Intelligent Model-based Integrity Assessment of Nonstationary Mechanical System

The fault diagnosis model for nonstationary mechanical system is proposed in the condition monitoring. The algorithm with an improved particle filter and Back Propagation for intelligent fault identification is developed, which is used to reduce the noise of the experimental vibration signals to delete the negative effect of the noise on the feature extraction of the original vibration signal. The proposed integrated method is applied for the trouble shoot of the impellers inside the centrifugal pump. The principal component analysis (PCA) method optimizes the clean vibration signal to choose the optimal eigenvalue features.The constructed (back propagation)BP neural network is trained to get the condition models for fault identification. The proposed novel model is compared with the BP neural network based on traditional PF and particle swarm optimization particle filter (PSO-PF) algorithm. The BP neural network diagnosis method based on the improved PF algorithm is much better for the integrity assessment of the centrifugal pump impeller. This method is much significant for big data mining in the fault diagnosis method of the complex mechanical system.

Automated summary

A fault diagnosis model for nonstationary mechanical system is proposed with an algorithm utilizing an improved particle filter and Back Propagation. The method is able to reduce noise in experimental vibration signals to effectively locate impeller faults in a centrifugal pump for integrity assessment.