Operational knowledge is one of the most valuable assets in a company, as it provides a strategic advantage over competitors and ensures steady and optimal operation in machines. An (interactive) assessment system on the shop floor can optimize the process and reduce stopovers because it can provide constant valuable information regarding the machine condition to the operators. However, formalizing operational (tacit) knowledge to explicit knowledge is not an easy task. This transformation considers modeling expert knowledge, quantification of knowledge uncertainty, and validation of the acquired knowledge. This study proposes a novel approach for production assessment using a knowledge transfer framework and evidence theory to address the aforementioned challenges. The main contribution of this paper is a methodology for the formalization of tacit knowledge based on an extended failure mode and effect analysis for knowledge extraction, as well as the use of evidence theory for the uncertainty definition of knowledge. Moreover, this approach uses primitive recursive functions for knowledge modeling and proposes a validation strategy of the knowledge using machine data. These elements are integrated into an interactive recommendation system hosted on a backend that uses HoloLens as a visual interface. We demonstrate this approach using an industrial setup: a laboratory bulk good system. The results yield interesting insights, including the knowledge validation, uncertainty behavior of knowledge, and interactive troubleshooting for the machine operator.

Multi-class ensemble classification remains a popular focus of investigation within the research community. The popularization of cloud services has sped up their adoption due to the ease of deploying large-scale machine-learning models. It has also drawn the attention of the industrial sector because of its ability to identify common problems in production. However, there are challenges to conform an ensemble classifier, namely a proper selection and effective training of the pool of classifiers, the definition of a proper architecture for multi-class classification, and uncertainty quantification of the ensemble classifier. The robustness and effectiveness of the ensemble classifier lie in the selection of the pool of classifiers, as well as in the learning process. Hence, the selection and the training procedure of the pool of classifiers play a crucial role. An (ensemble) classifier learns to detect the classes that were used during the supervised training. However, when injecting data with unknown conditions, the trained classifier will intend to predict the classes learned during the training. To this end, the uncertainty of the individual and ensemble classifier could be used to assess the learning capability. We present a novel approach for anomaly detection using ensemble classification and evidence theory. A pool selection strategy is presented to build a solid ensemble classifier. We present an architecture for multi-class ensemble classification and an approach to quantify the uncertainty of the base classifiers and the ensemble classifier. We address the problem of detecting unknown conditions (while feeding out-of-distribution data), presenting a novel approach that monitors the uncertainty of the ensemble classifier using evidence theory. Finally, we use the benchmark Tennessee Eastman to perform experiments to test the ensemble classifier's prediction and anomaly detection capabilities.

No abstract

No abstract

No abstract