Towards Explainable Process Predictions for Industry 4.0 in the DFKI-Smart-Lego-Factory

Abstract

With the advent of digitization on the shopfloor and the developments of Industry 4.0, companies are faced with opportunities and challenges alike. This can be illustrated by the example of AI-based process predictions, which can be valuable for real-time process management in a smart factory. However, to constructively collaborate with such a prediction, users need to establish confidence in its decisions. Explainable artificial intelligence (XAI) has emerged as a new research area to enable humans to understand, trust, and manage the AI they work with. In this contribution, we illustrate the opportunities and challenges of process predictions and XAI for Industry 4.0 with the DFKI-Smart-Lego-Factory. This fully automated factory prototype built out of LEGO Ⓡ bricks demonstrates the potentials of Industry 4.0 in an innovative, yet easily accessible way. It includes a showcase that predicts likely process outcomes and uses state-of-the-art XAI techniques to explain them to its workers and visitors.

Help Me Learn! Architecture and Strategies to Combine Recommendations and Active Learning in Manufacturing

“…In the context of manufacturing, XAI technologies have been tested in several scenarios such as predictive maintenance [61], real-time process management [62], and quality monitoring [63]. One of our research goals is to highlight the models' explainability in smart manufacturing processes, aligning XAI technologies with human interaction.…”

Toward Automated Support of Complaint Handling Processes: An Application in the Medical Technology Industry

“…Second, we have to examine how the tool performs in a practical setting and how the employees integrate it into their own handling of the complaint processes. Third, if it turns out that employees do not use the tool, because they do not understand why it makes a certain recommendation, we might consider adding a tool that explains the decisions, using methods of Explainable AI [35]. Overall, a practical use of our developed prototype requires us to walk the fine line between helping an employee and ensuring that the employee herself makes all final decisions regarding the complaint handling.…”

Explainable Predictive Process Monitoring

“…It was explained above that little research work has been conducted on explaining the outcome of process predictive monitoring. The most relevant work is by Rehse et al [15], which also aims at providing a dashboard to process participants with predictions and their explanation. However, the paper does not provide sufficient details on the actual usage of the explainable-AI literature, and the very preliminary evaluation is based on one single artificial process that consists of a sequence of five activities.…”