Fault detection and diagnosis method for cooling dehumidifier based on LS-SVM NARX model

• A nonlinearly ARX model is proposed for cooling dehumidifier diagnosis.
• The proposed NARX model is identified by LS-SVM.
• Both the penalty C and kernel function width σ in the LS-SVM model are automatically optimized by AGA.
• Two level models are built respectively for cooling dehumidifier fault detection and diagnosis.

Developing fault detection and diagnosis (FDD) for the cooling dehumidifier is very important for improving the equipment reliability and saving energy consumption. Due to the precise mathematic physical model for cooling dehumidifier FDD is difficult to build, a novel Nonlinear Autoregressive with Exogenous (NARX) method for the cooling dehumidifier FDD based on Least Squares Support Vector Machine (LS-SVM) is proposed. Firstly, the dehumidifier system is divided into two level models. Secondly, the parameters of the NARX model are identified by LS-SVM, and the parameters C and σ of the LS-SVM are optimized by adaptive genetic algorithm (AGA) in order to improve the model building precision. Lastly, two faults in condenser and compressor component are diagnosed by the built models. The experiment result indicates this proposed method is effective for cooling dehumidifier FDD and the model generalization ability is favorable.