Petroleum Science >2009,??Issue 2:??208-216 DOI: https://doi.org/10.1007/s12182-009-0034-8
Incipient mechanical fault detection based on multifractal and MTS methods Open?Access
文章信息
作者：Jinqiu Hu, Laibin Zhang, Wei Liang & Zhaohui Wang
作者單位：
投稿時(shí)間：08 May 2009
引用方式：Hu, J., Zhang, L., Liang, W. et al. Incipient mechanical fault detection based on multifractal and MTS methods. Pet. Sci. 6, 208–216 (2009). https://doi.org/10.1007/s12182-009-0034-8
文章摘要
An incipient mechanical fault detection method, combining multifractal theory and Mahalanobis-Taguchi system (MTS), which is based on statistical technology, is proposed in this paper. Multifractal features of vibration signals obtained from machine state monitoring are extracted by multifractal spectrum analysis and generalized fractal dimensions. Considering the situation of mass samples of normal mechanical running state and few fault states, the feature parameters corresponding to different mechanical running states are further optimized by a statistical method, based on which incipient faults are subsequently identified and diagnosed accurately. Experimental results proved that the method combining multifractal theory and MTS can be used for incipient fault state recognition effectively during the mechanical running process, and the accuracy of fault state identification is improved.
關(guān)鍵詞
-
Incipient fault; fault detection; multifractal; Mahalanobis-Taguchi system (MTS)