An artificial intelligence approach towards fault diagnosis of an air-handling unit

This paper presents a new method for fault diagnosis of an air-handling unit (AHU). The method determines performance indices using dynamic fuzzy neural networks (DFNN). The DFNN has two outstanding characteristics. Firstly, the learning speed is very fast and fuzzy rules can be generated quickly because no iterative learning is employed. Secondly, by using the pruning technology, significant nodes can be self-adaptive according to their contributions to the system performance. Consequently, the proposed method can achieve high performance with a parsimonious structure. Comprehensive comparisons with other existing approaches of fault diagnosis for the AHU demonstrate that the proposed method is superior in training speed and diagnosis speed and has high diagnosis rate.