Lithium battery SOH estimation method based on multilevel sequence information adaptive fusion
A sequence information, multi-level technology, applied in the measurement of electricity, electric vehicles, measurement of electrical variables, etc., can solve problems such as poor model generalization, inability to extract serialized information, and inability to accurately estimate lithium battery SOH, etc., to improve prediction. The effect of precision
Pending Publication Date: 2022-08-02
HANGZHOU DIANZI UNIV
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Among them, the convolutional neural network (CNN) is widely used in lithium battery SOH online estimation due to its advantages in time series prediction, but its single serial network structure cannot extract rich serialized information, which leads to model generalization Poor performance, unable to accurately estimate lithium battery SOH
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] The present invention will be further explained below in conjunction with the accompanying drawings.
[0031] The experimental environment used in this example is: CPU Intel(R)Core(TM)i5-10600KF CPU@4.10Ghz, GPU is RTX 3070, graphics card memory is 8GB, Python version is 3.7, Cuda version is 11.1, the depth used is The learning framework is TensorFlow-GPU 2.3.0, and the data used is from the battery prediction dataset of the NASA Prediction Center of Excellence.
[0032] like figure 1 As shown in the figure, the online estimation method of lithium battery SOH based on adaptive fusion of multi-level sequence information includes the following steps:
[0033] Step 1. In order to determine the degradation trend of the battery health state of the lithium battery under different working conditions, in this embodiment, data sets such as B0005, B0006, B0018, and B0029 are selected as the training set, and B0005 is selected as the test set. The battery model used in this data...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a lithium battery SOH estimation method based on multilevel sequence information adaptive fusion. According to the invention, a brand new serialization model based on deep learning is established, and the model is established by two cascaded multi-level fusion modules and a bidirectional LSTM layer. Based on the advantage that the provided model can adaptively extract and fuse multi-level serialization information, the model can solve the problems that the battery data volume is too small and extraction is insufficient to a certain extent, so that relatively accurate lithium battery SOH online estimation is realized. In addition, the model also has the advantage of long-term memory, so that the online estimation precision is further improved. According to an experiment, battery degradation data in an NASA lithium ion data set is adopted to carry out simulation verification on the network model, and a result shows that the model can guarantee relatively high robustness and accuracy while completing a lithium battery SOH online estimation task.
Description
technical field [0001] The invention belongs to the technical field of battery management, relates to a lithium battery management system technology, and in particular relates to a lithium battery SOH estimation method based on self-adaptive fusion of multi-level sequence information. Background technique [0002] Lithium batteries are widely used in electric vehicles (EVs) due to their long lifespan, high capacity, and wide operating temperature range. In order to ensure the operation safety, reliability and durability of electric vehicles, it is very important to monitor the battery status of electric vehicles in a timely and accurate manner. However, long-term, frequent use of the battery will inevitably shorten its lifespan. In addition, improper charging and use can also accelerate battery aging and even cause safety problems. Therefore, accurate estimation of lithium battery state of health (SOH) has become a key element to ensure the safe operation of electric vehic...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G01R31/367G01R31/378G01R31/392
CPCG01R31/367G01R31/378G01R31/392Y02T10/70
Inventor 鲍政怡高明裕何志伟董哲康杨宇翔林辉品
Owner HANGZHOU DIANZI UNIV