Advances in Battery Manufacturing and Operating Status Analysis

Filtering and Artificial Intelligence Strategy
1. Auflage 2026
ISBN: 978-1-394-43716-0
Verlag: John Wiley & Sons Inc

Buch, Englisch, 240 Seiten

Advanced filtering and AI algorithms for battery system analysis

Advances in Battery Manufacturing and Operating Status Analysis details zonotopic and particle filtering methods for robust real-time estimation of critical battery parameters, alongside hybrid models combining filters with long short-term memory networks for remaining useful life prediction. Coverage of genetic algorithms and Q-learning addresses intelligent battery grouping and manufacturing capacity forecasting. Technical case studies walk through problem definitions, data preprocessing, model selection, implementation, and interpretation of results.

Key topics also include: - Zonotopic and particle filtering approaches for achieving robust, real-time estimation of critical battery state parameters in operational environments
- Hybrid filter and long short-term memory network models designed to predict remaining useful life with improved accuracy
- Genetic algorithm and Q-learning strategies applied to intelligent battery grouping and manufacturing capacity forecasting
- Technical case studies covering problem definitions, data preprocessing, model selection, implementation, and real-world result interpretation
- Data-driven strategies for optimizing battery lifecycle stages from manufacturing through operation and sustainable energy storage

Researchers and industry professionals in energy storage, power electronics, and electrical engineering R&D will find targeted algorithmic strategies for battery system management. Graduate students studying energy storage and related disciplines gain exposure to filtering and AI methods applied directly to manufacturing and operational analysis challenges.

Autoren/Hrsg.

Wang, Ziyun

Wang, Yan

Ji, Zhicheng

Fachgebiete

• Technische Wissenschaften Energietechnik | Elektrotechnik Energieumwandlung, Energiespeicherung
• Technische Wissenschaften Verfahrenstechnik | Chemieingenieurwesen | Biotechnologie Verfahrenstechnik, Chemieingenieurwesen
• Technische Wissenschaften Elektronik | Nachrichtentechnik Nachrichten- und Kommunikationstechnik Regelungstechnik

Inhaltsverzeichnis

Introduction 1

1.1 Research background and significance 1
1.2 Battery manufacturing 2
1.3 Battery operating status analysis 4
1.4 Principle of filter design methods 6
1.5 Artificial intelligence strategy 8
1.6 Outlines 9

2 Advances in battery grouping by artificial intelligence strategy 11
2.1 Introduction to battery grouping 11
2.2 Problem formulation and model establishment 12
2.3 Chromosome encoding 13
2.4 Crossover modes designing 13
2.5 Population mutations 14
2.6 Convergence analysis 16
2.7 Case study on battery grouping 18
2.8 Concluding remarks 20

3 Advances in forecasting of battery manufacturing capacity by artificial intelligence strategy 21
3.1 Introduction to battery manufacturing capacity 21
3.2 Problem formulation 24
3.3 Q-learning principle 24
3.4 Variational mode decomposition 27
3.5 Long short-term memory 29
3.6 Design of the forecasting method 30
3.7 Case study on forecasting of battery manufacturing capacity 34
3.8 Concluding remarks 39

4 Advances in battery operating status analysis by zonotopic filtering 41
4.1 Introduction to battery operating status analysis 41
4.2 Problem formulation 43
4.3 Zonotopic filter 47
4.4 Zonotope and Gaussian Kalman filters 53
4.5 Orthotope-search-expansion-based extended zonotopic Kalman filter 61
4.6 Constrained zonotopic Kalman filtering 73
4.7 Case study on battery operating status analysis 79
4.8 Concluding remarks 92

5 Advances in battery operating status analysis by filtering and artificial intelligence 93
5.1 Problem formulation 93
5.2 Introduction to particle filter and particle swarm optimization 95
5.3 Particle swarm optimization based orthometric hyperparallel space filtering 98
5.4 Improved particle filter algorithm based on the parallelotope 107
5.5 Projected particle-confinement-based zonotopic space filtering 119
5.6 Zonotopic feasible set optimized filter based on differential evolution 130
5.7 Case study on battery operating status analysis 136
5.8 Concluding remarks 151

6 Advances in battery remaining useful life analysis by filtering and artificial intelligence 153
6.1 Introduction to battery remaining useful life analysis 153
6.2 Dynamic complexity reduction zonotopic Kalman filter 156
6.3 Double exponential empirical particle filter 163
6.4 Anti-aliasing filter and LSTM 169
6.5 Case study on battery remaining useful life analysis 173
6.6 Concluding remarks 186

7 Summary and future outlook 189
7.1 Summary 189
7.2 Future outlook 191

References 195

Über Autor(innen)

Ziyun Wang is a Professor and Doctoral Supervisor at Jiangnan University's School of Automation and Intelligent Science and Deputy Director of the Engineering Center for the Application of Internet of Things Technology. His research is focused on advanced manufacturing, battery operation analysis, and filter design.

Yan Wang is a Professor and Doctoral Supervisor at Jiangnan University's School of Automation and Intelligent Science and Yangtze River Distinguished Professor of the Ministry of Education. Her research spans artificial intelligence, advanced control and system optimization, and industrial internet technology.

Zhicheng Ji is a Professor and Doctoral Supervisor at Jiangnan University's School of Automation and Intelligent Science, and Director of Jiangsu Engineering Research Center for Intelligent Optimization Manufacturing of Industrial Internet, and former Vice Chancellor of Jiangnan University. His research is focused on energy system design, state estimation, and fault diagnosis.