Multivariate Features Extraction and Effective Decision Making Using Machine Learning Approaches

Abstract

Fault Detection and Isolation (FDI) in Heating, Ventilation, and Air Conditioning (HVAC) systems is an important approach to guarantee the human safety of these systems. Therefore, the implementation of a FDI framework is required to reduce the energy needs for buildings and improving indoor environment quality. The main goal of this paper is to merge the benefits of multiscale representation, Principal Component Analysis (PCA), and Machine Learning (ML) classifiers to improve the efficiency of the detection and isolation of Air Conditioning (AC) systems. First, the multivariate statistical features extraction and selection is achieved using the PCA method. Then, the multiscale representation is applied to separate feature from noise and approximately decorrelate autocorrelation between available measurements. Third, the extracted and selected features are introduced to several machine learning classifiers for fault classification purposes. The effectiveness and higher classification accuracy of the developed Multiscale PCA (MSPCA)-based ML technique is demonstrated using two examples: synthetic data and simulated data extracted from Air Conditioning systems.

A Review of Data-Driven Approaches and Techniques for Fault Detection and Diagnosis in HVAC Systems

“…Aguilar et al [ 56 ] developed an autonomous cycle of data analysis (ACODAT) that uses Random Forests (RF) and linear regression for a binary classification task to detect deviations in the start-up process, followed by an Multi-Layer Perceptron (MLP) and RF model for behavior prediction. Support Vector Machine-based Multiscale Principal Component Analysis (SVM-MSPCA) was addressed in [ 91 ], where the MPSCA technique was used for feature extraction purposes and SVM was applied for fault diagnosis. In addition, various Bayes-based algorithms have been mentioned as successfully applied in the selected literature: Bayesian classifier [ 90 , 92 ], diagnostic Bayesian network [ 86 , 94 ], Bayesian inference with Markov Chain Monte Carlo [ 85 ], and Naive Bayes [ 90 ] with combination of decision trees (DTs) and RF [ 55 ].…”

“…According to the work reviewed, it is common to use physics-based models to generate synthetic data (both faulty and healthy data), followed by data-driven modeling, i.e., supervised learning of fault prediction models [ 80 , 81 , 87 , 88 , 91 , 92 , 93 , 102 ]. Simple physical models were used by Chintala et al [ 104 ] where the Kalman filter in EnergyPlus was tested using only thermostat and outdoor temperature to perform FDD of equipment deterioration.…”

An improved weighted principal component analysis integrated with TOPSIS approach for global financial development ranking problem of Middle East countries

“…In feature selection approaches, the redundant features (criteria) are recognized and removed from the initial set of features and the remaining features are used for representing the required information (the approaches, e.g., References 24–26 are of this type). On the other hand, feature extraction approaches transform original data into a new lower‐dimensional space by projecting (the approaches, e.g., Reference 27 are of this type). The feature selection/extraction approaches are divided into supervised and unsupervised types.…”

PCA mix‐based Hotelling's T2multivariate control charts for intrusion detection system

“…For instance, Gharsellaoui et al. [38] used multi‐scale principal component analysis (MSPCA) to obtain higher classification accuracy.…”