Fault Detection in Industrial Plant Using k-Nearest Neighbors with Random Subspace Method

摘要

In this paper we propose a ensemble approach using k-nearest neighbors (k-NN) combined with random subspace method (RSM) to achieve an improved classification performance to fault detection problem. Fault detection and isolation is a subfield of control engineering which concerns itself with monitoring a system, identifying when a fault has occurred, and pinpointing the type of fault and its location. Fault detection is utilized to determine that a problem has occurred within in a certain channel or area of operation. In other words, the software application may recognize that the system is operating successfully, but performing at a level that is sub-optimal to predetermined target. In our study we showed that the proposed methodology is more efficiently than classical artificial neural network.