技术问题。
发明内容
本发明的目的是提供一种动力电池包的温度实时检测方法。
本发明要解决的是的对电池包实时温度检测准确性的问题。
为了解决上述问题，本发明通过以下技术方案实现：
一种动力电池包的温度实时检测方法，包括：
采集动力电池包在放电状态下的电压参数及电流参数；
采集电池包若干采样点的实测温度值；
若干实测温度输入至卡尔曼预测模型得到采样点下一步预测温度值；
将所述下一步预测温度、所述电压参数及电流参数输入至电池包温度场模型，得到电池包的三维空间理论温度场；
建立三维空间理论温度场到所有温度节点映射的深度神经网络模型；
调用深度神经网络模型，通过电池包内采样点温度来预测其他位置的温度，得到逼近真实温度场的三维空间修正温度场。
进一步地，深度神经网络模型为三维卷积神经网络，其卷积算法公式：
Figure PCTCN2022126342-appb-000001
其中，x是输入三维矩阵；y为输出三维矩阵；i、j、k为三个维度的坐标；U、V、W为卷积核的三维尺寸，取奇数；ω是卷积核的元素值。
进一步地，温度实时检测方法，还包括对所述深度神经网络模型训练。
进一步地，对深度神经网络模型的深度神经网络训练方法包括：
S1、将若干所述实测温度值输入至判别器；
S2、对所述修正温度场进行离散采样得到估计温度值，所述估计温度值输入至所述判别器；对所述修正温度场进行离散采样的采样坐标与输入判别器的实测温度的采样坐标一一对应；
S3、所述判别器输出判定结果并将判定结果反馈至所述深度神经网络模型；
S4、所述深度神经网络模型根据判定结果进行优化并生成新的修正温度场；
S5、重复S1至S4，直至所述判别器的正确率为50％±ε时，深度神经网络模型优化完成。
进一步地，所述ε≤1％。
进一步地，所述判别器为二分类的分类器，输出判定为实测温度值或估计温度值的结果。
进一步地，由所述电池包温度场模型的公式为：
Figure PCTCN2022126342-appb-000002
其中，
Figure PCTCN2022126342-appb-000003
Q P＝I 2R θ，C cell为电池比热容，T cell为电池温度，t为充放电时间，γ为导热系数，R为电池半径，Q S为可逆反应热，Q P为电池极化反应热和焦耳热，V电池体积，I电池充放电电流，E emf为电池开路电压，R θ为电池等效内阻。
进一步地，卡尔曼预测模型的公式为：
τ i(k+1|k)＝aτ i(k|k-1)+β(k)[t i(k)–cτ i(k|k-1)]
其中，预测增益方程为：
Figure PCTCN2022126342-appb-000004
均方预测误差方程为：
P(k+1|k)＝a 2P(k|k-1)-acβ(k)P(k|k-1)]+σ w 2
计算起始条件可令τ i(1|0)＝t i(1)，β(k)＝0，由此得到采样点下一步预测 温度τ i(k+1|k)；
其中，a为状态转移参量，c为测量增益，均为常数，δ表示温度采样到结果输出的延时时长。
进一步地，还包括对指定型号的电池包建立传感网络。
与现有技术相比，本发明技术方案及其有益效果如下：
(1)本发明的将有限采样点的实测温本发明借鉴了深度学习生成式对抗网络(GAN)模型的思路，创新性地引入了三维卷积神经网络模型，并将卡尔曼预测模型中的核心参数求解也纳入神经网络模型的深度学习迭代训练过程，从而使得该模型具备三维空间相关性以及更强的实时性。
(2)本发明将有限采样点的温度、电池包的电压参数及电流参数作为电池包温度场模型的约束，推导出电池包当前的理论温度场，适用范围广。
(3)本发明借鉴生成式对抗网络模型的思路，利用少量三维空间离散点的测温和电压、电流值，有效反演动力电池包的三维温度场。
(4)本发明从常规的深度学习二维卷积演绎出三维卷积神经网络，将有限次实测数据经过电池包温度场模型转换成三维空间理论温度场，再将三维空间理论温度场通过三维卷积神经网络生成更加逼近真实温度场的三维空间修正温度场，从而保留三维空间信息的相关性，获得电池包三维空间更真实的信息。
附图说明
图1是本发明实施例提供的一种动力电池包的温度实时检测方法的流程图；
图2是本发明实施例提供的卡尔曼预测模型的算法框图；
图3是本发明实施例提供的一种动力电池包的温度实时检测方法的流程图，包括神经网络训练流程；
图4是本发明实施例提供的18650动力电池包温度场实测分布图，(a)为 中间层温度传感器实测温度分布图，(b)为底层温度传感器实测温度分布图；
图5是本发明实施例提供的18650动力电池包三维结构建模图；
图6是本发明实施例提供的18650动力电池包模型网格划分示意图；
图7是本发明实施例提供的18650动力电池包三维空间温度场分布图，(a)为三维空间理论温度场，(b)为三维空间修正温度场。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
参阅图1，一种动力电池包的温度实时检测方法，包括：
S1、对指定型号的动力电池包建立传感网络。包括选择电池包内需要实测温度的位置，在该位置放置温度传感器。完成温度传感器、测温仪、充电设备及上位机相互之间的硬件连接及软件通讯，此为现有技术，不再赘述。
S2、通过传感网络采集电池包若干采样点的实测温度值8。
S3、采集动力电池包在放电状态下的电压参数及电流参数1。
S4、若干实测温度输入至卡尔曼预测模型得到采样点下一步预测温度值13。
卡尔曼预测模型12是对随机信号的最优估计，而且在其滤波过程中涉及到通过k-1时刻的信号对k时刻的信号τ i(k)的预测，i为整数取值可以为1、2、…、n，n为采样点的个数。我们可以假设待估随机信号的数学模型是一个由白噪声序列{w(k)}驱动的一阶递归过程，其动态方程为：
τ i(k)＝aτ i(k-1)+w(k-1)
测量过程的数学模型有白噪声{v(k)}扰动，其动态方程为：
t i(k)＝cτ i(k)+v(k)
其中a为状态转移参量，c为测量增益，均为常数。w(k-1)为过程噪声又名系统噪声，v(k)为测量噪声，他们的平方数学期望分别为σ w 2与σ v 2，均为常数，在训练模型中属于未知变量，需要在迭代运算中不断优化求解。卡尔曼预测模型12的公式：
τ i(k+1|k)＝aτ i(k|k-1)+β(k)[t i(k)–cτ i(k|k-1)]
其中预测增益方程：
Figure PCTCN2022126342-appb-000005
均方预测误差方程：
P(k+1|k)＝a 2P(k|k-1)-acβ(k)P(k|k-1)]+σ w 2
计算起始条件可令τ i(1|0)＝t i(1)，β(k)＝0，根据以上公式组即可得到下一个采样点随机信号的最优估计τ i(k+1|k)。
卡尔曼预测模型12的算法框图如图2所示。δ表示温度采样到结果输出的延时。因为预测算法运行需要一定的时间，温度场输出结果其实有周期δ的延时，因此需要向前预测一个周期δ的结果。
卡尔曼预测模型12能够根据运动状态自适应改变，可以实现最优的滤波效 果。巧妙地融合了实测数据与估计数据，对误差进行闭环管理，能有效地限制随机误差，从而达到最优的估计效果。
S5、将下一步预测温度值13、电压参数及电流参数1输入至电池包温度场模型2，从而得到电池包的三维空间理论温度场3。
由电池包温度场模型2的公式为：
Figure PCTCN2022126342-appb-000006
其中Q S、Q P由以下方程求出：
Figure PCTCN2022126342-appb-000007
Q P＝I 2R θ
将Q S、Q P的公式带入上述电池包温度场模型的公式中，可得：
Figure PCTCN2022126342-appb-000008
其中，C cell为电池比热容，T cell为电池温度，t为充放电时间，γ为导热系数，R为电池半径，Q S为可逆反应热，Q P为电池极化反应热和焦耳热，V电池体积，I电池充放电电流，E emf为电池开路电压，R θ为电池等效内阻。
S6、建立三维空间理论温度场3到所有温度节点映射的深度神经网络模型4，三维空间理论温度场3通过深度神经网络模型4得到三维空间修正温度场5。
深度神经网络模型4为一种生成式神经网络，可以是自编码/解码器、U-net、Transformer等，也可以是普通的神经网络，比如全连接网络。深度神经网络模型4的公式如下：
Figure PCTCN2022126342-appb-000009
其中，x是输入三维矩阵；y为计算结果，也是三维矩阵；i、j、k为三个维度的坐标；U、V、W为卷积核的三维尺寸，取奇数；ω是卷积核的元素值。
参阅图3，不断优化深度神经网络模型4，以使得三维空间理论温度场3到真实温度场的映射关系更加精准。优化深度神经网络模型的步骤如下：
S61、将若干所述实测温度值输入至判别器9，判别器9为一种分类器，此处为二分类，可以是LDA、SVM、KNN、Decision Tree、Random Forest、Bayes、ANN等形式。
S62、对修正温度场5进行离散采样得到估计温度值7，估计温度值7输入至判别器4；对修正温度场5进行离散采样的采样坐标6与S61中输入判别器9的实测温度的采样坐标一一对应。
S63、判别器9输出判定结果并将判定结果反馈至深度神经网络模型4。判别器9输出判定为实测温度值11或估计温度值10的结果，二者必具其一。
S64、深度神经网络模型4根据判定结果进行优化并生成新的修正温度场5。
重复S61至S64，即判别器9与深度神经网络模型4交替优化，反复迭代，直至判别器9无法分辨实测温度值11与估计温度值10，即表示深度神经网络模型4输出的三维空间修正温度场5与实测的温度场十分的接近，再即，深度神经网络模型4的训练完成。本是实施例中，当判别器的二分类正确率为50％±ε时，视为判别器9无法分辨实测温度值11与估计温度值10，ε的数值可以根据具体情况设定，本实施例中，ε≤1％，从而得到更为优化的深度神经网络模型。
S7、调用深度神经网络模型，通过电池包内采样点温度来预测其他位置的温度，得到无限逼近实际温度场的修正温度场5，从而完成对动力电池包的温度实时检测。
下面以18650电池包为例，对本发明的检测方法作进一步说明。
本实施例中，18650电池包包括7串7并共49个电池单体，18650电池单体型号为Panasonic NCR18650BD、重量46.8g，每个单体标称电压3.7V、容量3200mAh。在这个7×7的电池包中，有6×6＝36条狭缝间隙可供安放温度传感 器，每条狭缝安放2个传感器，分别位于中部和底部，一共安放了72个热电偶温度传感器，并完成热电偶温度传感器、负载、主机、充电设备、测温仪之间的硬件连接和软件通讯连接相连。
参阅图4，该动力电池包72个温度传感器在某一时刻的输出结果，其中，(a)为中间层36路温度传感器的温度分布，(b)为底层36路温度传感器的温度分布。
用SOLIDWORKS绘制18650电池单体的结构，并绘制电池包组装图，然后基于有限元分析软件ANSYS Workbench，结合实测数据，对18650电池包进行三维温度场仿真。将SOLIDWORKS建好的三维模型导入ANSYS Workbench进行仿真，根据动力电池包实物等比例建立三维模型。
如图5所示，电池包模型共由49个18650电池单体组成，每个电池单体为圆柱形，圆柱直径为18mm，高为65mm。
再将SOLIDWORKS中所建立的三维模型导入ANSYS Workbench中进行网格划分，网格划分示意如图6所示。
知道电池单体及电池包的规格参数以及材料特性后，并计算出电池包在电池放电一定时间后各点的温度，通过电池包温度场模型，从而进一步构建出三维空间的理论温度场。
本实施例中的深度神经网络模型4采用U-net结构。电池包三维空间每1mm间隔剖分一个温度场仿真节点，每个节点体积1mm 3，一共126×126×65个温度场仿真节点，通过U-net映射到修正后的126×126×65个温度节点，用于逼近电池包的实际温度场分布。与常规的深度神经网络处理二维图像不同，电池包温度场处理的是三维信息，以更完备地保存温度场三维空间的关联信息。
本实施例中，判别器9全连接的ANN结构，共7层，前6层为线性运算，节点数依次为：32、16、8、4、2、1，最后一层为激活函数，此激活函数为一 阶跃函数，属于非线性运算，输出分0、1两态，0表示判别为采样点是估计温度，1表示判别采样点为实测温度。
将实测温度值按照图3的方法对深度神经网络模型进行训练，再按照图1的动力电池包的温度实时检测方法，得到18650电池包的三维空间温度场，如图7所示，(a)是电池包温度场模型计算出来的动力电池包三维空间理论温度场，(b)是通过深度神经网络模型4输出的动力电池包三维空间修正温度场，其中圈画出相对高温的区域，与图4的实测温度分布图相对比，可以看出，修正后的温度分布更接近实际热场分布。
上述说明示出并描述了本发明的优选实施例，应当理解本发明并非局限于本文所披露的形式，不应看作是对其他实施例的排除，而可用于各种其他组合、修改和环境，并能够在本文发明构想范围内，通过上述教导或相关领域的技术或知识进行改动。而本领域人员所进行的改动和变化不脱离本发明的精神和范围，则都应在本发明所附权利要求的保护范围内。

Claims (9)

  1. 一种动力电池包的温度实时检测方法，其特征在于，包括：
    采集动力电池包在放电状态下的电压参数及电流参数；
    采集电池包若干采样点的实测温度值；
    若干实测温度输入至卡尔曼预测模型得到采样点下一步预测温度值；
    建立电池包温度场模型，并将所述下一步预测温度、所述电压参数及电流参数输入至电池包温度场模型，得到电池包的三维空间理论温度场；
    建立三维空间理论温度场到所有温度节点映射的深度神经网络模型；
    调用深度神经网络模型，通过电池包内采样点温度来预测其他位置的温度，得到逼近真实温度场的三维空间修正温度场。
  2. 根据权利要求1所述的一种动力电池包的温度实时检测方法，其特征在于，所述深度神经网络模型为三维卷积神经网络，其卷积算法公式：
    Figure PCTCN2022126342-appb-100001
    其中，x是输入三维矩阵；y为输出三维矩阵；i、j、k为三个维度的坐标；U、V、W为卷积核的三维尺寸，取奇数；ω是卷积核的元素值。
  3. 根据权利要求1所述的一种动力电池包的温度实时检测方法，其特征在于，还包括对所述深度神经网络模型训练。
  4. 根据权利要求3所述的一种动力电池包的温度实时检测方法，其特征在于，所述对深度神经网络模型的深度神经网络训练方法包括：
    S1、将若干所述实测温度值输入至判别器；
    S2、对所述修正温度场进行离散采样得到估计温度值，所述估计温度值输入至所述判别器；对所述修正温度场进行离散采样的采样坐标与输入判别器的实测温度的采样坐标一一对应；
    S3、所述判别器输出判定结果并将判定结果反馈至所述深度神经网络模型；
    S4、所述深度神经网络模型根据判定结果进行优化并生成新的修正温度场；
    S5、重复S1至S4，直至所述判别器的正确率为50％±ε时，深度神经网络 模型优化完成。
  5. 根据权利要求4所述的一种动力电池包的温度实时检测方法，其特征在于，所述ε≤1％。
  6. 根据权利要求4所述的一种动力电池包的温度实时检测方法，其特征在于，所述判别器为二分类的分类器，输出判定为实测温度值或估计温度值的结果。
  7. 根据权利要求1所述的一种动力电池包的温度实时检测方法，其特征在于，由所述电池包温度场模型的公式为：
    Figure PCTCN2022126342-appb-100002
    其中，
    Figure PCTCN2022126342-appb-100003
    Q P＝I 2R θ，C cell为电池比热容，T cell为电池温度，t为充放电时间，γ为导热系数，R为电池半径，Q S为可逆反应热，Q P为电池极化反应热和焦耳热，V电池体积，I电池充放电电流，E emf为电池开路电压，R θ为电池等效内阻。
  8. 根据权利要求1所述的一种动力电池包的温度实时检测方法，其特征在于，所述卡尔曼预测模型的公式为：
    τ i(k+1|k)＝aτ i(k|k-1)+β(k)[t i(k)–cτ i(k|k-1)]
    其中，预测增益方程为：
    Figure PCTCN2022126342-appb-100004
    均方预测误差方程为：
    P(k+1|k)＝a 2P(k|k-1)-acβ(k)P(k|k-1)]+σ w 2
    计算起始条件可令τ i(1|0)＝t i(1)，β(k)＝0，由此得到采样点下一步预测温度τ i(k+1|k)；
    其中，a为状态转移参量，c为测量增益，均为常数，δ表示温度采样到结果输出的延时时长。
  9. 根据权利要求1所述的一种动力电池包的温度实时检测方法，其特征在 于，还包括对指定型号的动力电池包建立传感网络。
PCT/CN2022/126342 2022-10-13 2022-10-20 一种动力电池包的温度实时检测方法 WO2024016500A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
ZA2024/00107A ZA202400107B (en) 2022-10-13 2024-01-02 Real-time temperature detection method for power battery pack

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211255274.6 2022-10-13
CN202211255274.6A CN115659790B (zh) 2022-10-13 2022-10-13 一种动力电池包的温度实时检测方法

Publications (1)

Publication Number Publication Date
WO2024016500A1 true WO2024016500A1 (zh) 2024-01-25

Family

ID=84987844

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/126342 WO2024016500A1 (zh) 2022-10-13 2022-10-20 一种动力电池包的温度实时检测方法

Country Status (3)

Country Link
CN (1) CN115659790B (zh)
WO (1) WO2024016500A1 (zh)
ZA (1) ZA202400107B (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117613326B (zh) * 2024-01-23 2024-04-05 新研氢能源科技有限公司 一种基于区域温度的燃料电池控制方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102195101A (zh) * 2010-03-05 2011-09-21 陕西铭越信息科技有限公司 动力电池组管理系统以及方法
CN106646265A (zh) * 2017-01-22 2017-05-10 华南理工大学 一种锂电池soc估计方法
CN108334940A (zh) * 2018-03-01 2018-07-27 大连道道科技有限公司 一种基于深度神经网络的锂电池包多个电池单体soc实时联合预测方法
CN109755683A (zh) * 2018-12-04 2019-05-14 厦门大学 一种基于压缩感知理论的电池包内部温度实时监测方法
CN112092676A (zh) * 2020-09-25 2020-12-18 吉林大学 一种利用虚拟温度传感器对电池包温度场的估算修正方法

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005059579A1 (en) * 2003-12-18 2005-06-30 Lg Chem, Ltd. Apparatus and method for estimating state of charge of battery using neural network
CN102034006B (zh) * 2010-12-16 2014-04-30 上海奕洁汽车科技有限公司 一种基于有限元法的蓄电池热管理分析及优化方法
CN109061506A (zh) * 2018-08-29 2018-12-21 河海大学常州校区 基于神经网络优化ekf的锂离子动力电池soc估计方法
CN113971332A (zh) * 2020-07-22 2022-01-25 上汽通用汽车有限公司 考虑电芯老化程度的电动汽车电池包温度场模型和方法
CN111983471B (zh) * 2020-08-24 2022-11-22 哈尔滨理工大学 一种基于双卡尔曼滤波的锂离子动力电池安全度估算方法及估算装置
CN112838295B (zh) * 2020-12-30 2022-05-10 广州橙行智动汽车科技有限公司 电池加热系统检测方法、装置、车辆及存储介质
KR20220110948A (ko) * 2021-02-01 2022-08-09 한국전기연구원 디지털트윈 장치 및 디지털트윈 기반의 배터리 온도감시방법
CN113281655B (zh) * 2021-05-20 2022-03-04 中南大学 一种低温环境下动力电池内部加热预测控制方法及装置
CN113722877B (zh) * 2021-07-14 2024-05-24 广东工业大学 一种对锂电池放电时温度场分布变化进行在线预测的方法
CN114184962B (zh) * 2021-10-19 2022-12-13 北京理工大学 一种多算法融合的锂离子电池soc和soh联合估算方法
CN114035054A (zh) * 2021-11-17 2022-02-11 重庆邮电大学 基于卡尔曼滤波器和神经网络联合估计模型的SoC估计方法
CN115113052A (zh) * 2022-06-27 2022-09-27 重庆大学 在线检测锂离子电池温度场及内热源场的方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102195101A (zh) * 2010-03-05 2011-09-21 陕西铭越信息科技有限公司 动力电池组管理系统以及方法
CN106646265A (zh) * 2017-01-22 2017-05-10 华南理工大学 一种锂电池soc估计方法
CN108334940A (zh) * 2018-03-01 2018-07-27 大连道道科技有限公司 一种基于深度神经网络的锂电池包多个电池单体soc实时联合预测方法
CN109755683A (zh) * 2018-12-04 2019-05-14 厦门大学 一种基于压缩感知理论的电池包内部温度实时监测方法
CN112092676A (zh) * 2020-09-25 2020-12-18 吉林大学 一种利用虚拟温度传感器对电池包温度场的估算修正方法

Also Published As

Publication number Publication date
CN115659790B (zh) 2024-02-06
CN115659790A (zh) 2023-01-31
ZA202400107B (en) 2024-03-27

Similar Documents

Publication Publication Date Title
Yang et al. Extreme learning machine-based thermal model for lithium-ion batteries of electric vehicles under external short circuit
CN108627766B (zh) 电池模组中电芯内部温度的实时测量方法及电池包
CN109755683A (zh) 一种基于压缩感知理论的电池包内部温度实时监测方法
Yang et al. The remaining useful life estimation of lithium-ion battery based on improved extreme learning machine algorithm
WO2024016500A1 (zh) 一种动力电池包的温度实时检测方法
KR102387780B1 (ko) 신경망 기반의 배터리 용량 추정 방법 및 장치
Wang et al. Temperature prediction of lithium-ion battery based on artificial neural network model
CN115236516B (zh) 基于电化学模型的锂电池的预警方法
CN113177290B (zh) 基于深度代理模型归一化的卫星组件温度场预测方法
Samad et al. Parameterization of battery electrothermal models coupled with finite element flow models for cooling
CN110427639A (zh) 基于双尺度流形学习的锂离子电池热过程时空建模方法
CN115587512A (zh) 基于ANSYS TwinBuilder的锂电池热电耦合数字孪生模型构建方法
Xie et al. Improving the air-cooling performance for battery packs via electrothermal modeling and particle swarm optimization
Xu et al. State-of-charge estimation and health prognosis for lithium-ion batteries based on temperature-compensated Bi-LSTM network and integrated attention mechanism
CN114186437A (zh) 一种面向电源系统可靠性仿真分析的多物理场耦合退化模型降阶方法
Ma et al. A novel health index for battery RUL degradation modeling and prognostics
CN117195713A (zh) 一种基于深度算子学习的锂电池模组温度场重建方法
CN115438588B (zh) 一种锂电池的温度预测方法、系统、设备及存储介质
KR20210016828A (ko) 배터리 관리 장치, 배터리 관리 방법 및 배터리 팩
CN115718883A (zh) 电池储能系统热预警方法及装置
CN115632181A (zh) 锂电池温度预警方法、系统、存储介质及终端
CN114035053A (zh) 一种锂电池热失控预警方法及其系统
CN114520389A (zh) 储能装置内部温度的确定方法及装置
Wu et al. State-of-Charge and State-of-Health Joint Estimation of Lithium-Ion Battery Based on Iterative Unscented Kalman Particle Filtering Algorithm With Fused Rauch–Tung–Striebel Smoothing Structure
Zhang et al. Estimation of state of health based on charging characteristics and back-propagation neural networks with improved atom search optimization algorithm

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22951764

Country of ref document: EP

Kind code of ref document: A1