A data fusion equipment monitoring method based on fuzzy set and improved D-S evidence theory

Abstract

In order to solve data problems with redundant, conflict and uncertainty in monitoring large mechanical equipment, a data fusion equipment monitoring method is proposed through the combination of fuzzy set and improved D-S evidence theory. Firstly, a recognition framework is built based on the actual situation of the equipment. Then, the likelihood of the attributes is calculated according to the fuzzy set membership function and the sensor's observation function, and the likelihood is used to determine the basic belief assignment function value of the attributes. Finally, the data fusion is carried out using the weight-based D-S's combination rule, and the state of equipment can be derived from the data fusion results. A simulation of monitoring method with application to the ozone generator is carried out using the proposed method, the results show that the accuracy of the proposed method is proved, and the uncertainty of the results is obviously reduced comparing with classic analyzing methods, which concludes that the proposed method has a practical significance in monitoring the state of equipment.