Comparative Study of State-Of-Charge Estimation with Recurrent Neural Networks

Keyphrases

• Recurrent Neural Network 100%
• State of Charge Estimation 100%
• Electric Vehicle 50%
• Reliable Operation 50%
• Machine Learning 50%
• Kalman Filter 50%
• Model-based Approach 50%
• Ambient Temperature 50%
• Temperature Range 50%
• State of Charge 50%
• Modeling Effort 50%
• Operating Conditions 50%
• Safe Operation 50%
• Real-world Application 50%
• Energy Storage System 50%
• Equivalent Circuit Model 50%
• Extended Kalman Filtering 50%
• Lithium-ion Cell 50%
• Data-driven Approach 50%
• Implementation Time 50%
• Reduced Modeling 50%
• Battery Management System 50%
• Parallel Connection 50%
• Battery Module 50%
• Long-short Term Memory Cell 50%
• Recurrent Neural Network with Long Short-Term Memory 50%
• Battery Data 50%
• Single-cell Battery 50%

Engineering

• State of Charge 100%
• Recurrent Neural Network 100%
• Filtration 66%
• Extended Kalman 33%
• Equivalent Circuit Model 33%
• Reliable Operation 33%
• Lithium-Ion Cell 33%
• Energy Storage System 33%
• Battery Management System 33%
• Safe Operation 33%
• Real World Application 33%
• Temperature Range 33%
• Observables 33%
• Electric Vehicle 33%
• State Variable 33%
• Long Short-Term Memory 33%
• Learning System 33%

Chemical Engineering

• Recurrent Neural Network 100%
• Learning System 50%
• Long Short-Term Memory 50%