专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20210197005A1 Stable basin-shaped trampoline 有权
公开(公告)号：US20210197005A1
公开(公告)日：2021-07-01
申请号：US17037996
申请日：2020-09-30
申请人： Siqi Wang
发明人： Siqi Wang
IPC分类号： A63B5/11
摘要： The present invention discloses a stable basin-shaped trampoline, which includes a frame, multiple resiliently flexible rods with lower ends and top ends respectively, and a bouncing mat; the lower end of each rod is inserted into the frame, and the bouncing mat is bridged arranged above the top ends of the rods; the outer diameter of the bouncing mat is less than that of the frame, the frame, the resiliently flexible rods and the mat encloses into an inverted basin-shaped structure with a relatively larger lower part and a small upper part; or, the outer diameter of the bouncing mat is larger than that of the frame, the frame, the resiliently flexible rods and the bouncing mat encloses into a basin-shaped structure with a large upper part and a small lower part. The basin-shaped structure increases the stability of the trampoline and makes the trampoline not easy to flip.

2. 发明申请

US20220036392A1 Deep Reinforcement Learning Based Real-time scheduling of Energy Storage System (ESS) in Commercial Campus 有权
公开(公告)号：US20220036392A1
公开(公告)日：2022-02-03
申请号：US17102644
申请日：2020-11-24
申请人： Desong Bian , Xiaohu Zhang , Di Shi , Ruisheng Diao , Siqi Wang , Zheming Liang
发明人： Desong Bian , Xiaohu Zhang , Di Shi , Ruisheng Diao , Siqi Wang , Zheming Liang
IPC分类号： G06Q30/02 , G06Q10/06 , G06K9/62 , G06N3/08 , G06Q50/06
摘要： A system with deep reinforcement learning based control determines optimal actions for major components in a commercial building to minimize operation costs while maximizing comprehensive comfort levels of occupants. An unsupervised deep Q-network method is introduced to handle the energy management problem by evaluating the influence of operation costs on comfort levels considering the environment factors at each time slot. An optimum control decision can be derived that targets both immediate and long-term goals, where exploration and exploitation are considered simultaneously.

3. 发明授权

US11610214B2 Deep reinforcement learning based real-time scheduling of Energy Storage System (ESS) in commercial campus 有权
公开(公告)号：US11610214B2
公开(公告)日：2023-03-21
申请号：US17102644
申请日：2020-11-24
申请人： Desong Bian , Xiaohu Zhang , Di Shi , Ruisheng Diao , Siqi Wang , Zheming Liang
发明人： Desong Bian , Xiaohu Zhang , Di Shi , Ruisheng Diao , Siqi Wang , Zheming Liang
IPC分类号： G06Q30/02 , G06Q10/06 , G06K9/62 , G06Q50/06 , G06N3/08 , B60L58/12 , G06Q30/0201 , G06Q10/0631
摘要： A system with deep reinforcement learning based control determines optimal actions for major components in a commercial building to minimize operation costs while maximizing comprehensive comfort levels of occupants. An unsupervised deep Q-network method is introduced to handle the energy management problem by evaluating the influence of operation costs on comfort levels considering the environment factors at each time slot. An optimum control decision can be derived that targets both immediate and long-term goals, where exploration and exploitation are considered simultaneously.

4. 发明授权

US11336092B2 Multi-objective real-time power flow control method using soft actor-critic 有权
公开(公告)号：US11336092B2
公开(公告)日：2022-05-17
申请号：US17092478
申请日：2020-11-09
申请人： Ruisheng Diao , Di Shi , Bei Zhang , Siqi Wang , Haifeng Li , Chunlei Xu , Desong Bian , Jiajun Duan , Haiwei Wu
发明人： Ruisheng Diao , Di Shi , Bei Zhang , Siqi Wang , Haifeng Li , Chunlei Xu , Desong Bian , Jiajun Duan , Haiwei Wu
IPC分类号： H02J3/00 , G05B13/04 , G05B13/02
摘要： Systems and methods are disclosed for control voltage profiles, line flows and transmission losses of a power grid by forming an autonomous multi-objective control model with one or more neural networks as a Deep Reinforcement Learning (DRL) agent; training the DRL agent to provide data-driven, real-time and autonomous grid control strategies; and coordinating and optimizing power controllers to regulate voltage profiles, line flows and transmission losses in the power grid with a Markov decision process (MDP) operating with reinforcement learning to control problems in dynamic and stochastic environments.

5. 发明申请

US20210367424A1 Multi-Objective Real-time Power Flow Control Method Using Soft Actor-Critic 有权
公开(公告)号：US20210367424A1
公开(公告)日：2021-11-25
申请号：US17092478
申请日：2020-11-09
申请人： Ruisheng Diao , Di Shi , Bei Zhang , Siqi Wang , Haifeng Li , Chunlei Xu , Desong Bian , Jiajun Duan , Haiwei Wu
发明人： Ruisheng Diao , Di Shi , Bei Zhang , Siqi Wang , Haifeng Li , Chunlei Xu , Desong Bian , Jiajun Duan , Haiwei Wu
IPC分类号： H02J3/00 , G05B13/02 , G05B13/04
摘要： Systems and methods are disclosed for control voltage profiles, line flows and transmission losses of a power grid by forming an autonomous multi-objective control model with one or more neural networks as a Deep Reinforcement Learning (DRL) agent; training the DRL agent to provide data-driven, real-time and autonomous grid control strategies; and coordinating and optimizing power controllers to regulate voltage profiles, line flows and transmission losses in the power grid with a Markov decision process (MDP) operating with reinforcement learning to control problems in dynamic and stochastic environments.

6. 发明授权

US11358017B2 Stable basin-shaped trampoline 有权
公开(公告)号：US11358017B2
公开(公告)日：2022-06-14
申请号：US17037996
申请日：2020-09-30
申请人： Siqi Wang
发明人： Siqi Wang
IPC分类号： A63B5/11 , A63B21/02
摘要： The present invention discloses a stable basin-shaped trampoline, which includes a frame, multiple resiliently flexible rods with lower ends and top ends respectively, and a bouncing mat; the lower end of each rod is inserted into the frame, and the bouncing mat is bridged arranged above the top ends of the rods; the outer diameter of the bouncing mat is less than that of the frame, the frame, the resiliently flexible rods and the mat encloses into an inverted basin-shaped structure with a relatively larger lower part and a small upper part; or, the outer diameter of the bouncing mat is larger than that of the frame, the frame, the resiliently flexible rods and the bouncing mat encloses into a basin-shaped structure with a large upper part and a small lower part. The basin-shaped structure increases the stability of the trampoline and makes the trampoline not easy to flip.

你已经成功收藏专利！

检索式保存成功!

IPRDB