Manufacturing is a highly complex field involving materials, machines, and processes that interact in ways we often don't fully understand. This complexity poses a significant challenge when we attempt to optimize manufacturing processes, introduce new materials, or enhance efficiency. While artificial intelligence (AI) has shown great promise in helping us identify patterns, make predictions, and drive innovation in manufacturing, understanding how some AI models make their predictions or decisions is very difficult. This 'black box' problem is a significant challenge, especially when manufacturers need to trust AI tools to improve production, quality, and safety.
The M-CAML (Michigan Cognitive and Adaptive Manufacturing Lab) team aims to develop methods and tools for interpreting and explaining how powerful AI models make predictions and decisions in manufacturing. By seeing what's going on inside the 'black box', we can also uncover new scientific or engineering insights about the underlying manufacturing processes. The ability to interpret and explain AI models is called 'explainable AI' (XAI) and is an exciting and rapidly expanding research area.
We will conduct a comprehensive study of AI models and architectures as well as methods, demonstrated, or projected, that are used to interpret mathematically different classes of AI models, and which we believe can be used in manufacturing contexts. The outcome of this work will be a validated compilation of quantitative information that will serve to project opportunities as well as baseline data set for assessing these methods and models.
The objective is to actualize M-CAML's research agenda that attracts partners and collaborators across sectors (industry, government, academia) and horizons (short, medium, long-term). This research agenda will also support research in cognitive manufacturing, generative design of manufacturing systems, and Digital Twin architectures. We hope that you will consider becoming the newest member of the M-CAML team.