Research On Fault Detection And Diagnosis Of Refrigeration Based On Principal Component Analysis

Fault detection and diagnosis (FDD) is the basis for timely maintenance to keep refrigeration systems operate at a normal and efficient condition. This study investigates Expert System, ANN and Fuzzy Math in FDD of refrigeration systems with the air-side heat transfer coefficient used for FDD. The interrelationship between faults and their symptoms are summarized which provide the base for the following study. PCA-SVM combined diagnosis system presents excellent performance that is high diagnosis accuracy and less time.According to the characteristics of gradual faults in refrigeration systems, a fault detection model based on Principal Component Analysis (PCA) was presented. An experimental study was introduced , which was conducted on a 90-ton centrifugal chiller to produce a database that will be used in the development and evaluation of Fault Detection and Diagnostic (FDD) methods applied to chillers. The present FDD model was validated and evaluated by the experiment. The results show that The PCA-FDD model can meet the detection performance requirement. Moreover, the model was applied to determine the kind of faults for the first time , which achieved satisfactory results.