A FAULT DIAGNOSIS METHOD BASED ON WAVELET APPROXIMATE ENTROPY FOR FAN

摘要：

The vibration signal of the fan is a typical non-stationary time-varied signal with chaotic characteristic.Approximate entropy is able to take description of disorder or irregularity in the motion systems.This paper introduces approximate entropy as a tool to describing the fan conditions.A threshold filtering algorithm based on the wavelet for reducing noise is introduced.Utilizing the above method, the vibration signals of the fan under different working conditions are analyzed.The result shows that the approximate entropy is able to identify the conditions of the fan with faults compared with the normal condition, thereby providing an effective technology for condition monitoring and fault diagnosis of mechanical equipment.

关键词： Fault diagnosis Wavelet coefficient Approximate entropy Fan

作者: JIN TIAN JUN-JIE GU XUE-ZHI PENG ZHI-MING QIN

作者单位: Education Ministry Key Laboratory on Condition Monitoring and Control for Power Plant Equipment, North China Electric Power University, Baoding 071003, China

会议类型: 国际会议

会议名称: 2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)

会议地点: 香港

会议语种:英文

页码: 519-523

在线出版日期: 2007-08-19（万方平台首次上网日期，不代表论文的发表时间）