您的检索：
学者姓名：杜胜利
精炼检索结果：
年份
成果类型
收录类型
来源
综合
合作者
语言
清除所有精炼条件
摘要 ：
Local path planning and obstacle avoidance in complex environments are two challenging problems in the research of intelligent robots. In this study, we develop a novel approach grounded in deep distributional reinforcement learning to address these challenges. Within this methodology, agents instantiated by deep neural networks perceive real-time local environmental information through sensor data, addressing inherent stochasticity and local path planning tasks in complex environments. End -to -end training is facilitated via distributional reinforcement learning algorithms and reward functions informed by heuristic knowledge. Optimal actions for path planning are determined through return value distributions. Finally, the simulation results show that the success rate of the proposed distributed algorithm is 98% in a random environment and 94% in a dynamic environment. This proves that the algorithm has better generalization and flexibility than the non -distributed algorithm.
关键词 ：
Local path planning Local path planning Distributional reinforcement learning Distributional reinforcement learning Collision avoidance Collision avoidance
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Du, Shengli , Zhu, Zexing , Wang, Xuefang et al. Real-time local path planning strategy based on deep distributional reinforcement learning [J]. | NEUROCOMPUTING , 2024 , 599 . |
| MLA | Du, Shengli et al. "Real-time local path planning strategy based on deep distributional reinforcement learning" . | NEUROCOMPUTING 599 (2024) . |
| APA | Du, Shengli , Zhu, Zexing , Wang, Xuefang , Han, Honggui , Qiao, Junfei . Real-time local path planning strategy based on deep distributional reinforcement learning . | NEUROCOMPUTING , 2024 , 599 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
The problem of sampled-data H(infinity )dynamic output-feedback control for networked control systems with successive packet losses (SPLs) and stochastic sampling is investigated in this article. The aim of using sampled-data control techniques is to alleviate network congestion. SPLs that occur in the sensor-to-controller (S-C) and controller-to-actuator (C-A) channels are modeled using a packet loss model. Additionally, it is assumed that stochastic sampling follows a Bernoulli distribution. A model is established to capture the stochastic characteristics of both the SPL model and stochastic sampling. This model is crucial as it allows us to determine the probability distribution of the sampling interval between successive update instants, which is essential for stability analysis. An exponential mean-square stability condition for the constructed equivalent discrete-time stochastic system, which also guarantees the prescribed H-infinity performance, is established by incorporating probability theory. The desired controller is designed using a step-by-step synthesis approach, which may offer lower design conservatism compared to some existing methods. Finally, our designed approach using a networked F-404 engine system model is validated and its merits relative to existing results are discussed. The proposed method is finally validated by employing a networked model of the F-404 engine system. Furthermore, the advantages of our method are presented in comparison to previous results.
关键词 ：
Delays Delays H-infinity dynamic output-feedback (DOF) control H-infinity dynamic output-feedback (DOF) control Probability distribution Probability distribution Networked control systems Networked control systems Stochastic systems Stochastic systems successive packet losses (SPLs) successive packet losses (SPLs) stochastic sampling stochastic sampling Stochastic processes Stochastic processes Packet loss Packet loss Bandwidth Bandwidth networked control systems (NCSs) networked control systems (NCSs)
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Sun, Hao-Yuan , Hou, Shuang , Du, Shengli et al. Sampled-Data H∞ Dynamic Output-Feedback Control for NCSs With Successive Packet Losses and Stochastic Sampling [J]. | IEEE TRANSACTIONS ON CYBERNETICS , 2024 , 54 (10) : 6024-6034 . |
| MLA | Sun, Hao-Yuan et al. "Sampled-Data H∞ Dynamic Output-Feedback Control for NCSs With Successive Packet Losses and Stochastic Sampling" . | IEEE TRANSACTIONS ON CYBERNETICS 54 . 10 (2024) : 6024-6034 . |
| APA | Sun, Hao-Yuan , Hou, Shuang , Du, Shengli , Han, Hong-Gui , Qiao, Jun-Fei . Sampled-Data H∞ Dynamic Output-Feedback Control for NCSs With Successive Packet Losses and Stochastic Sampling . | IEEE TRANSACTIONS ON CYBERNETICS , 2024 , 54 (10) , 6024-6034 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明提供了一种MSWI过程CO排放预测方法，该方法首先进行面向约简深度特征和LSTM优化的粒子设计，能够依据建模数据特点自适应确定特征选择阈值范围，其次将采用超一维卷积进行非线性特征提取后的深度特征输入至LSTM以构建预测模型，基于损失函数对卷积层和LSTM超参数进行更新，以模型的泛化性能作为优化算法的适应度函数，最后采用粒子群优化(PSO)算法依据数据特性进行自适应的特征和超参数选择。本发明提供的MSWI过程CO排放预测方法，能够基于约简深度特征和LSTM优化实现MSWI过程中的CO排放预测。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 汤健 , 张润雨 , 夏恒 et al. 一种MSWI过程CO排放预测方法 : CN202310620063.6[P]. | 2023-05-29 . |
| MLA | 汤健 et al. "一种MSWI过程CO排放预测方法" : CN202310620063.6. | 2023-05-29 . |
| APA | 汤健 , 张润雨 , 夏恒 , 杜胜利 , 乔俊飞 . 一种MSWI过程CO排放预测方法 : CN202310620063.6. | 2023-05-29 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明提出了一种基于深度强化学习的溶解氧浓度自适应PID控制方法，实现了污水处理过程中溶解氧DO浓度的精确在线控制；针对污水处理过程中具有不确定性、非线性、强耦合性，控制器参数难以确定，溶解氧DO浓度难以控制的特点，该控制方法将深度强化学习与传统PID控制相结合，通过深度强化学习DRL智能体实现对PID控制器参数的实时动态调整，从而解决了PID控制器应用于溶解氧DO的浓度控制时存在的控制精度不高、自适应能力差等问题；实验结果表明该方法不仅能快速、精准的控制溶解氧DO的浓度以达到精确在线控制的目的，还具有较好的自适应能力，能够在溶解氧DO的浓度期望值发生改变时快速的将溶解氧DO的浓度稳定在新的期望值附近。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 杜胜利 , 陈培锡 , 乔俊飞 . 一种基于深度强化学习的溶解氧浓度自适应PID控制方法 : CN202310427799.1[P]. | 2023-04-20 . |
| MLA | 杜胜利 et al. "一种基于深度强化学习的溶解氧浓度自适应PID控制方法" : CN202310427799.1. | 2023-04-20 . |
| APA | 杜胜利 , 陈培锡 , 乔俊飞 . 一种基于深度强化学习的溶解氧浓度自适应PID控制方法 : CN202310427799.1. | 2023-04-20 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
This article investigates the secure consensus problem of general linear multiagent systems with denial-of-service (DoS) attacks. Owning to the existence of DoS attacks, it is challenging to investigate the event-triggered control of multiagent systems in a fully distributed manner. This article presents a novel dynamic event-triggered mechanism to alleviate the limited communication resources. Moreover, the designed mechanism is fully distributed and scalable owing to the introduction of some adaptive coupling weights. Since the DoS attacks have been considered in the event-triggered rule design, a novel adaptive parameter with an additional exponential term is adopted to deal with DoS attacks. The Lyapunov design also introduces such a term for the subsequent stability analysis. Sufficient conditions guaranteeing the asymptotic consensus of the studied system are developed in light of the controller's parameters, duration, and frequency of the DoS attacks. Strict proof is provided to demonstrate that a secure consensus can be reached effectively under the proposed control mechanism. Furthermore, it is shown that the Zeno behavior can be excluded from the designed triggering mechanism. Finally, simulations on a multiagent system consisting of interconnected unmanned intelligent vehicles are conducted to verify the results.
关键词 ：
multiagent systems multiagent systems event-triggered mechanism event-triggered mechanism fully distributed protocol fully distributed protocol denial-of-service (DoS) attacks denial-of-service (DoS) attacks Consensus Consensus
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Du, Shengli , Sheng, Hong , Ho, Daniel W. C. et al. Secure Consensus of Multiagent Systems With DoS Attacks via Fully Distributed Dynamic Event-Triggered Control [J]. | IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS , 2023 , 53 (10) : 6588-6597 . |
| MLA | Du, Shengli et al. "Secure Consensus of Multiagent Systems With DoS Attacks via Fully Distributed Dynamic Event-Triggered Control" . | IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 53 . 10 (2023) : 6588-6597 . |
| APA | Du, Shengli , Sheng, Hong , Ho, Daniel W. C. , Qiao, Junfei . Secure Consensus of Multiagent Systems With DoS Attacks via Fully Distributed Dynamic Event-Triggered Control . | IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS , 2023 , 53 (10) , 6588-6597 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
This paper investigates the leader-following consensus problem for general linear multiagent systems under a fully distributed manner. To avoid using the global information of the communication network, two node-based adaptive parameters are designed and introduced to the fully distributed event-based control law. Such a protocol is more scalable and flexible for large-scaled and complex networked system, such as microgrids or multiple unmanned vehicles. A novel event-triggered rule is presented, and an internal dynamic variable is introduced in it to further cut down the triggering times and save the communication resources. A well-designed Lyapunov function candidate is constructed to not only ensure the convergence of the close-looped systems but also avoid using the eigenvalue of Laplacian matrix in the dynamic variable. Moreover, it is proved that the designed event-triggered conditions can avoid the Zeno behaviour. Finally, a simulation example based on a group of unmanned intelligent vehicle systems is provided to demonstrate the validity of the designed control method.(c) 2023 The Franklin Institute. Published by Elsevier Inc. All rights reserved.
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Du, Shengli , Sheng, Hong , Sun, Hao-Yuan . A fully distributed event-Triggered control approach to leader-following consensus of multiagent systems [J]. | JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS , 2023 , 360 (17) : 13227-13243 . |
| MLA | Du, Shengli et al. "A fully distributed event-Triggered control approach to leader-following consensus of multiagent systems" . | JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS 360 . 17 (2023) : 13227-13243 . |
| APA | Du, Shengli , Sheng, Hong , Sun, Hao-Yuan . A fully distributed event-Triggered control approach to leader-following consensus of multiagent systems . | JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS , 2023 , 360 (17) , 13227-13243 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明提供了一种基于机理‑数据驱动的城市污水处理脱氮过程的混合建模方法，其特征在于，包括以下具体步骤：S1、首先基于活性污泥一号模型(ASM1)，主要考虑脱氮过程对ASM1模型进行合理简化，建立简化机理模型；S2、基于matlab平台上，采用T-S模糊神经网络对简化机理模型与原模型的出水指标误差建立数据模型，补偿简化机理模型的建模误差；S3、基于已建立的简化机理模型和数据模型，采用并联结构进行融合，建立城市污水处理脱氮过程机理-数据混合模型，最后对该混合模型的出水指标进行了验证，同时与简化机理模型进行建模评价指标对比，验证了混合模型的有效性。本发明提供了一种机理与数据相融合的混合建模方法，建立了城市污水处理脱氮过程机理-数据混合模型，通过机理模型来计算污水处理脱氮过程的生化反应，采用数据模型对机理模型的建模误差进行补偿；结果表明：与单一的简化机理模型相比，混合模型的精度得到了极大的提升，混合模型不仅物理可解释性强，而且更好地利用了数据的因果关系。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 杜胜利 , 赵明明 , 乔俊飞 . 一种基于机理-数据驱动的城市污水处理脱氮过程的混合建模方法 : CN202210381970.5[P]. | 2022-04-12 . |
| MLA | 杜胜利 et al. "一种基于机理-数据驱动的城市污水处理脱氮过程的混合建模方法" : CN202210381970.5. | 2022-04-12 . |
| APA | 杜胜利 , 赵明明 , 乔俊飞 . 一种基于机理-数据驱动的城市污水处理脱氮过程的混合建模方法 : CN202210381970.5. | 2022-04-12 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明提供了一种基于RealSense相机的桌面型双机械臂视觉协同装置，包括底盘装置、肩部底座装置、左右机械臂装置、相机相关装置。所述底盘装置内嵌舵机，输出轴连接肩部底座装置，可实现整个装置在水平面的转动，扩大工作范围；双机械臂的设计以及机械臂末端可根据需求选择执行器，有效提高机械臂的工作效率；所述相机相关装置包括相机支架、头部底座、两个舵机与相机固定架，其中两个舵机为相机提供两个自由度的设计，相机固定架用于固定RealSense相机，具有高开发潜力。本发明具备通用性强、简易方便、仿人设计、成本低等多个优点，对机器人手眼脑配合的相关研究具有重要意义，在装配、医学治疗、服务机器人、科学示教等领域，具有广阔的应用前景。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 杜胜利 , 吉祥 , 胡皓原 et al. 一种基于RealSense相机的桌面型双机械臂视觉协同装置 : CN202211294726.1[P]. | 2022-10-21 . |
| MLA | 杜胜利 et al. "一种基于RealSense相机的桌面型双机械臂视觉协同装置" : CN202211294726.1. | 2022-10-21 . |
| APA | 杜胜利 , 吉祥 , 胡皓原 , 鱼天鸿 , 张宸瑞 , 刘雨婵 . 一种基于RealSense相机的桌面型双机械臂视觉协同装置 : CN202211294726.1. | 2022-10-21 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
This paper is concerned with the event-triggered model predictive control (ETMPC) problem of nitrogen removal process in the wastewater treatment plants. The main objective of this paper is to design an event-triggered control strategy such that the computation burden can be reduced effectively while maintaining the desired system performance. Unlike existing model predictive control (MPC), the controller in the proposed ETMPC takes action when certain event conditions are satisfied, and thus can reduce the communication and computation resource caused by continuous controller update. The triggering condition is designed according to the system output error and the prediction step of the MPC controller, and thus is easy to check. Moreover, a state space model of the studied nitrogen removal process is built, based on which the ETMPC is designed. The controller is developed to maintain the tracking performance of the dissolved oxygen concentration and nitrate nitrogen concentration by adjusting two key variables in the WWTPs. The stability analysis of the closed-loop system under the designed control strategy is conducted by using the Lyapunov stability theory. Some simulations are conducted to verify the effectiveness of the proposed method. Simulation results show that the proposed method can greatly reduce the number of controller update by up to 60% compared with MPC, whereas the ISE only increases by about 0.1, which is acceptable for WWTPs.
关键词 ：
Model predictive control (MPC) Model predictive control (MPC) Event-triggered control Event-triggered control WWTPs WWTPs Subspace identification Subspace identification
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Du, Shengli , Zhang, Qingda , Han, Honggui et al. Event-triggered model predictive control of wastewater treatment plants [J]. | JOURNAL OF WATER PROCESS ENGINEERING , 2022 , 47 . |
| MLA | Du, Shengli et al. "Event-triggered model predictive control of wastewater treatment plants" . | JOURNAL OF WATER PROCESS ENGINEERING 47 (2022) . |
| APA | Du, Shengli , Zhang, Qingda , Han, Honggui , Sun, Haoyuan , Qiao, Junfei . Event-triggered model predictive control of wastewater treatment plants . | JOURNAL OF WATER PROCESS ENGINEERING , 2022 , 47 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Exponential stability analysis of discrete-time nonlinear systems with a time-varying delay is concerned in this article. The main contribution of this article lies in proposing an improved stability analysis method called a delay-mode-based functional method. The improved method is presented by weakening a condition in the Lyapunov-Krasovskii functional method. With the help of the new method, less conservative exponential stability criteria of discrete-time linear systems with a time-varying delay are obtained and two classical examples are given to show that the delay-mode-based functional method is effective.
关键词 ：
discrete-time systems discrete-time systems exponential stability analysis exponential stability analysis time-varying delays time-varying delays
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Li, Xu , Wang, Rui , Du, Shengli et al. An improved exponential stability analysis method for discrete-time systems with a time-varying delay [J]. | INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL , 2021 . |
| MLA | Li, Xu et al. "An improved exponential stability analysis method for discrete-time systems with a time-varying delay" . | INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL (2021) . |
| APA | Li, Xu , Wang, Rui , Du, Shengli , Li, Te . An improved exponential stability analysis method for discrete-time systems with a time-varying delay . | INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL , 2021 . |
| 导入链接 | NoteExpress RIS BibTex |
导出
| 数据： |
选中 到 |
| 格式： |
