Trustworthiness of Artificial Intelligence Applications for Quality Optimisation in Metal Additive Manufacturing

Abstract

Market demand is driving the trend towards more individualised products, a phenomenon known as mass customisation. This has spurred the development of innovative technologies, collectively referred to as Industry 4.0. Within this framework, Metal Additive Manufacturing and Artificial Intelligence serve as cornerstone technologies. In manufacturing, Metal Additive Manufacturing promises the ability to efficiently produce low-volume products with reduced lead times. At the same time, it promises greater sustainability, reduced production complexity and improved supply chain resilience. However, the complex physical processes involved are beyond the capabilities of traditional quality improvement techniques such as Statistical Quality Control, necessitating the incorporation of Artificial Intelligence. Although the AI Act seeks to establish a robust regulatory framework to improve the trustworthiness of AI applications, empirical studies substantiating this trust in the context of quality optimisation remain scarce. To address this gap, this study explores the implementation of trustworthy AI in quality optimisation for Metal Additive Manufacturing, evaluating established frameworks and employing state-of-the-art methods to validate the trustworthiness of AI-based quality optimisation techniques. In addition, the physical plausibility and reliability of the AI models are qualitatively checked by process experts.