暖通空调(heating,ventilation,and air conditioning,HVAC)系统是目前营造健康、舒适封闭/半封闭空间环境的重要手段,但现有HVAC系统不仅能耗高,而且容易引起人体健康问题,比如病态建筑综合征、建筑相关疾病、传染性疾病交叉感染等.上...暖通空调(heating,ventilation,and air conditioning,HVAC)系统是目前营造健康、舒适封闭/半封闭空间环境的重要手段,但现有HVAC系统不仅能耗高,而且容易引起人体健康问题,比如病态建筑综合征、建筑相关疾病、传染性疾病交叉感染等.上述现象进一步说明由HVAC系统末端形成的室内气流组织(基于传统方法)仍不够完美,存在一定的盲区与不足.为了解决传统HVAC系统末端在设计与使用过程中存在的问题,逆向设计方法应运而生.与传统方法区别最大的是,逆向设计方法可以在每个设计循环确定最优的方向向量,而传统设计方法只能不断试错.为进一步阐明两类方法的差异并促使逆向设计方法不断改进,本文首先阐述了室内环境营造所面临/需要解决的科学问题;其次,对气流组织设计方法的分类及其基本原理进行了详细介绍;然后,通过真实的案例结果展示了两类方法的设计效果.虽然逆向设计方法在室内环境营造领域已取得了较大的进展,但目前的逆向设计方法仍需要理论推演、程序开发和数值求解等过程,在一定程度上阻碍了其推广应用.最后,本文讨论了室内环境营造领域未来可能的发展方向.比如,随着人因工程学、逆向设计方法、数字化设计方法、智能控制等领域的快速发展,室内环境设计与营造将趋向于多样化、智能化、智慧化.展开更多
1 Introduction The main idea of recommender system is how to learn accurate users’embeddings from behavior data[1].Each dimension of users’embeddings can reflect the interests of users in different potential aspects...1 Introduction The main idea of recommender system is how to learn accurate users’embeddings from behavior data[1].Each dimension of users’embeddings can reflect the interests of users in different potential aspects.In real-world scenarios,users’interests are drifting over time,which brings a challenge to learn accurate dynamic users’embeddings.Recently,various time-aware recommendation methods have been proposed to tackle this problem by modeling the evolution process of users’interests[2−4].However,they usually assume that users’embeddings drift with the same range on all dimensions.In practice,users’embeddings should change diversely on different dimensions over time.Specifically,for the rapidly changing interests of the users,the corresponding dimensions should change significantly.On the contrary,the dimensions representing stable interests may change slightly.展开更多
Compared with traditional convection air conditioning,the radiant cooling(RC)system has higher energy-saving potential and better comfort.At present,the particle swarm optimization(PSO)algorithm is one of the most adv...Compared with traditional convection air conditioning,the radiant cooling(RC)system has higher energy-saving potential and better comfort.At present,the particle swarm optimization(PSO)algorithm is one of the most advanced methods to optimize the design of indoor radiant terminals.However,this method requires to discretize the design domain in advance.If the geometric division is rough,the accuracy of the optimized results will be too low.To improve the accuracy of the calculation results,the geometric division needs to be refined,but it will greatly increase the calculation load.For each new geometric model,users need to determine a reasonable geometric division every time,which is very time consuming.To solve that problem,this investigation proposed a parameterized level set method(PLSM)to inversely design the area,shape,and locations of the radiant terminal.It not only does not need to discretize the design domain in advance,but also can realize the continuous topological change of the radiant terminal region.The results show that the PLSM can realize the continuous topological transformation of geometric shapes,and the final result of the average absolute value of PMV(∣PMV∣avg)around the occupants achieved 0.066.To enhance the practical application of the optimized results,K-means cluster analysis is used to regularize the shape of the radiation terminal region.The corresponding average∣PMV∣around the occupants is 0.102,which is also within an acceptable range.All in all,PLSM can be used to inversely design the RC systems,which provides an effective design method for realizing accurate control of the indoor environment using the RC systems.展开更多
文摘暖通空调(heating,ventilation,and air conditioning,HVAC)系统是目前营造健康、舒适封闭/半封闭空间环境的重要手段,但现有HVAC系统不仅能耗高,而且容易引起人体健康问题,比如病态建筑综合征、建筑相关疾病、传染性疾病交叉感染等.上述现象进一步说明由HVAC系统末端形成的室内气流组织(基于传统方法)仍不够完美,存在一定的盲区与不足.为了解决传统HVAC系统末端在设计与使用过程中存在的问题,逆向设计方法应运而生.与传统方法区别最大的是,逆向设计方法可以在每个设计循环确定最优的方向向量,而传统设计方法只能不断试错.为进一步阐明两类方法的差异并促使逆向设计方法不断改进,本文首先阐述了室内环境营造所面临/需要解决的科学问题;其次,对气流组织设计方法的分类及其基本原理进行了详细介绍;然后,通过真实的案例结果展示了两类方法的设计效果.虽然逆向设计方法在室内环境营造领域已取得了较大的进展,但目前的逆向设计方法仍需要理论推演、程序开发和数值求解等过程,在一定程度上阻碍了其推广应用.最后,本文讨论了室内环境营造领域未来可能的发展方向.比如,随着人因工程学、逆向设计方法、数字化设计方法、智能控制等领域的快速发展,室内环境设计与营造将趋向于多样化、智能化、智慧化.
基金This work was supported by the National Natural Science Foundation of China(Grant Nos.U21A20473,61906111,and 72171137)the Projects of Key Research and Development Plan of Shanxi Province(201903D121162)the 1331 Engineering Project of Shanxi Province.
文摘1 Introduction The main idea of recommender system is how to learn accurate users’embeddings from behavior data[1].Each dimension of users’embeddings can reflect the interests of users in different potential aspects.In real-world scenarios,users’interests are drifting over time,which brings a challenge to learn accurate dynamic users’embeddings.Recently,various time-aware recommendation methods have been proposed to tackle this problem by modeling the evolution process of users’interests[2−4].However,they usually assume that users’embeddings drift with the same range on all dimensions.In practice,users’embeddings should change diversely on different dimensions over time.Specifically,for the rapidly changing interests of the users,the corresponding dimensions should change significantly.On the contrary,the dimensions representing stable interests may change slightly.
基金supported by the National Natural Science Foundation of China(NSFC)through Grant No.52208098by the China Postdoctoral Science Foundation through Grant No.2022M710689by Jiangsu Planned Projects for Postdoctoral Research Funds through Grant No.2021K069A.
文摘Compared with traditional convection air conditioning,the radiant cooling(RC)system has higher energy-saving potential and better comfort.At present,the particle swarm optimization(PSO)algorithm is one of the most advanced methods to optimize the design of indoor radiant terminals.However,this method requires to discretize the design domain in advance.If the geometric division is rough,the accuracy of the optimized results will be too low.To improve the accuracy of the calculation results,the geometric division needs to be refined,but it will greatly increase the calculation load.For each new geometric model,users need to determine a reasonable geometric division every time,which is very time consuming.To solve that problem,this investigation proposed a parameterized level set method(PLSM)to inversely design the area,shape,and locations of the radiant terminal.It not only does not need to discretize the design domain in advance,but also can realize the continuous topological change of the radiant terminal region.The results show that the PLSM can realize the continuous topological transformation of geometric shapes,and the final result of the average absolute value of PMV(∣PMV∣avg)around the occupants achieved 0.066.To enhance the practical application of the optimized results,K-means cluster analysis is used to regularize the shape of the radiation terminal region.The corresponding average∣PMV∣around the occupants is 0.102,which is also within an acceptable range.All in all,PLSM can be used to inversely design the RC systems,which provides an effective design method for realizing accurate control of the indoor environment using the RC systems.
