Congratulations | CEGN’s University-Industry-Research Collaboration Achieves Significant Results, EI Journal Publishes Scientific Research Achievement

Recently, CEGN’s CEGN's collaborative research with Hunan University of Engineering resulted in the publication of a significant paper titled A Predictive Approach for Lithium-Ion Battery SOH using LSTM Neural Networks Enhanced by Health Matrix Optimization?in the EI-indexed Distributed Generation & Alternative Energy Journal. Prior to this, the patent application for the “Method, Device, Equipment, and Storage Medium for Predicting the Health State of Lithium Batteries” was also approved. This series of achievements highlights CEGN’s progress in core energy storage technologies and fundamental research, while also serving as a testament to the success of the collaboration between industry and academia.

With the continued expansion of renewable energy utilization and the increasing adoption of electric vehicles, efficient and reliable battery management systems (BMS) have become key technologies to ensure battery safety, improve efficiency, and extend battery life. Lithium-ion batteries, known for their superior energy density and long lifespan, are widely used in electric vehicles and energy storage systems. However, lithium-ion battery performance deteriorates over time, which directly impacts their safety, reliability, and cost-effectiveness. Therefore, improving the intelligence of battery management systems and accurately predicting the health status of batteries is crucial.

In this context, a team consisting of Youyuan Peng, Feng Huang, Xin Xie, Guocai Gui, Fei Zhao, Yuliu Ou, and Hai Xu conducted in-depth research and innovatively introduced the LSTM neural network-based SOH prediction method enhanced by health matrix optimization. This method effectively balances prediction accuracy and speed. Its applications are broad, covering multiple modules within the BMS, including real-time health monitoring, early warning systems, charging control, performance optimization, and fault diagnosis. The method allows BMS to dynamically adjust operating parameters based on real-time data, identify potential faults in advance, and develop scientifically sound charging plans. Additionally, it supports data analysis and long-term trend evaluation, providing reliable insights for charging and discharging strategies, effectively extending battery life and reducing maintenance costs.

It is worth noting that as early as 2023, CEGN’s Chairman Guocai Gui was appointed as a graduate mentor at Hunan University of Engineering, and Professor Feng Huang from the university was also appointed as a consultant to CEGN’s Energy Storage Institute. Through deep collaboration, both parties have not only facilitated the exchange of knowledge and technology but have also contributed significantly to cultivating professionals in the field of new energy.

By combining the theoretical research strengths of universities with the practical experience of CEGN, the transformation of scientific research from the laboratory to real-world applications has been accelerated. Moving forward, CEGN will continue to deepen and expand university-industry-research collaboration, producing even more fruitful results and making a positive contribution to industry progress and sustainable social development.

Contact us to explore collaboration opportunities in the new energy market.

www.cegnen.com, [email protected], 0086 755-8697 6699, Ext. 1