Hybrid method for the diagnosis of electrical rotary machines by vibration signals
暂无分享,去创建一个
The vibration study in rotational electrical machines is a research topic that involves mathematical modeling, model identification, and signal analysis, among others. The failures in motors and generators modify the vibration signals. In this paper, the use of Adaptive Networks Based on Fuzzy Inference System (ANFIS) is proposed for rotary electrical machines' diagnosis, because it is able to achieve consistent approximations of machines' behavior when facing a faulty condition or functioning normally. Results using actual measurements are valuable and give higher expectations for the future.
[1] James I. Taylor,et al. The Vibration Analysis Handbook , 1994 .
[2] Jin Chen,et al. Neuro-fuzzy Based Condition Prediction of Bearing Health: , 2009 .
[3] Stefania Gallova,et al. Neuro-Fuzzy Learning and Genetic Algorithm Approach with Chaos Theory Principles Applying for Diagnostic Problem Solving , 2009 .
[4] Jyh-Shing Roger Jang,et al. ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..