Combining case-based reasoning and process mining for root cause analysis in complex manufacturing environments

Root Cause Analysis (RCA) of problems in a manufacturing process is becoming increasingly complex due to the growing complexity of products and processes. On the other hand, due to digitalisation and Industry 4.0, various systems collect an increasing volume of data about the processes. These data can be used to improve the RCA, but it can be challenging because the data is scattered across different systems. Therefore, this paper presents a framework to assist engineers with location-time RCA. The proposed framework is based on the Case-Based Reasoning cycle. It includes four steps: collect production trace data, enrich the collected data, identify the production trace, and finally compare traces to identify the location of the root cause. Techniques from the Semantic Web and Process Mining communities are combined in the framework to offer an integrated solution from data collection to root cause localisation.