Heating,ventilation and air-conditioning(HVAC)accounts for around 40%of the total building energy consumption.It has therefore become a major target for reductions,in terms of both energy usage and CO2 emissions.In th...Heating,ventilation and air-conditioning(HVAC)accounts for around 40%of the total building energy consumption.It has therefore become a major target for reductions,in terms of both energy usage and CO2 emissions.In the light of progress in building intelligence and energy technologies,traditional methods for HVAC optimization,control,and fault diagnosis will struggle to meet essential requirements such as energy efficiency,occupancy comfort and reliable fault detection.Machine learning and data science have great potential in this regard,particularly with developments in information technology and sensor equipment,providing access to large volumes of high-quality data.There remains,however,a number of challenges before machine learning can gain widespread adoption in industry.This review summarizes the recent literature on machine learning for HVAC system optimization,control and fault detection.Unlike other reviews,we provide a comprehensive coverage of the applications,including the factors considered.A brief overview of machine learning and its applications to HVAC is provided,after which we critically appraise the recent literature on control,optimization and fault diagnosis and detection.Finally,we provide a comprehensive discussion on the limitations of current research and suggest future research directions.展开更多
Although the popular multi-fidelity surrogate models,stochastic collocation and nonlinear autoregression have been applied successfully to multiple benchmark problems in different areas of science and engineering,they...Although the popular multi-fidelity surrogate models,stochastic collocation and nonlinear autoregression have been applied successfully to multiple benchmark problems in different areas of science and engineering,they have certain limitations.We propose a uniform Bayesian framework that connects these two methods allowing us to combine the strengths of both.To this end,we introduce Greedy-NAR,a nonlinear Bayesian autoregressive model that can handle complex between-fidelity correlations and involves a sequential construction that allows for significant improvements in performance given a limited computational budget.The proposed enhanced nonlinear autoregressive method is applied to three benchmark problems that are typical of energy applications,namely molecular dynamics and computational fluid dynamics.The results indicate an increase in both prediction stability and accuracy when compared to those of the standard multi-fidelity autoregression implementations.The results also reveal the advantages over the stochastic collocation approach in terms of accuracy and computational cost.Generally speaking,the proposed enhancement provides a straightforward and easily implemented approach for boosting the accuracy and efficiency of concatenated structure multi-fidelity simulation methods,e.g.,the nonlinear autoregressive model,with a negligible additional computational cost.展开更多
基金supported by the Creative Research Groups of the National Natural Science Foundation of China(No.52021004).
文摘Heating,ventilation and air-conditioning(HVAC)accounts for around 40%of the total building energy consumption.It has therefore become a major target for reductions,in terms of both energy usage and CO2 emissions.In the light of progress in building intelligence and energy technologies,traditional methods for HVAC optimization,control,and fault diagnosis will struggle to meet essential requirements such as energy efficiency,occupancy comfort and reliable fault detection.Machine learning and data science have great potential in this regard,particularly with developments in information technology and sensor equipment,providing access to large volumes of high-quality data.There remains,however,a number of challenges before machine learning can gain widespread adoption in industry.This review summarizes the recent literature on machine learning for HVAC system optimization,control and fault detection.Unlike other reviews,we provide a comprehensive coverage of the applications,including the factors considered.A brief overview of machine learning and its applications to HVAC is provided,after which we critically appraise the recent literature on control,optimization and fault diagnosis and detection.Finally,we provide a comprehensive discussion on the limitations of current research and suggest future research directions.
基金This work has been supported by DARPA TRADES Award HR0011-17-2-0016.
文摘Although the popular multi-fidelity surrogate models,stochastic collocation and nonlinear autoregression have been applied successfully to multiple benchmark problems in different areas of science and engineering,they have certain limitations.We propose a uniform Bayesian framework that connects these two methods allowing us to combine the strengths of both.To this end,we introduce Greedy-NAR,a nonlinear Bayesian autoregressive model that can handle complex between-fidelity correlations and involves a sequential construction that allows for significant improvements in performance given a limited computational budget.The proposed enhanced nonlinear autoregressive method is applied to three benchmark problems that are typical of energy applications,namely molecular dynamics and computational fluid dynamics.The results indicate an increase in both prediction stability and accuracy when compared to those of the standard multi-fidelity autoregression implementations.The results also reveal the advantages over the stochastic collocation approach in terms of accuracy and computational cost.Generally speaking,the proposed enhancement provides a straightforward and easily implemented approach for boosting the accuracy and efficiency of concatenated structure multi-fidelity simulation methods,e.g.,the nonlinear autoregressive model,with a negligible additional computational cost.
