A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Online model-based fault detection and diagnosis strategy for VAV air handling units
Highlights ► An online model-based FDD method is developed for VAV AHUs. ► AHU models with self-tuning parameters are used to detect faults. ► An online adaptive scheme is presented to update fault detection thresholds. ► Three rule-based fault classifiers are developed to diagnose faults in VAV AHUs. ► The FDD method was validated online in real VAV air-conditioning systems.
Abstract An online model-based fault detection and diagnosis (FDD) strategy is presented in this paper to diagnose abrupt faults of variable-air-volume (VAV) air handling units (AHU). The FDD strategy proposed adopts a hybrid approach integrating model-based FDD method and rule-based FDD method. Self-tuning model is used to detect the faults in AHU systems. Model parameters are adjusted by a genetic algorithm-based optimization method to reduce the residual between prediction and measurement. If the residual exceeds the corresponding fault detection threshold, it indicates the occurrence of fault or abnormality in AHU systems. Meanwhile, an online adaptive scheme is proposed to estimate the fault detection threshold, which varies with system operating conditions. Furthermore, three rule-based fault classifiers are developed and utilized to find fault sources. The FDD strategy proposed was tested and validated on real VAV air-conditioning systems involving multiple faults. The validation results show that the FDD strategy proposed can provide an effective tool for detecting and diagnosing the faults of air handling units.
Online model-based fault detection and diagnosis strategy for VAV air handling units
Highlights ► An online model-based FDD method is developed for VAV AHUs. ► AHU models with self-tuning parameters are used to detect faults. ► An online adaptive scheme is presented to update fault detection thresholds. ► Three rule-based fault classifiers are developed to diagnose faults in VAV AHUs. ► The FDD method was validated online in real VAV air-conditioning systems.
Abstract An online model-based fault detection and diagnosis (FDD) strategy is presented in this paper to diagnose abrupt faults of variable-air-volume (VAV) air handling units (AHU). The FDD strategy proposed adopts a hybrid approach integrating model-based FDD method and rule-based FDD method. Self-tuning model is used to detect the faults in AHU systems. Model parameters are adjusted by a genetic algorithm-based optimization method to reduce the residual between prediction and measurement. If the residual exceeds the corresponding fault detection threshold, it indicates the occurrence of fault or abnormality in AHU systems. Meanwhile, an online adaptive scheme is proposed to estimate the fault detection threshold, which varies with system operating conditions. Furthermore, three rule-based fault classifiers are developed and utilized to find fault sources. The FDD strategy proposed was tested and validated on real VAV air-conditioning systems involving multiple faults. The validation results show that the FDD strategy proposed can provide an effective tool for detecting and diagnosing the faults of air handling units.
Online model-based fault detection and diagnosis strategy for VAV air handling units
Wang, Haitao (author) / Chen, Youming (author) / Chan, Cary W.H. (author) / Qin, Jianying (author) / Wang, Jinhua (author)
Energy and Buildings ; 55 ; 252-263
2012-08-15
12 pages
Article (Journal)
Electronic Resource
English
Online model-based fault detection and diagnosis strategy for VAV air handling units
| Online Contents | 2012
Robust model-based fault diagnosis for air handling units
| Elsevier | 2014
Robust model-based fault diagnosis for air handling units
| Online Contents | 2015
Deep-learning-based fault detection and diagnosis of air-handling units
| Elsevier | 2019
A robust fault detection and diagnosis strategy for multiple faults of VAV air handling units
| Online Contents | 2016