Ensemble learning based multi-fault diagnosis of air conditioning system

• Published in: Energy and buildings Vol. 319; p. 114548
• Main Authors: You, Yuwen, Tang, Junhao, Guo, Miao, Zhao, Yuan, Guo, Chunmei, Yan, Ke, Yang, Bin
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 15-09-2024
• Subjects: Bagging and boosting; Ensemble learning; Fault detection and diagnosis; Feature selection; Multi-label learning; Multiple faults; Multiple faults; Multi-label learning; Feature selection; Bagging and boosting; Ensemble learning; Fault detection and diagnosis
• ISSN: 0378-7788
• DOI: 10.1016/j.enbuild.2024.114548

•Ensemble method for HVAC concurrent fault diagnosis.•Ensemble model enhances the Generalization and stability.•Feature selection reduces feature redundancy and enhances interpretability.•Training database can be enriched by GANs.
The failure of air conditioning systems is random and uncertain, with one or more faults occurring simultaneously at any given time. Factors such as difficulty in collecting fault data and the singularity of existing diagnostic models all impact diagnostic performance. Ensemble learning based fault diagnosis strategy for an air conditioning system was proposed. By using generative adversarial networks (GANs) to enrich the training database and combining Bagging and Boosting to reduce model variance and bias, the final output was derived by integrating the diagnostic results of multiple models. Additionally, Spearman correlation analysis and feature importance ranking were utilized to identify the features that have the greatest impact on the model so as to further enhancing its performance. Experimental results demonstrated that this method can effectively diagnose single and multiple faults even in the absence of sufficient training data. An overall accuracy of 98.54 % was achieved with a Hamming loss as low as 0.0047.