A novel multistage Support Vector Machine based approach for Li ion battery remaining useful life estimation

By Meru A. Patil, Piyush Tagade, K. Hariharan, S. M. Kolake, T. Song, Tae-Jung Yeo, S. Doo. 2015

556 citations recorded by the source corpus.

Subfields: Automotive Engineering, Control and Systems Engineering, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/1178fdb9a6bee589c3c538e96633d89cf684ca1e

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. David A. Howey
2. Jingwen Wei
3. Michael A. Osborne
4. Lei Ren
5. Zonghai Chen
6. Li Zhao
7. Robert R. Richardson
8. Guangzhong Dong

In Control and Systems Engineering

1. Jingwen Wei
2. Michael A. Osborne
3. Lei Ren
4. Noureddine Zerhouni
5. Zonghai Chen
6. David A. Howey
7. Li Zhao
8. Robert R. Richardson

In Electrical and Electronic Engineering

1. David A. Howey
2. Jingwen Wei
3. Michael A. Osborne
4. Noureddine Zerhouni
5. Zonghai Chen
6. Robert R. Richardson
7. Guangzhong Dong
8. Widanalage Dhammika Widanage

Citations in the corpus

• Remaining Useful Life Prediction and State of Health Diagnosis for Lithium-Ion Batteries Using Particle Filter and Support Vector Regression (2018, background): “In order to establish the state transition model to describe system dynamic characteristics, the data-driven algorithms including ANN, SVM, and Gaussian process regression (GPR), etc., have been utilized.”
• Long Short-Term Memory Recurrent Neural Network for Remaining Useful Life Prediction of Lithium-Ion Batteries (2018, unknown): “[15] proposed a multistage SVM approach for RUL prediction of lithium-ion batteries.”
• Gaussian process regression for forecasting battery state of health (2017, background): “For instance, a number of recent studies have used Support Vector Machines (SVMs) for predicting future cell capacity based on it’s historical capacity vs. cycle data and/or from data from multiple identical cells [11, 12, 13, 14].”
• Remaining Useful Life Prediction for Lithium-Ion Battery: A Deep Learning Approach (2018, methodology): “[13] proposed a real-time RUL estimation method for lithium-ion battery based on the classification and regression properties of machine learning techniques based on Support Vector Machine (SVM).”
• LSTM-Based Battery Remaining Useful Life Prediction With Multi-Channel Charging Profiles (2020, methodology): “Specifically, data-driven methods rely solely on historical capacity degradation data rather than requiring explicit mathematical models of battery degradation or internal mechanisms of the battery [10]–[12].”
• Direct Remaining Useful Life Estimation Based on Support Vector Regression (2017, methodology): “In [24], the RUL estimation is made only for the state near the EOL and is defined as a percentage of EOL values.”