Application of LSTM Method Combined with Feature Optimization in Chiller Failure Detection

Abstract Aiming at the characteristics of a long short-term memory network (LSTM) which is suitable for processing high-dimensional, strongly coupled, and highly time-dependent data, it combines advantages feature selection to reduce difficulty learning tasks improve performance model fault diagnosis. This paper proposes an LSTM method combining sequential floating forward search with integrated chiller sensor deviation detection. The detection results proposed are compared those single method, concluded that efficiency in significantly better than method.