December 2016
·
17 Reads
Pressurizer is one of the major equipment in nuclear power plant (NPP), which controls the reactor cooling system pressure within the allowable range. That is, faults of the pressurizer can be hugely affected to the NPP; thus early faults detection of the pressurizer is very significant to the NPP safety. For this, this study applies Mahalanobis Taguchi System (MTS) which is one of the promising pattern classification methods based on mahalanobis distance concept and Taguchi quality engineering theory to the early faults detection problem of pressurizer pressure control system. To validate the faults detection performance of the MTS, we conducted experiments using data from full scope NPP simulator based on a pressurizer pressure transmitter faults scenario. As a results, MTS can rapidly detect the faults compared to conventional faults detection based on single sensor monitoring.