Two building factors-a longer thermal lag of more than one hour for building envelops and a lag of indoor radiation to convert into cooling load-have impact on the instantaneous heat input and instantaneous cooling lo...Two building factors-a longer thermal lag of more than one hour for building envelops and a lag of indoor radiation to convert into cooling load-have impact on the instantaneous heat input and instantaneous cooling load.So the two factors should be taken into account when selecting the weather parameters for air-conditioning system design.This paper developed a new statistic method for the rational selection of coincident solar irradiance,dry-bulb and wet-bulb temperatures.The method was applied to historic weather records of 25 years in Hong Kong to generate coincident design weather data.And the results show that traditional design solar irradiance,dry-bulb and wet-bulb temperatures may be significantly overestimated in many conditions,and the design weather data for the three different constructions is not kept constant.展开更多
Recent studies show that artificial intelligence(AI),such as machine learning and deep learning,models can be adopted and have advantages in fault detection and diagnosis for building energy systems.This paper aims to...Recent studies show that artificial intelligence(AI),such as machine learning and deep learning,models can be adopted and have advantages in fault detection and diagnosis for building energy systems.This paper aims to conduct a comprehensive and systematic literature review on fault detection and diagnosis(FDD)methods for heating,ventilation,and air conditioning(HVAC)systems.This review covers the period from 2013 to 2023 to identify and analyze the existing research in this field.Our work concentrates explicitly on synthesizing AI-based FDD techniques,particularly summarizing these methods and offering a comprehensive classification.First,we discuss the challenges while developing FDD methods for HVAC systems.Next,we classify AI-based FDD methods into three categories:those based on traditional machine learning,deep learning,and hybrid AI models.Additionally,we also examine physical model-based methods to compare them with AI-based methods.The analysis concludes that AI-based HVAC FDD,despite its higher accuracy and reduced reliance on expert knowledge,has garnered considerable research interest compared to physics-based methods.However,it still encounters difficulties in dynamic and time-varying environments and achieving FDD resolution.Addressing these challenges is essential to facilitate the widespread adoption of AI-based FDD in HVAC.展开更多
Space cooling is an important building energy end-use that was found in recent years to be significantly impacted by occupant behaviours.However,the majority of previous studies ignored the interplay between the opera...Space cooling is an important building energy end-use that was found in recent years to be significantly impacted by occupant behaviours.However,the majority of previous studies ignored the interplay between the operation of windows and air conditioners(ACs)on cooling load,particularly in building energy modelling.In addition,studies on the analysis of cooling load characteristics regarding high-rise buildings are insufficient.The vertical effect of high-rise buildings on cooling load remains vague.This study thus aims to examine how window and AC operation behaviours impact the cooling load of high-rise buildings in an urban context demonstrated by a real-life typical 40-floor residential building in Hong Kong.This study investigates window and AC operation behaviours jointly and examines the vertical effect on cooling load by using agent-based building energy modelling(BEM)techniques and initiating stochastic and diverse behaviour modes.A carefully designed questionnaire survey was conducted to help build behaviour modes and validate energy models.Ninety building energy models were established integrating meteorological parameters generated by the computational fluid dynamics(CFD)programme for ten typical floors and nine combinations of window and AC behaviour modes.The results show that comfort-based AC modes and schedule-based window modes yielded the lowest cooling load.Considering the combined effect of AC and window uses,the maximum difference in cooling loads could be 26.8%.Behaviour modes and building height induce up to 32.4%differences in cooling loads.Besides,a deviation between the behaviour modes and height on the cooling load was found.The findings will help develop a thorough energy model inferring occupants’window and AC behaviour modes along with the building height in high-rise residential buildings.The findings indicate that the interaction impact of window and AC behaviour modes and height should be jointly considered in future high-rise building energy modelling,building energy standards,and policymaking.展开更多
文摘Two building factors-a longer thermal lag of more than one hour for building envelops and a lag of indoor radiation to convert into cooling load-have impact on the instantaneous heat input and instantaneous cooling load.So the two factors should be taken into account when selecting the weather parameters for air-conditioning system design.This paper developed a new statistic method for the rational selection of coincident solar irradiance,dry-bulb and wet-bulb temperatures.The method was applied to historic weather records of 25 years in Hong Kong to generate coincident design weather data.And the results show that traditional design solar irradiance,dry-bulb and wet-bulb temperatures may be significantly overestimated in many conditions,and the design weather data for the three different constructions is not kept constant.
文摘Recent studies show that artificial intelligence(AI),such as machine learning and deep learning,models can be adopted and have advantages in fault detection and diagnosis for building energy systems.This paper aims to conduct a comprehensive and systematic literature review on fault detection and diagnosis(FDD)methods for heating,ventilation,and air conditioning(HVAC)systems.This review covers the period from 2013 to 2023 to identify and analyze the existing research in this field.Our work concentrates explicitly on synthesizing AI-based FDD techniques,particularly summarizing these methods and offering a comprehensive classification.First,we discuss the challenges while developing FDD methods for HVAC systems.Next,we classify AI-based FDD methods into three categories:those based on traditional machine learning,deep learning,and hybrid AI models.Additionally,we also examine physical model-based methods to compare them with AI-based methods.The analysis concludes that AI-based HVAC FDD,despite its higher accuracy and reduced reliance on expert knowledge,has garnered considerable research interest compared to physics-based methods.However,it still encounters difficulties in dynamic and time-varying environments and achieving FDD resolution.Addressing these challenges is essential to facilitate the widespread adoption of AI-based FDD in HVAC.
基金supported by grants from the General Research Fund of the Hong Kong Research Grants Council[No.17203219]the Collaborative Research Fund of the Hong Kong Research Grants Council[No.C7047-20GF].
文摘Space cooling is an important building energy end-use that was found in recent years to be significantly impacted by occupant behaviours.However,the majority of previous studies ignored the interplay between the operation of windows and air conditioners(ACs)on cooling load,particularly in building energy modelling.In addition,studies on the analysis of cooling load characteristics regarding high-rise buildings are insufficient.The vertical effect of high-rise buildings on cooling load remains vague.This study thus aims to examine how window and AC operation behaviours impact the cooling load of high-rise buildings in an urban context demonstrated by a real-life typical 40-floor residential building in Hong Kong.This study investigates window and AC operation behaviours jointly and examines the vertical effect on cooling load by using agent-based building energy modelling(BEM)techniques and initiating stochastic and diverse behaviour modes.A carefully designed questionnaire survey was conducted to help build behaviour modes and validate energy models.Ninety building energy models were established integrating meteorological parameters generated by the computational fluid dynamics(CFD)programme for ten typical floors and nine combinations of window and AC behaviour modes.The results show that comfort-based AC modes and schedule-based window modes yielded the lowest cooling load.Considering the combined effect of AC and window uses,the maximum difference in cooling loads could be 26.8%.Behaviour modes and building height induce up to 32.4%differences in cooling loads.Besides,a deviation between the behaviour modes and height on the cooling load was found.The findings will help develop a thorough energy model inferring occupants’window and AC behaviour modes along with the building height in high-rise residential buildings.The findings indicate that the interaction impact of window and AC behaviour modes and height should be jointly considered in future high-rise building energy modelling,building energy standards,and policymaking.
