将物理学与人工智能融合应用于高级电池性能预测研究

该博士项目旨在开发一种先进的电池预测人工智能框架，通过融合电化学物理理论与机器学习技术，以预测不同条件下的电池退化及剩余使用寿命。项目还包括对二次电池应用的研究，重点在于在不同运行工况下进行精准预测并给出不确定性评估。

Introduction: Through SRAP, Coventry-based PhD researchers undertake one to two years of research training in Singapore under the joint supervision of researchers from both Coventry and ARTC. The programme offers PhD researchers an exceptional opportunity to gain international research experience while contributing to ambitious, multidisciplinary research addressing global technological and sustainability challenges. This collaborative PhD programme enables researchers to work at the interface of academic research, advanced engineering and industrial innovation. Researchers will engage with expertise and facilities across both institutions, build international research networks, and develop experience in translating advanced research into practical solutions for future mobility and remanufacturing systems. The programme is particularly suited to ambitious researchers seeking to shape next-generation electric mobility systems and circular manufacturing technologies, while gaining valuable research experience across the UK and Singapore. Project details: This particular PhD research project will develop an advanced physics-informed artificial intelligence (AI) framework for battery prognostics, enabling accurate prediction of battery degradation trajectory, and remaining useful life (RUL) under dynamic operating conditions. The research will integrate electrochemical and degradation physics with machine learning and data-driven modelling to understand and predict battery ageing trajectories. A key objective will be to develop models capable of predicting future degradation trajectories together with quantified confidence levels, providing reliable uncertainty estimates for decision-making rather than relying solely on point predictions. The project will further investigate second-life battery applications, forecasting the RUL of batteries when they are repurposed for different operating profiles and applications. This will involve considering variations in duty cycles, temperature, charging strategies, load profiles, and application requirements. The research might include: · Investigate battery degradation under a range of operating conditions relevant to electrified propulsion and second-life applications; · Implement the battery prognostics through machine learning and deep learning techniques; · Analyse how historical physical mechanisms such as capacity loss, resistance growth, loss of lithium inventory, loss of active materials, and other relevant ageing processes can be represented in the prognostics; · Integrate physics-based battery models/constraints and AI effectively to improve long-term degradation prediction; · Forecast battery degradation trajectories with reliable confidence and uncertainty estimates; · Predict the RUL when batteries transition from their primary application to different second-life applications. · Investigate how the developed approach can be transferred across battery chemistries, and operating conditions.

Entry requirements: A minimum of a 2:1 first degree in a relevant discipline/subject area with a minimum 60% mark in the project element or equivalent with a minimum 60% overall module average. PLUS The potential to engage in innovative research and to complete the PhD within 4 years. A minimum of English language proficiency (IELTS academic overall minimum score of 7.0 with a minimum of 6.5 in each component). Additional requirements: Candidates should normally hold, or expect to obtain, a strong first degree and/or master's qualification in a relevant STEM discipline. Suitable backgrounds may include: • Computer Science and Engineering • Mathematics • Control Science and Engineering • Electrochemical Engineering • Mechanical Engineering • Electrical and Electronic Engineering, or a closely related discipline. Depending on the specific PhD project, desirable technical experience may include one or more of the following: • Battery technologies and battery management systems • Battery testing and characterisation • Battery degradation • Artificial Intelligence • Modelling • Electric vehicle or electric propulsion systems • Control • Forecasting Candidates should demonstrate a strong interest in interdisciplinary research and an enthusiasm for addressing complex engineering and sustainability challenges. Candidates should be capable of working independently while also contributing effectively to a multidisciplinary research team. Strong analytical, problem-solving, communication and scientific writing skills are essential. As the programme involves international collaborative research and an extended research attachment in Singapore, candidates should also demonstrate adaptability, cultural awareness, effective communication and a willingness to work in an international research environment. Candidates may be required to satisfy the academic, English-language, immigration, security and other eligibility requirements of Coventry University, A*STAR and the Singapore Research Attachment Programme.

资助来源： 学费与奖学金 优势： 成功入选的候选人将获得全面的研究训练，包括技术、个人及职业技能方面的培养。考文垂大学的所有研究人员（从博士到教授）均属于博士学院与研究能力与发展中心，该机构将提供高质量的培训与职业发展支持。 您被邀请加入考文垂人工智能博士培训中心（C-CDT AI）：这是一个充满活力的合作平台，汇集了大学各处的人工智能研究人员与PGR研究人员。作为C-CDT成员，您将受益于系统的人工智能培训（涵盖核心研究方法至伦理与创新领域）、跨学科同行网络、专业指导、共享GPU/云资源、研讨会、讲座以及以行业为导向的挑战项目。这种额外的培训与社区支持可补充您的本研究所提供的课程，加速您的技术与职业发展，并让您融入一个广泛的人工智能研究生态系统，该体系致力于解决各领域的关键问题。

申请方式： 关于该项目的更多信息，请联系**[会员信息]** 所有申请者必须提供完整的辅助文件、推荐信，以及一篇长度为2000字的说明文，以证明申请者的专业能力与兴趣与该项目具有相关性。 申请考文垂大学 申请流程：