Application of pattern matching method for detecting faults in air handling unit system

• Propose a strategy to utilize the building automation systems data for automated fault detection and diagnostics.
• Calculate the degree of similarity between historical data window and current snapshot data in order to locate periods of historical operation that are similar to current operating conditions.
• The methodology is validated by operational data of an AHU system in real building.
• Test results show that the sensibility of PCA models is enhanced by preprocessing the training data with the Pattern Matching method.

This paper presents a hybrid air handling unit (AHU) fault detection strategy based on Principal Component Analysis (PCA) method and Pattern Matching method. The basic idea of the pattern matching method is to locate periods of operation from a historical data set whose operational conditions are similar to the target operating condition. The proposed Pattern Matching-PCA method uses two similarity factors, PCA similarity factors and Distance similarity factors, to characterize the degree of similarity between historical data window and current snapshot data. PCA model is then built using the historical AHU operation dataset that are identified to be similar to current snapshot operation data. The method is validated by operational data of an AHU system in real building. The results show that the sensibility of PCA models is enhanced by preprocessing the training data with the Pattern Matching method.