- Browse by Author
Browsing by Author "Taheri, Saman"
Now showing 1 - 6 of 6
Results Per Page
Sort Options
Item A Bi-Level Data-Driven Framework for Fault-Detection and Diagnosis of HVAC Systems feature explainability(Elsevier, 2022-07) Movahed, Paria; Taheri, Saman; Razban, Ali; Mechanical Engineering, School of Engineering and TechnologyMachine learning methods have lately received considerable interest for fault detection diagnostic (FDD) analysis of heating, ventilation, and air conditioning (HVAC) systems due to their high detection accuracy. Meanwhile, HVAC malfunctions are regarded as rare occurrences, hence normal operating data samples are much more accessible than data samples in faulty and malfunctioning conditions. The dominating frequency of normal operation in HVAC datasets have also led to heavily biased classification algorithms within the literature. Moreover, the focus of previous literature has been on increasing accuracy of the models while this leads to a high number of false positives (misleading alarms) in the system. To enhance the performance of diagnostic procedures and fill the mentioned gaps, this study proposes a novel data-driven framework. A bi-level machine learning framework is developed for diagnosing faults in air handling units and rooftop units based on principal component analysis (PCA), time series anomaly detection, and random forest (RF). It is shown that PCA can reduce the dataset dimension with one principal component accounting for 95% of data variance. Also, the random forest could classify the faults with 89% precision for single zone AHU, 85% precision for RTU, and 79% for multi-zone AHU.Item Developing a method to calculate leaks in a compressed air line using time series pressure measurements(Elsevier, 2022-07) Jafarian, Alireza; Taheri, Saman; Daniel, Ebin; Razban, Ali; Mechanical Engineering, School of Engineering and TechnologyCompressed air is a powerful source of stored energy and is use in a variety of applications varying from painting to pressing in industrial manufacturing. One of the common problems in this system is air leakage. Air leaks forming within the compressed air piping network, act as continuous consumers and reduce the pressure within the pipes. Therefore, the air compressors will have to work harder to compensate for the losses in the pressure and preventing inefficiently of pneumatic devices. This will all cumulatively impact the manufacturer considerably when it comes to energy consumption and profits. There are multiple methods of air leak detection and accounting. The methods are usually conducted in non-production hours, the time that main air consumption within the piping is air leaks. In this paper, a model that includes both the production and non-production hours when accounting for the leaks is presented. It is observed that there is 50.33% increase in the energy losses, and 82.90% increase in the demand losses that are estimated when the effects of the air leaks are observed continuously and in real time. A real time monitoring system can provide an in-depth understanding of the compressed air system and its efficiency. The main goal of this paper is to find a nonintrusive way to calculate the amount of air as well as energy lost due to these leaks using time series pressure measurements.Item Learning-based CO2 concentration prediction: Application to indoor air quality control using demand-controlled ventilation(Elsevier, 2021-11) Taheri, Saman; Razban, Ali; Mechanical and Energy Engineering, School of Engineering and TechnologyThere have been increasing concerns over the air quality inside buildings as high levels of bio-effluents can cause nausea, dizziness, headaches, and fatigue to the people working in those spaces. First published in 2004 as Standard 62.1, ASHRAE Standard 62.2-2019 requires highly occupied spaces to implement heating, ventilation, and air conditioning (HVAC) that can dilute contaminants produced by occupants. In this regard, occupant-centric ventilation control has been regarded as an effective practice to maintain a satisfactory indoor air quality (IAQ) when dealing with highly variable occupancy environments. However, few established models in current literature and practice consider dynamic occupancy behavior and adaptive IAQ control. To address this gap, a dynamic indoor CO2 model is constructed using machine learning algorithms to forecast CO2 concentrations across a range of forecasting horizons. Herein, we tuned and compared six state-of-the-art learning algorithms—including Support Vector Machine, AdaBoost, Random Forest, Gradient Boosting, Logistic Regression, and Multilayer Perceptron. The algorithms’ performances are validated using CO2 and historical meteorological data collected from a campus classroom with a variable occupancy rate. Simulation results showed that Multilayer Perceptron can strongly predict the volatile CO2 behavior and also outperforms other algorithms in terms of accuracy. Furthermore, a control strategy capable of modeling and detecting dynamic patterns of CO2 level is utilized to modulate the ventilation rate in real-time and also reduce the energy consumption. The proposed controller reduced the HVAC fan’s energy consumption by 51.4% and provided ventilation as needed per the ASHRAE standards.Item A novel probabilistic regression model for electrical peak demand estimate of commercial and manufacturing buildings(Elsevier, 2022-02) Taheri, Saman; Razban, Ali; Mechanical Engineering, School of Engineering and TechnologyDue to the high cost of electricity in commercial and industrial sectors, demand forecast models have gained increasing attention. However, there are two unresolved issues: (1) Models are not adaptable when exposed to previously unknown data (2) The value of regression methods vs. state-of-the-art machine learning models has not been made apparent before. This study’s goal is to develop probabilistic demand estimation models. We propose a probabilistic Bayesian regression framework that can not only estimate future demands with high accuracy but also be updated once new information is available. By applying the proposed algorithm to two real-world case studies (commercial and manufacturing), we show a 40.3% and 30.8% improvement in terms of mean absolute error for the two cases. Moreover, the proposed technique outperforms powerful machine learning approaches, including support vector machine by 10.39%, random forest by 6.17%, and multilayer perceptron by 9.14% in terms of mean absolute percentage error.Item Pandemic-Aware Day-Ahead Demand Forecasting Using Ensemble Learning(IEEE, 2022) Arjomandi-Nezhad, Ali; Ahmadi, Amirhossein; Taheri, Saman; Fotuhi-Firuzabad, Mahmud; Moeini-Aghtaie, Moein; Lehtonen, Matti; Mechanical and Energy Engineering, School of Engineering and TechnologyElectricity demand forecast is necessary for power systems’ operation scheduling and management. However, power consumption is uncertain and depends on several factors. Moreover, since the onset of covid-19, the electricity consumption pattern went through significant changes across the globe, which made the forecasting demand more challenging. This is mainly due to the fact that pandemic-driven restrictions changed people’s lifestyles and work activities. This calls for new forecasting algorithms to more effectively handle these conditions. In this paper, ensemble-based machine learning models are utilized for this task. The lockdown temporal policies are added to the feature set in order to make the model capable of correcting itself in pandemic situations and enhance data quality for the forecasting task. Several ensemble-based machine learning models are examined for the short-term country-level demand prediction model. Besides, the quantile random forest regression is implemented for a probabilistic point of view. For case studies, the models are trained for predicting Germany’s country-level demand. The results indicate that ensemble models, especially boosting and bagging-boosting models, are capable of accurate country-level demand forecast. Besides, the majority of these models are robust against missing the pandemic policy data. However, utilizing the pandemic policy data as features increases the forecasting accuracy during the pandemic situation significantly. Furthermore, the probabilistic quantile regression demonstrated high accuracy for the aforementioned case study.Item Reliability-based energy scheduling of active buildings subject to renewable energy and demand uncertainty(Elsevier, 2022-02-01) Taheri, Saman; Akbari, Amin; Ghahremani, Bahareh; Razban, Ali; Mechanical and Energy Engineering, School of Engineering and TechnologyThe increasing penetration of renewable energy sources (RESs) and the inherent volatility in demand profiles have added another layer of complexity to the management of energy resources in modern active buildings (ABs). Yet, three challenges have been neglected in previous studies: (1) There is no universal systematic method for identifying an AB’s general stochastic model; (2) No research has been conducted on the reliability-based design optimization for ABs’ energy supply; (3) Uncertain sources are not categorized based on their importance in regard to the optimization problem. This article aims to solve these challenges by proposing a probabilistic-based optimization approach for solving the reliability issue of energy supply in buildings with on-site renewable energy sources (RESs), taking into account the uncertainty associated with photovoltaic (PV) production and demand fluctuations. The suggested framework seeks to reduce the overall costs of the system while ensuring high energy supply reliability. The proposed methodology, when applied to a real-world case study, demonstrates a 60% increase in reliability of energy supply as compared to typical deterministic methodologies.