Assessment of a large language model based digital intelligent assistant in assembly manufacturing

Abstract

The use of Digital Intelligent Assistants (DIAs) in manufacturing aims to enhance performance and reduce cognitive workload. By leveraging the advanced capabilities of Large Language Models (LLMs), the research aims to understand the impact of DIAs on assembly processes, emphasizing human-centric design and operational efficiency. The study is novel in considering the three primary objectives: evaluating the technical robustness of DIAs, assessing their effect on operators' cognitive workload and user experience, and determining the overall performance improvement of the assembly process. Methodologically, the research employs a laboratory experiment, incorporating a controlled setting to meticulously assess the DIA's performance. The experiment used a between-subjects design comparing a group of participants using the DIA against a control group relying on traditional manual methods across a series of assembly tasks. Findings reveal a significant enhancement in the operators' experience, a reduction in cognitive load, and an improvement in the quality of process outputs when the DIA is employed. The article contributes to the study of the DIA's potential and AI integration in manufacturing, offering insights into the design, development, and evaluation of DIAs in industrial settings.