Interval-Valued Features Based Machine Learning Technique for Fault Detection and Diagnosis of Uncertain HVAC Systems

IEEE Access

Sondes Gharsellaoui¹  Mohamed Trabelsi¹  Shady S. Refaat²  Hassani Messaoud³  Majdi Mansouri⁴  Mohamed-Faouzi Harkat⁴ 

[1] Electrical and Computer Engineering Program, Texas A&x0026;Electronic and Communications Engineering Department, Kuwait College of Science and Technology, Safat, Kuwait;LASMA, Badji Mokhtar - Annaba University, Annaba, Algeria;M University at Qatar, Doha, Qatar;

关键词: HVAC systems;    machine learning (ML);    model uncertainties;    feature extraction and selection;    interval-valued principal component analysis (IPCA);    fault detection and diagnosis (FDD);   

DOI  :  10.1109/ACCESS.2020.3019365

来源: DOAJ

【 摘 要 】

The operation of heating, ventilation, and air conditioning (HVAC) systems is usually disturbed by many uncertainties such as measurement errors, noise, as well as temperature. Thus, this paper proposes a new multiscale interval principal component analysis (MSIPCA)-based machine learning (ML) technique for fault detection and diagnosis (FDD) of uncertain HVAC systems. The main goal of the developed MSIPCA-ML approach is to enhance the diagnosis performance, improve the indoor environment quality, and minimize the energy consumption in uncertain building systems. The model uncertainty is addressed by considering the interval-valued data representation. The performance of the proposed FDD is investigated using sets of synthetic and emulated data extracted under different operating conditions. The presented results confirm the high-efficiency of the developed technique in monitoring uncertain HVAC systems due to the high diagnosis capabilities of the interval feature-based support vector machines and k-nearest neighbors and their ability to distinguish between the different operating modes of the HVAC system.

【 授权许可】

Unknown