Data driven approach for Fault Detection and Identification using Competitive Learning techniques

Use of competitive learning techniques towards the area of fault detection is being investigated. The objective of Fault Detection and Identification (FDI) is to detect, isolate and identify faults so that the system performance can be improved. This paper is focused on the data driven approach for fault detection and would use: (i) Unsupervised Competitive Learning, (ii) Conscience Learning and (iii) Self Organizing Maps to develop a robust fault diagnosis scheme. This approach would provide an effective data reduction technique for FDI so that instead of using the complete data set available from a control system, pre-processing of the available data would be done using vector quantization and clustering approach. The effectiveness of the developed algorithms is tested using the data available from a Vertical Take off and Landing (VTOL) aircraft model.