Classification Techniques for Fault Detection and Diagnosis of an Air-Handling Unit

Published

September 1, 1999

Author(s)

J House, Won Y. Lee, Dong R. Shin

Abstract

The objective of this study is to demonstrate the application of several classification techniques to the problem of detecting and diagnosing faults in data generated by a variable-air-volume air-handling unit simulation model, and to describe the strengths and weaknesses of the techniques considered. Artificial neural network classifiers, nearest neighbor classifiers, nearest prototype classifiers, a rule-based classifier, and a Bayes classifier are considered for both fault detecting and diagnostics. Based on the performance of the classification techniques, the Bayes classifier appears to be a good choice for fault detection. It is a straightforward method that requires limited memory and computational effort and it consistently yielded the lowest percentage of incorrect diagnoses. For fault diagnosis, the rule-based method is favored for classification problems such as the one considered here where the various classes of faulty operation are well separated and can be distinguished by a single dominant symptom or feature. Results also indicate that the success or failure of classification techniques hinges to a large degree on an ability to separate different classes of operation in some feature (temperatue, pressure, etc.) space. Hence, preprocessing of data to extract dominant features is as important as the selection of the classifier.

Citation

Ashrae Journal

Volume

105

Issue

No. 1

Pub Type

Journals

Download Paper

Local Download

Keywords

air handling, classification, monitoring

Citation

House, J. , Lee, W. and Shin, D. (1999), Classification Techniques for Fault Detection and Diagnosis of an Air-Handling Unit, Ashrae Journal, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=860766 (Accessed November 8, 2024)