CN111983457A - A battery pack SOH estimation method based on LSTM neural network - Google Patents
A battery pack SOH estimation method based on LSTM neural networkDownload PDFInfo
- Publication number
- CN111983457A CN111983457ACN202010678378.2ACN202010678378ACN111983457ACN 111983457 ACN111983457 ACN 111983457ACN 202010678378 ACN202010678378 ACN 202010678378ACN 111983457 ACN111983457 ACN 111983457A
- Authority
- CN
- China
- Prior art keywords
- neural network
- battery pack
- lstm neural
- output
- soh
- 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.)
- Pending
Links
Images
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]
- G01R31/367—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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06N3/045—Combinations of networks
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06N3/048—Activation functions
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Secondary Cells (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明属于新能源电动汽车电池组健康状态估算领域，具体涉及一种基于LSTM神经网络的电池组SOH估算方法。The invention belongs to the field of estimating the state of health of a battery pack of a new energy electric vehicle, and in particular relates to a method for estimating the SOH of a battery pack based on an LSTM neural network.
背景技术Background technique
锂离子动力电池因其循环寿命长、能量密度大、安全性好等优点被应用于电动汽车。为了满足电动汽车实际运行时的能量和功率要求，大量的单体电池被串联和并联到电池组中。从电动汽车安全性和动力性的角度出发，对电池组健康状态(State of Health，SOH)的在线估算十分重要。电池组的健康状态直接反映了电池组的老化情况和电池组的当前状态(包括容量和功率的输出能力)。电池组健康状态的正确估算不仅可以及时避免电池的不安全行为，也可以为电池组的维护和更换工作提供保障。Lithium-ion power batteries are used in electric vehicles because of their long cycle life, high energy density, and good safety. In order to meet the energy and power requirements of the actual operation of electric vehicles, a large number of single cells are connected in series and parallel to the battery pack. From the perspective of electric vehicle safety and power, online estimation of the state of health (SOH) of the battery pack is very important. The state of health of the battery pack directly reflects the aging of the battery pack and the current state of the battery pack (including capacity and power output capability). Correct estimation of the state of health of the battery pack can not only avoid unsafe behavior of the battery in time, but also provide guarantee for the maintenance and replacement of the battery pack.
目前，对于电池组SOH估算的主要方法有：At present, the main methods for battery pack SOH estimation are:
(1)查表法：通过实验测试电池组循环次数和SOH的对应关系，离线查表对电池组SOH进行估计；但是实验数据的测试周期长，且估算结果误差较大。(1) Look-up table method: The corresponding relationship between the number of cycles of the battery pack and SOH is tested experimentally, and the SOH of the battery pack is estimated by off-line look-up table; however, the test period of the experimental data is long, and the error of the estimation result is large.
(2)内阻法：以内阻作为电池组SOH的评价指标，对电池组SOH进行估计，但是电池组的内阻不能直接获得，需要建立电池组模型对电池组内阻进行参数辨识；所建立电池组模型的准确性和模型参数辨识精度都极大影响着电池组的SOH。(2) Internal resistance method: The internal resistance is used as the evaluation index of the SOH of the battery pack to estimate the SOH of the battery pack, but the internal resistance of the battery pack cannot be obtained directly, and a battery pack model needs to be established to identify the parameters of the battery pack internal resistance; The accuracy of the battery pack model and the accuracy of model parameter identification greatly affect the SOH of the battery pack.
(3)容量增量方法：通过从IC曲线中选取特征变量，将特征作为输入数据集，构建SOH估计模型对电池组SOH进行估计。由于ICA(Incremental Capacity Analysis)通常需要恒定的充放电数据，所以此方法大多运用于实验室的电池组SOH估计。(3) Capacity increment method: By selecting characteristic variables from the IC curve and taking the characteristic as the input data set, the SOH estimation model is constructed to estimate the SOH of the battery pack. Since ICA (Incremental Capacity Analysis) usually requires constant charge and discharge data, this method is mostly used in laboratory SOH estimation of battery packs.
上述估算方法需要在实验室完成，在电动汽车实际行驶过程中，驾驶条件、天气以及驾驶员的驾驶行为对电池组SOH都有一定的影响，这些影响是不可能通过实验模拟得到的，导致无法估算电池组SOH。The above estimation method needs to be completed in the laboratory. In the actual driving process of electric vehicles, driving conditions, weather and driver's driving behavior have certain influences on the SOH of the battery pack. These influences cannot be obtained through experimental simulation, resulting in inability to Estimate battery pack SOH.
发明内容SUMMARY OF THE INVENTION
针对现有技术中存在不足，本发明提供了一种基于LSTM神经网络的电池组SOH估算方法，解决基于实验室验证的估算方法难以适应复杂的实际工作环境的问题。In view of the deficiencies in the prior art, the present invention provides a battery pack SOH estimation method based on LSTM neural network, which solves the problem that the estimation method based on laboratory verification is difficult to adapt to the complex actual working environment.
本发明是通过以下技术手段实现上述技术目的的。The present invention achieves the above technical purpose through the following technical means.
一种基于LSTM神经网络的电池组SOH估算方法，包括步骤：A battery pack SOH estimation method based on LSTM neural network, including steps:
步骤(1)，采集实际运行一年以上的电动汽车的电池组充电数据，进行相关性分析，提取LSTM神经网络的输入特征；Step (1), collect the battery pack charging data of the electric vehicle that has actually been running for more than one year, carry out correlation analysis, and extract the input features of the LSTM neural network;
步骤(2)，利用SOC-电量增益法计算电池组最大可用容量，作为LSTM神经网络的输出特征；Step (2), using the SOC-electricity gain method to calculate the maximum available capacity of the battery pack as the output feature of the LSTM neural network;
步骤(3)，构建LSTM神经网络模型，确定LSTM神经网络输出值；Step (3), construct the LSTM neural network model, and determine the output value of the LSTM neural network;
由遗忘门sigmoid层对t-1时刻记忆单元中的部分信息进行遗忘，再对t时刻记忆单元中的信息进行更新，由输出门确定LSTM神经网络输出值；Part of the information in the memory unit at time t-1 is forgotten by the forget gate sigmoid layer, and then the information in the memory unit at time t is updated, and the output gate determines the output value of the LSTM neural network;
步骤(4)，利用训练并验证后的LSTM神经网络模型估算电池组SOH。Step (4), using the trained and verified LSTM neural network model to estimate the SOH of the battery pack.
进一步的技术方案，所述输入特征包括充电时电池组的电流、电压、温度和SOC。In a further technical solution, the input characteristics include current, voltage, temperature and SOC of the battery pack during charging.
进一步的技术方案，所述电池组最大可用容量的计算公式为：In a further technical solution, the formula for calculating the maximum available capacity of the battery pack is:
其中，Cnorm为电池组最大可用容量，ΔQ为电池组电量变化量，ΔSOC为电池组SOC变化量，SOC(t0)为放电起始时刻电池荷电状态，SOC(tend)为放电结束时刻电池荷电状态，I(t)为t时刻电池电流，η为库伦效率。Among them, Cnorm is the maximum available capacity of the battery pack, ΔQ is the amount of change in the battery pack power, ΔSOC is the amount of change in the battery pack SOC, SOC(t0 ) is the state of charge of the battery at the start of discharge, and SOC(tend ) is the end of discharge The state of charge of the battery at time, I(t) is the battery current at time t, and η is the Coulomb efficiency.
进一步的技术方案，所述遗忘门sigmoid层对t-1时刻记忆单元中的部分信息进行遗忘，公式为：In a further technical solution, the forgetting gate sigmoid layer forgets part of the information in the memory unit at time t-1, and the formula is:
ft＝σ(Wfx·xt+Wfh·ht-1+bf)ft =σ(Wfx ·xt +Wfh ·ht-1 +bf )
其中，ft为遗忘门的输出向量，σ为sigmoid函数，
更进一步的技术方案，所述对t时刻记忆单元中的信息进行更新，公式为：In a further technical solution, the information in the memory unit at time t is updated, and the formula is:
Ct＝ftCt-1+it tanh(Wzxxt+Wzhht-1+bz)Ct =ft Ct-1 +it tanh(Wzx xt +Wzh ht-1 +bz )
其中，it为输入门的输出向量，且it＝σ(Wix·xt+Wih·ht-1+bi)，Ct-1和Ct分别为t-1时刻和t时刻的记忆单元状态，
更进一步的技术方案，所述由输出门确定LSTM神经网络输出值，公式为：A further technical solution, the output value of the LSTM neural network is determined by the output gate, and the formula is:
ht＝Ottanh(ct)ht =Ot tanh(ct )
其中，Ot为输出门的输出向量，且Ot＝σ(Woxxt+Wohht-1+bo)，
进一步的技术方案，所述LSTM神经网络模型训练时利用输入特征和输出特征进行。In a further technical solution, the LSTM neural network model is trained using input features and output features.
进一步的技术方案，所述估算电池组SOH采用的公式为：In a further technical solution, the formula used for estimating the SOH of the battery pack is:
其中Clstm为LSTM神经网络预测的电池组容量，C0为电池组初始容量。where Clstm is the capacity of the battery pack predicted by the LSTM neural network, and C0 is the initial capacity of the battery pack.
本发明的有益效果为：The beneficial effects of the present invention are:
(1)本发明采用LSTM神经网络估算电池组SOH，LSTM神经网络的输入特征和输出特征均由实际运行一年以上的电动汽车的电池组充电数据获取，使得本发明的估算方法适用于电动汽车全状态、全气候运行时的电池组SOH，而不受运行环境的限制，克服了基于实验室验证的估算方法难以适应复杂的实际工作环境的问题。(1) The present invention uses the LSTM neural network to estimate the SOH of the battery pack, and the input features and output features of the LSTM neural network are obtained from the battery pack charging data of an electric vehicle that has actually operated for more than one year, so that the estimation method of the present invention is suitable for electric vehicles. The SOH of the battery pack during all-state, all-climate operation is not limited by the operating environment, which overcomes the problem that the estimation method based on laboratory verification is difficult to adapt to the complex actual working environment.
(2)本发明LSTM神经网络模型既对t-1时刻记忆单元中的部分信息进行遗忘，又对t时刻记忆单元中的信息进行更新，LSTM神经网络模型可以根据随时积累的数据进行改进，使得基于LSTM神经网络估算电池组SOH的方法，具有更强的时效性和适用性。(2) The LSTM neural network model of the present invention not only forgets part of the information in the memory unit at time t-1, but also updates the information in the memory unit at time t. The LSTM neural network model can be improved according to the data accumulated at any time, so that The method of estimating the SOH of the battery pack based on the LSTM neural network has stronger timeliness and applicability.
附图说明Description of drawings
图1为本发明所述LSTM神经网络模型示意图。FIG. 1 is a schematic diagram of the LSTM neural network model according to the present invention.
具体实施方式Detailed ways
下面结合附图以及具体实施例对本发明作进一步的说明，但本发明的保护范围并不限于此。The present invention will be further described below with reference to the accompanying drawings and specific embodiments, but the protection scope of the present invention is not limited thereto.
一种基于LSTM神经网络的电池组SOH估算方法，具体包括如下步骤：A battery pack SOH estimation method based on LSTM neural network, which specifically includes the following steps:
S1，对实际运行一年以上(包含春、夏、秋、冬四季)的电动汽车的电池组充电数据进行采集，对采集的数据进行相关性分析，提取LSTM神经网络的输入特征，包括充电时电池组的电流、电压、温度和SOC(剩余电量)。S1: Collect the battery pack charging data of the electric vehicle that has actually run for more than one year (including spring, summer, autumn, and winter), perform correlation analysis on the collected data, and extract the input features of the LSTM neural network, including the charging time. Current, voltage, temperature and SOC (remaining charge) of the battery pack.
S2，通过SOC-电量增益法计算当前电池组的最大可用容量S2, calculate the maximum available capacity of the current battery pack through the SOC-charge gain method
由于电动汽车电池组充电数据采样每隔20s进行一次，不能获得20s内所有的电流数据，因此采用离散化的SOC-电量增益法计算电池组最大可用容量，并以此作为LSTM神经网络的输出特征；公式如下：Since the charging data sampling of the battery pack of the electric vehicle is performed every 20s, all the current data within 20s cannot be obtained. Therefore, the discretized SOC-electricity gain method is used to calculate the maximum available capacity of the battery pack, and use this as the output feature of the LSTM neural network. ; the formula is as follows:
式中，Cnorm为电池组最大可用容量，ΔQ为电池组电量变化量，ΔSOC为电池组SOC变化量，SOC(t0)为放电起始时刻电池荷电状态，SOC(tend)为放电结束时刻电池荷电状态，I(t)为t时刻电池电流，η为库伦效率(一般情况η≈1)。In the formula, Cnorm is the maximum available capacity of the battery pack, ΔQ is the amount of change in the battery pack power, ΔSOC is the amount of change in the SOC of the battery pack, SOC(t0 ) is the state of charge of the battery at the beginning of discharge, and SOC(tend ) is the discharge The state of charge of the battery at the end time, I(t) is the battery current at time t, and η is the Coulomb efficiency (in general, η≈1).
S3，构建LSTM神经网络模型，确定LSTM神经网络输出值S3, construct the LSTM neural network model, and determine the output value of the LSTM neural network
如图1所示，LSTM神经网络模型包括输入门、遗忘门和输出门，给定当前时刻的单元输入是xt，上一时刻的隐藏状态是ht-1，上一时刻记忆单元状态是Ct-1。首先由遗忘门sigmoid层完成对上一时刻记忆单元Ct-1中的部分信息遗忘，接着和输入门sigmoid层、候选门tanh层一起完成对当前时刻记忆单元Ct的状态更新，最后由输出门sigmoid层和当前时刻记忆单元Ct完成对LSTM神经网络上一时刻输出值的更新，即确定当前时刻的输出状态ht。As shown in Figure 1, the LSTM neural network model includes an input gate, a forgetting gate and an output gate. Given that the unit input at the current moment is xt , the hidden state at the last moment is ht-1 , and the memory unit state at the last moment is Ct-1 . First, the forgetting gate sigmoid layer completes the forgetting of part of the information in the memory unit Ct-1 at the previous moment, and then completes the state update of the memory unit Ct at the current moment together with the input gate sigmoid layer and the candidate gate tanh layer. The gate sigmoid layer and the memory unit Ct at the current moment complete the update of the output value of the LSTM neural network at the previous moment, that is, determine the output state ht at the current moment.
S31，首先由遗忘门sigmoid层对t-1时刻记忆单元中的部分信息进行遗忘，公式如下：S31, firstly, the forgetting gate sigmoid layer forgets part of the information in the memory unit at time t-1, the formula is as follows:
ft＝σ(Wfx·xt+Wfh·ht-1+bf)ft =σ(Wfx ·xt +Wfh ·ht-1 +bf )
式中，ft为遗忘门的输出向量，σ为sigmoid函数，
S32，对t时刻记忆单元中的信息进行更新，公式如下：S32, update the information in the memory unit at time t, the formula is as follows:
it＝σ(Wix·xt+Wih·ht-1+bi)it =σ(Wix ·xt +Wih ·ht-1 +bi )
Ct＝ftCt-1+it tanh(Wzxxt+Wzhht-1+bz)Ct =ft Ct-1 +it tanh(Wzx xt +Wzh ht-1 +bz )
式中，it为输入门的输出向量，tanh为tanh函数，Ct-1和Ct分别为t-1时刻和t时刻的记忆单元状态，
S33，由输出门确定LSTM神经网络输出值，公式如下：S33, the output value of the LSTM neural network is determined by the output gate, and the formula is as follows:
Ot＝σ(Woxxt+Wohht-1+bo)Ot =σ(Wox xt +Woh ht-1 +bo )
ht＝Ottanh(ct)ht =Ot tanh(ct )
式中，Ot为输出门的输出向量，
S4，基于LSTM神经网络模型，进行电池组SOH估计S4, based on the LSTM neural network model, the battery pack SOH estimation
S41，训练LSTM神经网络模型S41, train the LSTM neural network model
以某一地区的某辆电动汽车数据集(厂家提供的一年以上的数据)，进行LSTM神经网络模型训练，LSTM算法是有监督学习的机器学习算法，以电压、电流、温度、SOC作为输入特征，SOC-电量增益法计算得出的电池组最大可用容量为输出特征，对LSTM神经网络模型进行训练。Use a data set of an electric vehicle in a certain area (data provided by the manufacturer for more than one year) to train the LSTM neural network model. The LSTM algorithm is a supervised learning machine learning algorithm, which uses voltage, current, temperature, and SOC as input. The maximum available capacity of the battery pack calculated by the SOC-electricity gain method is the output feature, and the LSTM neural network model is trained.
S42，以同一地区的四辆电动汽车数据集(厂家提供的一年以上的数据)进行测试，以电池组容量预测值(LSTM神经网络模型输出值)和真实值(即电池组最大可用容量)的RMSE(均方根误差，衡量电池组整个寿命周期内电池容量预测值与真实值的偏差)作为评价指标，表1为四辆电动汽车的均方根误差的数值，由表1可以看出除第三辆车的RMSE略大于1，其余车辆的RMSE均小于1，可见LSTM神经网络模型是有效的。S42, test with the data set of four electric vehicles in the same area (data provided by the manufacturer for more than one year), with the predicted value of the battery pack capacity (the output value of the LSTM neural network model) and the real value (that is, the maximum available capacity of the battery pack) The RMSE (root mean square error, which measures the deviation between the predicted value of the battery capacity and the actual value during the entire life cycle of the battery pack) is used as the evaluation index. Table 1 shows the value of the root mean square error of the four electric vehicles. Except the RMSE of the third vehicle is slightly greater than 1, the RMSE of the rest of the vehicles is less than 1, which shows that the LSTM neural network model is effective.
表1四辆电动汽车的预测误差Table 1 Prediction errors of four electric vehicles
S43，利用LSTM神经网络模型估算电池组SOH，采用下述公式：S43, use the LSTM neural network model to estimate the SOH of the battery pack, using the following formula:
其中，Clstm为LSTM神经网络预测的电池组容量，C0为电池组初始容量(厂家提供)。Among them, Clstm is the capacity of the battery pack predicted by the LSTM neural network, and C0 is the initial capacity of the battery pack (provided by the manufacturer).
所述实施例为本发明的优选的实施方式，但本发明并不限于上述实施方式，在不背离本发明的实质内容的情况下，本领域技术人员能够做出的任何显而易见的改进、替换或变型均属于本发明的保护范围。The embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above-mentioned embodiments, and any obvious improvement, replacement or Modifications all belong to the protection scope of the present invention.
Claims (8)
Translated fromChinese
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010678378.2ACN111983457A (en) | 2020-07-15 | 2020-07-15 | A battery pack SOH estimation method based on LSTM neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010678378.2ACN111983457A (en) | 2020-07-15 | 2020-07-15 | A battery pack SOH estimation method based on LSTM neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111983457Atrue CN111983457A (en) | 2020-11-24 |
Family
ID=73437876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010678378.2APendingCN111983457A (en) | 2020-07-15 | 2020-07-15 | A battery pack SOH estimation method based on LSTM neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111983457A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112763929A (en)* | 2020-12-31 | 2021-05-07 | 华东理工大学 | Method and device for predicting health of battery monomer of energy storage power station system |
| CN113064093A (en)* | 2021-03-22 | 2021-07-02 | 山东建筑大学 | Energy storage battery state of charge and state of health joint estimation method and system |
| CN113128672A (en)* | 2021-04-16 | 2021-07-16 | 昆明理工大学 | Lithium ion battery pack SOH estimation method based on transfer learning algorithm |
| CN113219358A (en)* | 2021-04-29 | 2021-08-06 | 东软睿驰汽车技术（沈阳）有限公司 | Battery pack health state calculation method and system and electronic equipment |
| CN113740735A (en)* | 2021-08-30 | 2021-12-03 | 昆明理工大学 | Method for estimating SOC of lithium ion battery |
| CN113917337A (en)* | 2021-10-13 | 2022-01-11 | 国网福建省电力有限公司 | Battery state of health estimation method based on charging data and LSTM neural network |
| CN114167301A (en)* | 2021-11-30 | 2022-03-11 | 同济大学 | Power battery evaluation method based on real vehicle data of electric vehicle |
| CN114492182A (en)* | 2022-01-18 | 2022-05-13 | 江苏大学 | Method for predicting cycle life of battery pack in any topological structure |
| CN114580262A (en)* | 2021-11-18 | 2022-06-03 | 吉林大学 | Lithium ion battery health state estimation method |
| CN114791993A (en)* | 2022-05-16 | 2022-07-26 | 江苏大学 | A kind of power battery pack SOH prediction method and system |
| CN114994546A (en)* | 2022-06-15 | 2022-09-02 | 江苏大学 | Battery pack SOH prediction system and method based on block chain and Informer neural network |
| CN115366101A (en)* | 2022-08-22 | 2022-11-22 | 桂林电子科技大学 | CNN-LSTM-based robot pneumatic clamping force modeling estimation method |
| CN120142957A (en)* | 2025-05-15 | 2025-06-13 | 国网山西省电力公司长治供电公司 | Combined prediction method of battery SOH and SOC based on neural network |
| CN120195575A (en)* | 2025-05-26 | 2025-06-24 | 华东交通大学 | Battery health status assessment method, system, storage medium and computer |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150066406A1 (en)* | 2013-08-27 | 2015-03-05 | The Regents Of The University Of Michigan | On-board state of health monitoring of batteries using incremental capacity analysis |
| CN110598300A (en)* | 2019-09-05 | 2019-12-20 | 东软睿驰汽车技术（沈阳）有限公司 | Battery SOH prediction method and device |
| CN110824364A (en)* | 2019-10-24 | 2020-02-21 | 重庆邮电大学 | Lithium battery SOH estimation and RUL prediction method based on AST-LSTM neural network |
| US20200081070A1 (en)* | 2017-11-20 | 2020-03-12 | The Trustees Of Columbia University In The City Of New York | Neural-network state-of-charge and state of health estimation |
| CN111308375A (en)* | 2020-02-04 | 2020-06-19 | 浙江大学 | LSTM-FFNN-based electric forklift lithium ion battery health state prediction method |
- 2020
- 2020-07-15CNCN202010678378.2Apatent/CN111983457A/enactivePending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150066406A1 (en)* | 2013-08-27 | 2015-03-05 | The Regents Of The University Of Michigan | On-board state of health monitoring of batteries using incremental capacity analysis |
| US20200081070A1 (en)* | 2017-11-20 | 2020-03-12 | The Trustees Of Columbia University In The City Of New York | Neural-network state-of-charge and state of health estimation |
| CN110598300A (en)* | 2019-09-05 | 2019-12-20 | 东软睿驰汽车技术（沈阳）有限公司 | Battery SOH prediction method and device |
| CN110824364A (en)* | 2019-10-24 | 2020-02-21 | 重庆邮电大学 | Lithium battery SOH estimation and RUL prediction method based on AST-LSTM neural network |
| CN111308375A (en)* | 2020-02-04 | 2020-06-19 | 浙江大学 | LSTM-FFNN-based electric forklift lithium ion battery health state prediction method |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112763929A (en)* | 2020-12-31 | 2021-05-07 | 华东理工大学 | Method and device for predicting health of battery monomer of energy storage power station system |
| CN112763929B (en)* | 2020-12-31 | 2024-03-08 | 华东理工大学 | Method and device for predicting health of battery monomer of energy storage power station system |
| CN113064093B (en)* | 2021-03-22 | 2024-03-08 | 百思科新能源技术(青岛)有限公司 | Method and system for jointly estimating state of charge and state of health of energy storage battery |
| CN113064093A (en)* | 2021-03-22 | 2021-07-02 | 山东建筑大学 | Energy storage battery state of charge and state of health joint estimation method and system |
| CN113128672A (en)* | 2021-04-16 | 2021-07-16 | 昆明理工大学 | Lithium ion battery pack SOH estimation method based on transfer learning algorithm |
| CN113219358A (en)* | 2021-04-29 | 2021-08-06 | 东软睿驰汽车技术（沈阳）有限公司 | Battery pack health state calculation method and system and electronic equipment |
| CN113740735A (en)* | 2021-08-30 | 2021-12-03 | 昆明理工大学 | Method for estimating SOC of lithium ion battery |
| CN113917337A (en)* | 2021-10-13 | 2022-01-11 | 国网福建省电力有限公司 | Battery state of health estimation method based on charging data and LSTM neural network |
| CN114580262A (en)* | 2021-11-18 | 2022-06-03 | 吉林大学 | Lithium ion battery health state estimation method |
| CN114580262B (en)* | 2021-11-18 | 2024-07-12 | 吉林大学 | Lithium ion battery health state estimation method |
| CN114167301A (en)* | 2021-11-30 | 2022-03-11 | 同济大学 | Power battery evaluation method based on real vehicle data of electric vehicle |
| CN114492182A (en)* | 2022-01-18 | 2022-05-13 | 江苏大学 | Method for predicting cycle life of battery pack in any topological structure |
| CN114791993A (en)* | 2022-05-16 | 2022-07-26 | 江苏大学 | A kind of power battery pack SOH prediction method and system |
| CN114994546A (en)* | 2022-06-15 | 2022-09-02 | 江苏大学 | Battery pack SOH prediction system and method based on block chain and Informer neural network |
| CN115366101A (en)* | 2022-08-22 | 2022-11-22 | 桂林电子科技大学 | CNN-LSTM-based robot pneumatic clamping force modeling estimation method |
| CN120142957A (en)* | 2025-05-15 | 2025-06-13 | 国网山西省电力公司长治供电公司 | Combined prediction method of battery SOH and SOC based on neural network |
| CN120195575A (en)* | 2025-05-26 | 2025-06-24 | 华东交通大学 | Battery health status assessment method, system, storage medium and computer |
| CN120195575B (en)* | 2025-05-26 | 2025-09-12 | 华东交通大学 | Battery health state evaluation method, system, storage medium and computer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111983457A (en) | A battery pack SOH estimation method based on LSTM neural network | |
| Lin et al. | State of charge estimation with the adaptive unscented Kalman filter based on an accurate equivalent circuit model | |
| Li et al. | Data driven battery modeling and management method with aging phenomenon considered | |
| US11965935B2 (en) | Method and apparatus for operating a system for providing predicted states of health of electrical energy stores for a device using machine learning methods | |
| CN113419187B (en) | A Lithium-ion Battery Health Estimation Method | |
| US11366171B2 (en) | Battery state estimation method | |
| CN111581904B (en) | Lithium battery SOC and SOH collaborative estimation method considering cycle number influence | |
| CN107957562B (en) | An online prediction method for the remaining life of lithium-ion batteries | |
| CN103472398B (en) | Based on the electrokinetic cell SOC method of estimation of spreading kalman particle filter algorithm | |
| CN108519556A (en) | A Lithium-ion Battery SOC Prediction Method Based on Recurrent Neural Network | |
| US20220011370A1 (en) | Apparatus for mining battery characteristic data having sensitivity to solid phase diffusion coefficient of battery electrode and method thereof | |
| CN111948560A (en) | Lithium battery state of health estimation method based on multi-factor evaluation model | |
| CN113702843A (en) | Lithium battery parameter identification and SOC estimation method based on suburb optimization algorithm | |
| AU2021100373A4 (en) | A Battery Pack SOH Estimation Method Based on LSTM Neural Network | |
| CN113805075A (en) | BCRLS-UKF-based lithium battery state of charge estimation method | |
| CN112557907A (en) | SOC estimation method of electric vehicle lithium ion battery based on GRU-RNN | |
| CN113128672B (en) | Lithium ion battery pack SOH estimation method based on transfer learning algorithm | |
| CN115236521A (en) | State-of-Health Estimation Method for Li-ion Batteries Based on Semi-Supervised Co-training Framework | |
| Li et al. | Discharge capacity estimation for Li-ion batteries based on particle filter under multi-operating conditions | |
| CN115015760A (en) | Lithium battery state of health assessment method based on neural network and transfer ensemble learning | |
| CN106872899A (en) | A kind of electrokinetic cell SOC methods of estimation based on reduced dimension observer | |
| CN114487890A (en) | An improved long short-term memory neural network for lithium battery state of health estimation method | |
| CN117269805A (en) | Vehicle-mounted lithium battery pack health state evaluation model training and predicting method and device | |
| CN116804711A (en) | Method and apparatus for providing a predicted state of health of a device battery based on a predicted usage pattern | |
| CN113740735A (en) | Method for estimating SOC of lithium ion battery |
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 | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20201124 | |
| RJ01 | Rejection of invention patent application after publication |