Performance Assessment based on Health Baseline and MML for Hydraulic System

Abstract

In recent years, with the wide application of hydraulic system, the performance assessment for hydraulic system has gained significant attention. However, a few studies focus on health assessment and traditional methods such as distance metric functions have limitation because different metric functions are only suitable for specific requirements. A scheme of performance degradation assessment based on health baseline and metric learning is proposed in this study. First, General regression neural network (GRNN) based observer is employed as health baseline to generate the estimated output of hydraulic system. The residual is obtained by calculating difference between the actual and estimated output. Then, time domain features are extracted from residual error. After that, apply the Mahalanobis metric learning (MML) to find a suitable metric adaptively for the training data set regarding distance. Finally, the distance between current status and normal status is normalized into confidence value (CV) to quantize the performance. A simulation model of hydraulic system is established based on HyPneu and Simulink, then gradual fault are injected to validate the proposed method. The results of experimental analysis demonstrate the effectiveness and adaptability of the performance degradation assessment method.