Application of PCA method and FCM clustering to the fault diagnosis of excavator's hydraulic system

In order to improve reliability of the excavator's hydraulic system, a fault diagnosis approach based upon principal component analysis (PCA) method and fuzzy c-means (FCM) clustering was proposed. PCA is a powerful method for re-expressing multivariate data, which could effectively extract the correlation among process variables. With this approach, samples of target faults were used to develop PCA models in the first step and the largest eigenvalues extracted from the models were used as fault feature vector. Secondly, FCM clusering performed as fault classifier to determine the test fault. Simulated faults were introduced to validate the approach. Simulation results show that the proposed fault diagnosis approach could effectively applied to the excavator's hydraulic system.