A Novel Information Fusion Model Based on D-S Evidence Theory for Equipment Diagnosis

Abstract

With the wide-scale use of mechanical equipment, more and more faults occur. At the same time, data deluge about the conditions of machines come into being with the development of sensor technology and information technology. It provides opportunities and challenges to solve the fault problems of mechanical equipment. Information fusion seems to be a useful solution, which is the process of integration of multiple data and knowledge representing the same object into a consistent, accurate, and useful representation. A novel information fusion model, with hybrid-type fusion architecture, is built in this paper. This model consists of data layer, feature layer and decision layer, based on a new Dempster/Shafer (D-S) evidence algorithm. After the data preprocessing based on event reasoning in data layer and feature layer, the information will be fused based on the new algorithm in feature layer and decision layer. Application of this information fusion model in fault diagnosis is beneficial in two aspects, diagnostic applicability and diagnostic accuracy. An effect can be caused by different faults. This information fusion model can solve this problem and increase the number of recognizable faults, to expand the range of fault diagnosis. Additionally, this model can overcome the uncertainty of information and equipment to increase diagnostic accuracy. Two case studies are implemented by this information fusion model to evaluate it. In the first case, fault probabilities calculated by different methods are adopted as inputs to diagnose a fault, which is quite different to be detected based on the information from a single system. The second case is about sensor fault diagnosis. Fault signals are planted into the measured parameters for the diagnostic system, to test the ability to consider the uncertainty of measured parameters. The case study result shows that the model can identify the fault more effectively and accurately. Meanwhile, it has good expansibility, which may be used in more fields.