Browsing by Author "Movahed, Paria"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    A bi-level data-driven framework for fault-detection and diagnosis of HVAC systems
    (Elsevier, 2023-06) Movahed, Paria; Taheri, Saman; Razban, Ali; Mechanical and Energy Engineering, Purdue School of Engineering and Technology
    Long-term operation of heating, ventilation, and air conditioning (HVAC) systems will eventually lead to a range of HVAC system failures, resulting in excessive energy consumption and maintenance costs. To avoid HVAC malfunctioning, fault detection diagnostic (FDD) is utilized as a common practice. Machine learning methods have lately received considerable interest for FDD analysis of 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 has also led to heavily biased classification algorithms within the literature. Moreover, the focus of previous literature has been on increasing the accuracy of the models which leads to a high number of false positives (misleading alarms) in the system. In order 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 (AHUs) and rooftop units (RTUs) 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. By proposing this framework, three persistent challenges are addressed: (I) minimizing false positives; (II) accounting for data imbalance; and (III) normal condition monitoring of equipment.
  • Thumbnail Image
    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 Technology
    Machine 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.
  • Thumbnail Image
    Item
    Enhancing Energy Management System using Internet-of-things Sensors and Energy Simulation -A Case Study of Industrial Ventilation
    (Taylor & Francis, 2023-01) Wu, Da-Chun; Movahed, Paria; Razban, Ali; Chen, Jie; Mechanical and Energy Engineering, Purdue School of Engineering and Technology
    There is a need for energy conservation in order to achieve the 2030 Sustainable Development Goals. Many studies have demonstrated that delivering real-time assessment and energy saving goals are some of the most effective practices to reduce energy consumption and can be achieved by utilizing energy management. However, there remains a sizable gap in the development of the energy management and energy-efficiency evaluation for complicated manufacturing processes. With the current development of new technologies such as Internet of Things, big-data analytics, and machine learning, improvements can be made to further enhance the effectiveness of the energy management system. In this study, a real-time monitoring system that utilizes IoT sensors, cloud-based big data, and grey-box modeling is proposed. This paper describes the ongoing study of using the proposed energy management system in an electroplating manufacturer to reduce its ventilation energy consumption.