A Novel Fault Identification Method Driven by Knowledge and Data

Abstract

In the field of intelligent manufacturing, fault identification is an effective way to improve product service by identifying the cause of failures. For addressing it, the Generalized Bayesian Network (GBN) model is extended based on the traditional Bayesian Network in this paper, which redefines the directed edges and probability parameters among nodes. Compared with Bayesian Network, the GBN model has the ability to simultaneously define causality and correlation of variables. In addition, the structure of network is not only based on statistical data but also driven by expert knowledge. In order to achieve the collaboration of data and knowledge while maintaining the consistency, a hierarchical collaborative framework is designed including the data layer and knowledge layer. Furthermore, a hierarchical multi-objective optimization algorithm, namely Hierarchical Non-dominated Sorting Genetic Algorithm II (HNSGA-II), is advanced to solve the proposed model. Finally, an industrial case study for fault cause identification targeting the product service helps illustrate all details.