MTMmotion®

MTM methods are a proven standard for analyzing and designing human work processes. However, work planners continue to face challenges in applying these methods correctly and efficiently. Artificial intelligence — particularly in the case of large language models — holds significant potential for combatting these challenges. However, the use of AI raises legitimate questions regarding the reliability and traceability of the results. The approach presented here combines LLMs with a rule-based algorithm to extract the information required for MTM analyses from textual process descriptions such as work instructions. This information is then translated into MTM analyses in accordance with the MTM methodology. This approach ensures that the resulting analyses can be transparently traced back to the original input data by the user.

The cost of production is a key factor for industrial companies. Labour costs are one relevant portion of these costs, especially for production sites with a high percentage of manual processes. Therefore, describing, analysing, and designing manual work processes in a systematic way is an important task in most Industrial Engineering departments. There are multiple methods to describe and analyse work processes. Widely known methods include REFA, MTM and Work Factor. While there are multiple MTM methods to address the different types of production, one of the most established methods is MTM-UAS®. The most recent process building block system is MTM-HWD®. It describes work processes not only from a productive standpoint, but also includes ergonomic factors to assure productive and ergonomic work in one step. While the MTM systems can be used to systematically design work processes, they still require manual effort for data collection and interpretation. Due to this fact, not every ...