Title :
Prediction and diagnosis of mine hoist fault based on wavelet neural network
Author :
Xijun Zhu ; Jinyun Guo ; Chongyu Wei
Author_Institution :
Coll. of Sci. & Technol., Qingdao Univ. of Sci. & Technol., Qingdao
Abstract :
The wavelet neural network is used to analyze and predict the time series of key characteristic parameters about the abradability of steel wire rope, time of idle motion, life of pad wear away, clearance of brake shoe, remnant oil pressure and deflection degree of brake disk for the mine hoist. Then the trend of mine hoist fault can be forecasted from these predicted characteristic parameters. Simulations and experiments indicate that the forecasting precision can satisfy the practical requirement. It is very significant to ensure the secure and efficient running of mine hoist.
Keywords :
discs (structures); fault diagnosis; hoists; mining; neural nets; wavelet transforms; wear; brake disk deflection degree; brake shoe clearance; idle motion time; mine hoist fault diagnosis; mine hoist fault prediction; pad wear away life; remnant oil pressure; wavelet neural network; wire rope abradability; Fault diagnosis; Footwear; Motion analysis; Neural networks; Petroleum; Predictive models; Steel; Time series analysis; Wavelet analysis; Wire; Fault Diagnosis; Fault Prediction; Mine Hoist; Wavelet Neural Network;
Conference_Titel :
Control and Decision Conference, 2008. CCDC 2008. Chinese
Conference_Location :
Yantai, Shandong
Print_ISBN :
978-1-4244-1733-9
Electronic_ISBN :
978-1-4244-1734-6
DOI :
10.1109/CCDC.2008.4597383
