A Novel Incipient Fault Detection and Diagnosis Scheme Based on Kernel Density Weighting Support Vector Data Description: Application on the DAMADICS Benchmark Process

Abstract

Support vector data description (SVDD) is a classical process monitoring skill and usually uses Euclidean distance to evaluate the status of a process. It should be noted that the proposed evaluation method restricts the detection performance for some faults, when the overall fault data has structural deviation compared with normal data. To address this problem, a novel incipient fault detection and diagnosis scheme based on kernel density weighting SVDD (KDWSVDD) is proposed. Firstly, the multidimensional kernel density estimation function and the density threshold are obtained by training data. Next, the adaptive weight is given to a test sample through measuring the probability density difference between the test sample and the training samples. Then, the statistic in SVDD is reconstructed to complete the fault detection of weighted samples. Finally, the contribution graph method is extended to diagnose the abnormal variable of incipient fault. KDWSVDD can increase the fault scale by giving adaptive weight to the test samples, so as to effectively monitor the incipient fault in a process. The experimental results on two numerical cases and DAMADICS benchwork process show that compared with SVDD, KDWSVDD has better process monitoring performance for incipient fault.

Keywords

• Data-driven detection
• Multidimensional kernel density estimation
• Support vector data description
• Incipient fault
• Fault diagnosis