Research On CHMM Based Equipment Performance Degradation Assessment

With the rapid development of science and technology, modern mechanical equipment is proceeding at the direction of hugeness, high-speed, heavy-load and intelligence. The faults of equipment will affect the production efficiency and induce economic loss, or even bring up personnel casualty and cause serious social effects. So it is an urgent problem to be solved on how to assess the equipment condition effectively so as to take measures in time to prevent the catastrophic accidents.The mechanical equipment performance degradation is a continuous process, and there are some different stages from the initial degradation to the final failure. If the equipment performance can be detected, it would be possible to make the equipment maintenance plan well targeted and prevent the failure of equipment. Based on the above, the equipment performance degradation assessment is proposed.In this paper, performance degradation assessment based on CHMM is researched systematically, and the main contents are as follows:1) According to the requirements of performance degradation assessment, Kernel-PCA (KPCA) based feature extraction is researched. A further discussion about the optimization of kernel function parameter is made, and experimental result shows that KPCA is more effective than PCA in classification problems.2) Introduce CHMM to the performance degradation analysis. CHMM based performance monitoring is proposed under the situation of incomplete equipment state data, and the self-adapting alarm technology is discussed. Also, the whole framework of performance degradation assessment based on CHMM is proposed under the situation of complete data, which includes degradation mode recognition, performance quantitative assessment and remaining useful life prediction. Meanwhile, the Analytic Hierarchy Process (AHP) is used to solve the equipment performance integration problem.3) In order to validate the effectiveness of the performance degradation assessment method, a bearing accelerated life test is performed on the accelerated bearing life tester (ABLT-1A). The results show that: Firstly, under the situation of incomplete data, it is sensitive and accurate to reflect the bearing's performance using CHMM based performance monitoring method, and the self-adapting alarm technology can work very well. Secondly, under the situation of complete data, CHMM based performance degradation assessment method can be used to indicate the bearing's performance state correctly and quantitatively, and estimate the bearing's remaining useful life effectively.4) Design the equipment performance degradation assessment prototype system. The performance degradation assessment module is designed and developed based on the distributed programming model, WCF (Windows Communication Foundation), which is the realization technology of SOA (Service-Oriented Architecture). The utilization of WCF can solve the problem that the realization of performance degradation assessment algorithm is too complex to be satisfied with only one computer. A gas blower performance degradation assessment system is realized on the .NET platform, which validates the availability of the design.