Here,a nonhydrostatic alternative scheme(NAS)is proposed for the grey zone where the nonhydrostatic impact on the atmosphere is evident but not large enough to justify the necessity to include an implicit nonhydrostat...Here,a nonhydrostatic alternative scheme(NAS)is proposed for the grey zone where the nonhydrostatic impact on the atmosphere is evident but not large enough to justify the necessity to include an implicit nonhydrostatic solver in an atmospheric dynamical core.The NAS is designed to replace this solver,which can be incorporated into any hydrostatic models so that existing well-developed hydrostatic models can effectively serve for a longer time.Recent advances in machine learning(ML)provide a potential tool for capturing the main complicated nonlinear-nonhydrostatic relationship.In this study,an ML approach called a neural network(NN)was adopted to select leading input features and develop the NAS.The NNs were trained and evaluated with 12-day simulation results of dry baroclinic-wave tests by the Weather Research and Forecasting(WRF)model.The forward time difference of the nonhydrostatic tendency was used as the target variable,and the five selected features were the nonhydrostatic tendency at the last time step,and four hydrostatic variables at the current step including geopotential height,pressure in two different forms,and potential temperature,respectively.Finally,a practical NAS was developed with these features and trained layer by layer at a 20-km horizontal resolution,which can accurately reproduce the temporal variation and vertical distribution of the nonhydrostatic tendency.Corrected by the NN-based NAS,the improved hydrostatic solver at different horizontal resolutions can run stably for at least one month and effectively reduce most of the nonhydrostatic errors in terms of system bias,anomaly root-mean-square error,and the error of the wave spatial pattern,which proves the feasibility and superiority of this scheme.展开更多
By using alternating current plasma arc welding,the influences were studied of such parameters as welding curent,arc voltage,welding speed,wire feed rate,and magnitude of ion gas flow on front melting width,wdle rei...By using alternating current plasma arc welding,the influences were studied of such parameters as welding curent,arc voltage,welding speed,wire feed rate,and magnitude of ion gas flow on front melting width,wdle reinforcement,and back melting width of LF6 aluminum alloy.Model of the formation of welding seam in alternating current plasma arc welding of aluminum was set up with the method of artificial neural neural network - BP algorithm. Qyakuty of formation was consequently predicted and evaluated.The experimental result shows that,compared with other modeling methods,artificial network model can be used to more accurately predict formation of weld,and to guide the production practice.展开更多
温控负荷(thermostatically controlled loads,TCLs)集群作为一种灵活的可调度资源,已成为促进电网经济运行和帮助电网恢复稳定的有力手段之一。然而,由于温控负荷单体功率小、位置分散且参数各异,给调度带来了困难。为了灵活利用数量...温控负荷(thermostatically controlled loads,TCLs)集群作为一种灵活的可调度资源,已成为促进电网经济运行和帮助电网恢复稳定的有力手段之一。然而,由于温控负荷单体功率小、位置分散且参数各异,给调度带来了困难。为了灵活利用数量庞大的负荷侧资源进行负荷跟随控制,该文建立温控负荷的虚拟电池模型和负荷集群的聚合模型,并提出基于双层分布式通信网络的控制策略。上层利用分布式交替方向乘子法(alternating direction method of multipliers,ADMM)来解决不同负荷聚合器的最佳跟随功率问题,以确保跟随效益最优;下层提出基于快速分布式平均一致性算法的深度神经网络(deep neural networks,DNN)的方法,使得聚合器内部的所有温控负荷以相等的虚拟电池荷电状态(state of charge,SoC)快速共享上层得到的跟随功率,并有效减少了通信数据量。不同时间尺度的算例验证提出的控制策略能够实现快速的负荷跟随,并保证用户侧的效益。展开更多
基金supported by the National Science Foundation of China(Grant No.42230606)。
文摘Here,a nonhydrostatic alternative scheme(NAS)is proposed for the grey zone where the nonhydrostatic impact on the atmosphere is evident but not large enough to justify the necessity to include an implicit nonhydrostatic solver in an atmospheric dynamical core.The NAS is designed to replace this solver,which can be incorporated into any hydrostatic models so that existing well-developed hydrostatic models can effectively serve for a longer time.Recent advances in machine learning(ML)provide a potential tool for capturing the main complicated nonlinear-nonhydrostatic relationship.In this study,an ML approach called a neural network(NN)was adopted to select leading input features and develop the NAS.The NNs were trained and evaluated with 12-day simulation results of dry baroclinic-wave tests by the Weather Research and Forecasting(WRF)model.The forward time difference of the nonhydrostatic tendency was used as the target variable,and the five selected features were the nonhydrostatic tendency at the last time step,and four hydrostatic variables at the current step including geopotential height,pressure in two different forms,and potential temperature,respectively.Finally,a practical NAS was developed with these features and trained layer by layer at a 20-km horizontal resolution,which can accurately reproduce the temporal variation and vertical distribution of the nonhydrostatic tendency.Corrected by the NN-based NAS,the improved hydrostatic solver at different horizontal resolutions can run stably for at least one month and effectively reduce most of the nonhydrostatic errors in terms of system bias,anomaly root-mean-square error,and the error of the wave spatial pattern,which proves the feasibility and superiority of this scheme.
文摘By using alternating current plasma arc welding,the influences were studied of such parameters as welding curent,arc voltage,welding speed,wire feed rate,and magnitude of ion gas flow on front melting width,wdle reinforcement,and back melting width of LF6 aluminum alloy.Model of the formation of welding seam in alternating current plasma arc welding of aluminum was set up with the method of artificial neural neural network - BP algorithm. Qyakuty of formation was consequently predicted and evaluated.The experimental result shows that,compared with other modeling methods,artificial network model can be used to more accurately predict formation of weld,and to guide the production practice.
文摘温控负荷(thermostatically controlled loads,TCLs)集群作为一种灵活的可调度资源,已成为促进电网经济运行和帮助电网恢复稳定的有力手段之一。然而,由于温控负荷单体功率小、位置分散且参数各异,给调度带来了困难。为了灵活利用数量庞大的负荷侧资源进行负荷跟随控制,该文建立温控负荷的虚拟电池模型和负荷集群的聚合模型,并提出基于双层分布式通信网络的控制策略。上层利用分布式交替方向乘子法(alternating direction method of multipliers,ADMM)来解决不同负荷聚合器的最佳跟随功率问题,以确保跟随效益最优;下层提出基于快速分布式平均一致性算法的深度神经网络(deep neural networks,DNN)的方法,使得聚合器内部的所有温控负荷以相等的虚拟电池荷电状态(state of charge,SoC)快速共享上层得到的跟随功率,并有效减少了通信数据量。不同时间尺度的算例验证提出的控制策略能够实现快速的负荷跟随,并保证用户侧的效益。
