Rolling bearing fault diagnosis based on quantum LS-SVM

Abstract Rolling bearing is an indispensable part of the contemporary industrial system, and its working conditions affect state entire system. Therefore, there great engineering value to researching improving fault diagnosis technology rolling bearings. However, with involvement whole mechanical equipment, we need have a large quantity data support accuracy diagnosis, while efficiency classical machine learning algorithms poor in processing big data, huge amount computing resources required. To solve this problem, paper combines HHL algorithm quantum LS-SVM proposes model based on least square vector (QSVM). Based experiments simulated analog computers, demonstrate that our QSVM feasible, it can play far superior advantage over context data.