Affiliations: [a] School of Science, Beijing University of Posts and Telecommunications, Beijing, China
| [b] Colombian College of Arts and Science, The George Washington University, Washington, USA
Correspondence:
[*]
Corresponding author. Li Yajie, School of Science, Beijing University of Posts and Telecommunications, Beijing, China. E-mail: lyj7712@163.com.
Abstract: The safety of the mechanical equipment is very important that gives mechanical fault diagnosing technique great significance. This article is focusing on the complex fault diagnosis applied on mechanical equipment. Since it is not easy to make an accurate explanation to the principle component when we use the principal component analysing method to extract the principal component, we use the factor analysis method in Step 1 to do the dimension reduction to the variables. We use Chebyshev’s inequality to do the estimation because we don’t know the variables’ distribution in Step 2. We do the fault diagnosing in Step 3. We have different options to realize fault diagnosing. We can set a threshold according to our former experiences to do fault diagnosing. And compare it to the normal condition to get the differences thus to finalize diagnosing. We can also go to an expert. This step is called complex data analysing method. We will use this method to check the feasibility of this method.
Keywords: Fault detection, data analysis, factor analysis, Chebyshev’s inequality
