Remaining Useful Life Prediction for Lithium-Ion Battery: A Deep Learning Approach

By Lei Ren, Li Zhao, Sheng Hong, Shiqiang Zhao, Hao Wang, Lin Zhang. IEEE Access, 2018

343 citations recorded by the source corpus.

Accurate prediction of remaining useful life (RUL) of lithium-ion battery plays an increasingly crucial role in the intelligent battery health management systems. The advances in deep learning introduce new data-driven approaches to this problem. This paper proposes an integrated deep learning approach for RUL prediction of lithium-ion battery by integrating autoencoder with deep neural network (DNN). First, we present a multi-dimensional feature extraction method with autoencoder model to represent battery health degradation. Then, the RUL prediction model-based DNN is trained for multi-battery remaining cycle life estimation. The proposed approach is applied to the real data set of lithium-ion battery cycle life from NASA, and the experiment results show that the proposed approach can improve the accuracy of RUL prediction.

Subfields: Automotive Engineering, Electrical and Electronic Engineering, Safety, Risk, Reliability and Quality

View Paper: https://www.semanticscholar.org/paper/1b42b3cedee8104a0fcb07894691717bc6920df2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

1. Xiaosong Hu
2. David A. Howey
3. Xianke Lin
4. Weihan Li
5. Simona Onori
6. Philipp Dechent
7. N. Sengupta
8. Anuradha M. Annaswamy

In Electrical and Electronic Engineering

1. David A. Howey
2. Xiaosong Hu
3. Xianke Lin
4. Weihan Li
5. Philipp Dechent
6. Simona Onori
7. N. Sengupta
8. Anuradha M. Annaswamy

In Safety, Risk, Reliability and Quality

1. Xiaosong Hu
2. Yunhong Che
3. Simona Onori
4. David A. Howey
5. Xianke Lin

Citations in the corpus

• A Data-Driven Auto-CNN-LSTM Prediction Model for Lithium-Ion Battery Remaining Useful Life (2021, background): “In order to evaluate the performance of our model, we have compared experimental results with the other two methods [27], [28] using the same training and testing sets.”
• Online capacity estimation of lithium-ion batteries with deep long short-term memory networks (2021, methodology): “Approaches based on deep neural networks (DNN) [29,39] employ autoencoders to extract the high-level features from raw charging curve data and pass them to a DNN to obtain the SOH as output.”
• Battery Health Prediction Using Fusion-Based Feature Selection and Machine Learning (2020, methodology): “The toolbox used for ANN is the Neural Net Fitting app in MATLAB; the toolbox used for is libsvm-3.”
• LSTM-Based Battery Remaining Useful Life Prediction With Multi-Channel Charging Profiles (2020, background): “Since acquiring battery charging and discharging data is an expensive process both in terms of time and cost, the NASA datasets of battery charging and discharging are commonly used as a common reference [7], [27]–[29].”
• A Neural-Network-Based Method for RUL Prediction and SOH Monitoring of Lithium-Ion Battery (2019, methodology): “proposed a lithium-ion battery RUL prediction method which combined autoencoder with deep neural network [26].”