Fault diagnosis result fusion method and device

Abstract

The invention provides a fusion method and a device for fault diagnosis results, wherein, the method comprises the following steps of: acquiring a plurality of fault diagnosis results obtained by a plurality of diagnosis methods; wherein each diagnosis method corresponds to a fault diagnosis result; the corresponding fault diagnosis results of each diagnosis method are transformed into individualmatching degree according to the individual matching degree matrix. Individual matching degree represents the degree of trust in the fault diagnosis results given by each diagnostic method. Accordingto the transformed individual matching degree, the confidence level of multi-fusion results of multi-fault diagnosis results is determined by pre-established confidence rule database. The confidence rule base is established according to several fault fusion samples in advance, and the confidence level represents the trust degree of each fusion result. According to the confidence of the fusion results, the final fault diagnosis results are determined. The technical scheme improves the accuracy of the fault diagnosis result and ensures the efficient and safe operation of the equipment.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to a method and device for fusing fault diagnosis results. Background technique [0002] Classical fault diagnosis methods have been widely used in the actual industry. However, with the increase of production scale, the increase of process complexity and the improvement of product quality requirements, higher requirements are put forward for fault diagnosis. On the one hand, the diagnostic performance of the fault diagnosis method may decrease significantly with the increase of running time, resulting in false alarms and missing alarm information. Operators need to spend a lot of time to check these alarm information one by one to ensure the normal and safe operation of the system. On the other hand, any fault diagnosis method often needs to ignore some factors or make some assumptions in the process of derivation and proof. These preconditions often lead to different fa...

AI Technical Summary

Problems solved by technology

However, the D-S fusion theory cannot deal with the incompleteness of prior knowledge, which shows that evidence conflicts often appear in the process of decision fusion, resulting in low accuracy of fault diagnosis fusion.

[0004] For the above problems, no effective solution has been proposed

Images