Data and code

• Battery aging dataset: We generated the largest known dataset of its kind from 215 commercial lithium-ion batteries of the same type controlled individually at the same operating conditions until >25% capacity fade.  All the data and associated code are shared [here], and a detailed description of the experiment is given in the [article].

• A Python tutorial about Physics-Informed Neural Networks (PINN) and Model-Integrated Neural Networks (MINN) is given at [Link].

Updates

Nov. 2023: 

• Excited to know that our Swedish Research Council (VR) project grant application has been approved. VR is Sweden's largest governmental research funding body and supports research of the highest quality in all scientific fields. Very proud!

• Our paper "Detecting abnormality of battery lifetime from first-cycle data using few-shot learning" has been accepted by Advanced Science, a high-impact, interdisciplinary science journal. We also share the largest known dataset for battery lifetime-abnormality detection. The paper will appear soon. All data and code are shared here.

• We have another guest, PhD student Wendi Guo from Aalborg University. Welcome! 

Sep. 2023: 

• We have a guest researcher Dr. Xin Sui from the Smart Battery Center at Aalborg University. Welcome! 

• We visited CEVT and Polestar. Thanks for your warm hospitality and interesting introduction, Yizhou and Lee! Indeed, we should visit our industrial collaborators more often and connect our research to real-world products as closely as possible. 

• We participated in the EPE ECCE Europe Conference and the Smart Battery Annual Workshop in Aalborg, Denmark. Our talks for the Tutorial "Intelligent BMS": [Artificial Intelligence for Physics-Based Battery Modelling]; [Physics-Based Battery Charging Control for Grid-Connected Studies]. The talk for the Smart Battery Annual Workshop: [What Is Health-Aware Fastest Charging? Bridging Physical Models & ML Provides An Answer]. I was also involved in a panel discussion with Prof. Pavol Bauer from TU Delft, Prof. Kim Guldstrand Larsen and Prof. Remus Teodorescu from AAU. [Photo1, Photo2, Photo3]

Aug. 2023: 

• We participated in two conferences organized by the Swedish Electromobility Center. Our collaborator and guest researcher Chih Feng Lee gave a talk about vehicle-to-grid and our PhD student Godwin Peprah gave a poster presentation about battery thermal modelling. [Photos]

Jul. 2023: 

• Four of our papers are presented at the 22nd IFAC World Congress in Yokohama, Japan, which is the largest conference in automatic control. Check our papers here [Link1, Link2, Link3, Link4]. 

Jun. 2023: 

• Our paper "Co-estimation of state of charge and state of health for lithium-ion batteries based on fractional-order calculus" published in IEEE Transactions on Vehicular Technology in 2018 has received the Best Vehicular Electronics Paper Award of the IEEE Vehicular Technology Society! Thanks to the efforts of all co-authors and to the recognition of the committee! 

• My postdoctoral researcher Dr Xiaolei Bian and I participated in the conference AABC in Mainz, Germany. An excellent conference for batteries, particularly the session Battery Intelligence. [Photo]

• Benedick Strugnell-Lees has recently joined our team as a PhD student. He will work on the project "Optimal usage and properties of battery storage units using 2nd life batteries". Welcome Benedick!

• Our proposed project "Integrating reinforcement learning and predictive control for smart home energy management (SmartHEM)'' is awarded the prestigious Marie Skłodowska-Curie Actions (MSCA) Postdoctoral Fellowship! Excited to have the fourth Marie Skłodowska-Curie Fellow join us.

May 2023: 

• Our proposed project, "E-powertrain predictive maintenance using physics informed learning (TEAMING )," to the Staff Exchanges programme of Marie Skłodowska-Curie Actions has been granted. Great thanks to my team members and all the involved partners! 

• Our newly obtained result for physics-based machine learning has been added to arXiv. We propose a novel architecture, termed model-integrated neural networks (MINN), that is able to learn the physics-based dynamics of general autonomous or non-autonomous systems consisting of partial differential algebraic equations (PDAEs). This architecture offers a systematic way to obtain optimally simplified models that are physically insightful, numerically accurate, and computationally tractable simultaneously. 

• Our work on battery ageing prediction using AI is promoted by the Swedish Electromobility Center. Here is the newsletter "AI to predict battery aging in electric vehicles".

• I am thrilled to announce that my PhD student, Yizhou Zhang, defended his licentiate thesis successfully. Congratulations, Yizhou! Here is the thesis.

• I am proud to be involved in organising the IET’s inaugural conference on Energy Storage technologies that will be hosted in Glasgow, UK, on 15-16 November 2023. A warm welcome to your paper submissions and hope to meet you there!

Feb 2023: 

• I'm honored to be one of six internal candidates nominated by our university for the 2023 Wallenberg Academy Fellow, a prestigious grant supporting top young researchers in Sweden. If successful, this will provide valuable resources for my research. The outcome is uncertain, but I'm grateful for the opportunity.

Jan 2023: 

• I gave an invited talk titled "Machine learning for battery health diagnosis and prognosis under arbitrary usage profiles" at the Annual Meeting of Batteries Sweden (BASE).

• Dr Xiaolei Bian gave a guest lecture "Equivalent circuit models and state estimation for batteries" in the Chalmers Battery Course.

More updates at [Link]