Large Language Model‐Based Cognitive Assistants for Quality Management Systems in Manufacturing: A Requirement Analysis

Engineering Reports, vol. 7

Abstract

ABSTRACT The integration of large language model‐based cognitive assistants (LLM‐CAs) into manufacturing offers opportunities to enhance decision‐making, quality, and efficiency. However, aligning LLM‐CAs with quality management systems (QMS), such as ISO 9001:2015, remains a complex task. This study systematically reviewed 53 studies (2022–2024) to identify 84 literature‐based requirements related to LLM‐CAs deployment for QMS. We translated the identified challenges into 24 actionable requirements using thematic analysis. Grounded in the human, technology, and organization concept (HTO), we classified the requirements across HTO subsystems and their overlaps and mapped them to the seven ISO 9001:2015 clauses. Our analysis reveals strong alignment between LLM‐CAs and QMS principles, particularly in areas such as support in decision‐making processes and continuous improvement. Moreover, our findings highlight persistent challenges, such as transparency, compliance risks, and workforce adaptation. An illustrative case study of setup time optimization demonstrates the practical application of these findings. The results provide a structured foundation for QMS‐compliant integration of LLM‐CAs into manufacturing. Future research should extend these findings through stakeholder‐driven validation, system architecture development, and real‐world implementation studies. This extension would, therefore, support responsible and human‐centered LLM‐CA adoption in digitalized manufacturing environments.

Authors 4

1. Marcos Galdino corresponding Aachen IQS Intelligence in Quality Sensing Laboratory for Machine Tools and Production Engineering (WZL)

   RWTH Aachen University

   Affiliation as printed

   IQS Intelligence in Quality Sensing, Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University RWTH Aachen University Aachen Germany

2. Tobias Hamann Aachen IQS Intelligence in Quality Sensing Laboratory for Machine Tools and Production Engineering (WZL)

   RWTH Aachen University

   Affiliation as printed

   IQS Intelligence in Quality Sensing, Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University RWTH Aachen University Aachen Germany

3. Anas Abdelrazeq Aachen IQS Intelligence in Quality Sensing Laboratory for Machine Tools and Production Engineering (WZL)

   RWTH Aachen University

   Affiliation as printed

   IQS Intelligence in Quality Sensing, Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University RWTH Aachen University Aachen Germany

4. Ingrid Isenhardt Aachen IQS Intelligence in Quality Sensing Laboratory for Machine Tools and Production Engineering (WZL)

   RWTH Aachen University

   Affiliation as printed

   IQS Intelligence in Quality Sensing, Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University RWTH Aachen University Aachen Germany