Explainable Neural Network for Sensitivity Analysis of Lithium-ion Battery Smart Production

Battery production is crucial for determining the quality of electrode,which in turn affects the manufactured battery performance.As battery production is complicated with strongly coupled intermediate and control parameters,an efficient solution that can perform a reliable sensitivity analysis of the production terms of interest and forecast key battery properties in the early production phase is urgently required.This paper performs detailed sensitivity analysis of key production terms on determining the properties of manufactured battery electrode via advanced data-driven modelling.To be specific,an explainable neural network named generalized additive model with structured interaction(GAM-SI)is designed to predict two key battery properties,including electrode mass loading and porosity,while the effects of four early production terms on manufactured batteries are explained and analysed.The experimental results reveal that the proposed method is able to accurately predict battery electrode properties in the mixing and coating stages.In addition,the importance ratio ranking,global interpretation and local interpretation of both the main effects and pairwise interactions can be effectively visualized by the designed neural network.Due to the merits of interpretability,the proposed GAM-SI can help engineers gain important insights for understanding complicated production behavior,further benefitting smart battery production.

Towards Long Lifetime Battery:AI-Based Manufacturing and Management

Technologies that accelerate the delivery of reliable battery-based energy storage will not only contribute to decarbonization such as transportation electrification,smart grid,but also strengthen the battery supply chain.As battery inevitably ages with time,losing its capacity to store charge and deliver it efficiently.This directly affects battery safety and efficiency,making related health management necessary.Recent advancements in automation science and engineering raised interest in AI-based solutions to prolong battery lifetime from both manufacturing and management perspectives.This paper aims at presenting a critical review of the state-of-the-art AI-based manufacturing and management strategies towards long lifetime battery.First,AI-based battery manufacturing and smart battery to benefit battery health are showcased.Then the most adopted AI solutions for battery life diagnostic including state-of-health estimation and ageing prediction are reviewed with a discussion of their advantages and drawbacks.Efforts through designing suitable AI solutions to enhance battery longevity are also presented.Finally,the main challenges involved and potential strategies in this field are suggested.This work will inform insights into the feasible,advanced AI for the health-conscious manufacturing,control and optimization of battery on different technology readiness levels.

Comprehensive Waste Minimization Study at an Industrial Battery Manufacturing Plant in Ohio, USA

Industrial battery manufacturing facilities generate large quantities of hazardous waste, which must be properly treated before it can be disposed. Reducing the quantities of these waste streams can significantly reduce the cost of treatment and lead to competitive advantages. Waste minimization at these facilities is beneficial for the stakeholders and the environment. The quantities of hazardous waste can be minimized by upgrading the facility＇s technology or substituting hazardous substances, which are used in the battery manufacturing process, with more environmentally friendly options. Separation of waste streams will allow for additional reuse opportunities and revenue generation from the sale of these materials, which will enhance the financial performance of the facility. This paper provides a case study of comprehensive waste minimization in a battery manufacturing plant in Ohio, USA. Source reduction, recovery, and recycling methods are taken into account with consideration given to economic impacts. The goal of the study was to develop an understanding of the facility＇s waste generating processes, to suggest methods to reduce to the waste generation and finally to select an appropriate waste minimization option to suggest the facility＇s management team. Some of the suggested methods are currently being practiced while others are at the initial stage of development.

Revisiting the electrode manufacturing: A look into electrode rheology and active material microenvironment

The microstructures on electrode level are crucial for battery performance, but the ambiguous understanding of both electrode microstructures and their structuring process causes critical challenges in controlling and evaluating the electrode quality during fabrication. In this review, analogous to the cell microenvironment well-known in biology, we introduce the concept of ‘‘active material microenvironment”(ME@AM)that is built by the ion/electron transport structures surrounding the AMs, for better understanding the significance of the electrode microstructures. Further, the scientific significance of electrode processing for electrode quality control is highlighted by its strong links to the structuring and quality control of ME@AM. Meanwhile, the roles of electrode rheology in both electrode structuring and structural characterizations involved in the entire electrode manufacturing process(i.e., slurry preparation, coating/printing/extrusion, drying and calendering) are specifically detailed. The advantages of electrode rheology testing on in-situ characterizations of the electrode qualities/structures are emphasized. This review provides a glimpse of the electrode rheology engaged in electrode manufacturing process and new insights into the understanding and effective regulation of electrode microstructures for future high-performance batteries.

Quantifying key factors for optimised manufacturing of Li-ion battery anode and cathode via artificial intelligence

Li-ion battery is one of the key players in energy storage technology empowering electrified and clean transportation systems.However,it is still associated with high costs due to the expensive material as well as high fluctuations of the manufacturing process.Complicated production processes involving mechanical,chemical,and electrical operations makes the predictability of the manufacturing process a challenge,hence the process is optimised through trial and error rather systematic simulation.To establish an in-depth understanding of the interconnected processes and manufacturing parameters,this paper combines data-mining techniques and real production to offer a method for the systematic analysis,understanding and improving the Li-ion battery electrode manufacturing chain.The novelty of this research is that unlike most of the existing research that are focused on cathode manufacturing only,it covers both of the cathode and anode case studies.Furthermore,it is based on real manufacturing data,proposes a systematic design of experiment method for generating high quality and representative data,and leverages the artificial intelligence techniques to identify the dependencies in between the manufacturing parameters and the key quality factors of the electrode.Through this study,machine learning models are developed to quantify the predictability of electrode and cell properties given the coating process control parameters.Moreover,the manufacturing parameters are ranked and their contribution to the electrode and cell characteristics are quantified by models.The systematic data acquisition approach as well as the quantified interdependencies are expected to assist the manufacturer when moving towards an improved battery production chain.