检索结果-内蒙古大学图书馆

Optimal control of PVC polymerization process with set values based on td3 algorithm

ISA transactions 2025年

作者： Shuzhi Gao Qing Liu Shiwei Yang Qiang Wang Equipment Reliability Institute Shenyang University of Chemical Technology Shenyang 110142 China. Electronic address: gaoshuzhi@***. College of Information Engineering Shenyang University of Chemical Technology Shenyang 110142 China. Shenyang Institute of Engineering Shenyang 110142 China.

Aiming at the various time frames between the operation computing and the base loop computing of the PVC polymerization process, as well as the difficulty in establishing the nonlinear model of the operation layer, this paper presents a data-based run-level control method combining iterative lifting technique and the td3 algorithm. Aiming at the problem of different time scales of the two-layer structure, the iterative boosting technique is used to boost the cycle of the basic level of circulation to the cycle of the operation layer, and substitute the closed-loop basic loop system into the operational layer model; then the operation layer model is augmented and generalized, and general control objects that use the set values of the cyclic layer as input values, and with the operation index as the output value, are obtained. Based on the synchronized updating of the value function and the control strategy, the online strategy iteration algorithm is implemented using a model-free method based on td3 neural network.

关键词： Data driven PVC aggregation process Run optimization control Setpoint td3 algorithm

来源：评论

学校读者我要写书评

暂无评论

One-to-one Air-combat Maneuver Strategy Based on Improved td3 algorithm

One-to-one Air-combat Maneuver Strategy Based on Improved TD...

引用

Chinese Automation Congress (CAC)

作者： Qiu, Xuyi Yao, Ziyu Tan, Fuwei Zhu, Zhen Lu, Jun-Guo Integrat Technol Key Lab Av Syst Shanghai Peoples R China Northeastern Univ Dept Artificial Intelligence Shenyang Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai Peoples R China

ISBN: (纸本)9781728176871

In this paper, the problem of one-to-one unmanned fighter air-combat autonomous maneuver decision including missile evasion is considered. Firstly, the model of one-to-one unmanned tighter air-combat is established by reducing the 3-dimensional space into the 2-dimensional planes. Considering that Twin Delayed Deep Deterministic policy gradient algorithm (td3) can deal with continuous control problems and has strong robustness, an improved td3 algorithm is presented to realize the air-combat autonomous maneuver decision. To increase training efficiency, a new loss term between recommended action and actor output is proposed in this algorithm. Finally, one-to-one air-combat is simulated on DCS World platform and the effectiveness of this algorithm is verified.

关键词： Deep reinforcement learning td3 algorithm air-combat missile evasion maneuver DCS World

来源：评论

学校读者我要写书评

暂无评论

Research on multi-UAV aggregation task based on GA-td3 algorithm

Research on multi-UAV aggregation task based on GA-TD3 algor...

引用

第43届中国控制会议

作者： Yaozhong Zhang Meiyan Ding Yao Yuan Jiandong Zhang Guoqing Shi Qiming Yang School of Electronics and Information Northwestern Polytechnical University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The aggregation task is one of the typical tasks of Unmanned Aerial Vehicle(UAV) operations and has always been a hot research topic. With the development of technology and the continuous proves of war, multi-UAV have significant advantages in combat compared to single UAV. To address the intelligent control problem of multi-UAV aggregation task, this paper proposes a Twin Delayed Deep Deterministic policy gradient(td3) algorithm based on an evolutionary algorithm and introduces an evolutionary reinforcement learning framework. A learning cross operator is proposed to make offspring inherit parent features through training. To avoid high interaction costs, a critic network-assisted evaluation mechanism is proposed,and a response control decision is designed to combine real and virtual fitness to improve accuracy. Therefore, a Twin Delayed Deep Deterministic policy gradient algorithm combining Genetic algorithm enhanced by learning cross factors and auxiliary evaluation(GA-td3) is proposed. Simulation results show that GA-td3 has better training effects and generalization.

关键词： td3 algorithm aggregation task learning-based crossover operator critic network-assisted evaluation mechanism GA-td3 algorithm

来源：评论

学校读者我要写书评

暂无评论

Hydraulic-Supports Alignment by td3 with Segmented Experience Pool

引用

NEURAL PROCESSING LETTERS 2025年第2期57卷 1-22页

作者： Yang, Yi Dai, Yapeng Wang, Tian Qian, Wei Henan Polytech Univ Sch Elect Engn & Automat Jiaozuo 454003 Peoples R China Henan Key Lab Intelligent Detect & Control Coal Mi Jiaozuo 454003 Peoples R China Beihang Univ Inst Artificial Intelligence Beijing 100191 Peoples R China

Hydraulic-supports alignment is to keep the coal mining face in line and is heavily influenced by the various geological states. The experiences produced by the moving process are unbalanced, which leads to the agent not learning important knowledge from the rare samples. This paper is the first to introduce the reinforcement learning to the hydraulic-supports alignment, and establish the Markov optimal decision model by td3 algorithm. Aiming at the imbalance issue of the experience, this paper proposes a segmented experience pool and three sampling replay mechanisms according to the characteristics of the moving process with various geological states. Experimental results show that the improved td3, utilizing a segmented experience pool with three different replay mechanisms, could effectively identify the optimal moving policy and achieve significant convergence in cases involving both normal movement and insufficient movement of hydraulic-supports. In contrast, the td3 performs inadequately and struggles to find the optimal policy.

关键词： Hydraulic-supports alignment Various geological states Markov optimal decision td3 algorithm Segmented experience pool

来源：评论

学校读者我要写书评

暂无评论

Controlling Cable Driven Parallel Robots Operations-Deep Reinforcement Learning Approach

引用

IEEE ACCESS 2025年 13卷 36212-36223页

作者： Joyo, Muhammad Kamran Alenezi, Abdulmajeed M. Xu, Wenfu Alawad, Mohamad A. Yaqoob, Muhmmad Tayyab Maricar, Noor Khan, Sheroz Harbin Inst Technol Shenzhen Sch Mech Engn & Automat Shenzhen 518055 Peoples R China PAF KIET Coll Engn Elect Dept Karachi 75190 Pakistan Islamic Univ Madinah Dept Elect Engn Madinah 42351 Saudi Arabia Imam Mohammad Ibn Saud Islamic Univ IMSIU Coll Engn Dept Elect Engn Riyadh 11623 Saudi Arabia PAF KIET Coll Engn Avion Dept Karachi 75190 Pakistan Onaizah Coll Coll Engn & Informat Technol Dept Elect Engn Unaizah 56447 Al Qassim Saudi Arabia

Deep Reinforcement Learning (DRL) is a powerful approach for generating control strategies for a variety of complex systems, representing an emerging paradigm in control applications. An important feature of Deep RL is that it does not explicitly model the process, but instead it relies on optimization-driven techniques to devise effective control policies. Despite its remarkable success in simulated environments, RL holds great potential in real-world applications. This article explores the complex challenges involved in implementing Deep Reinforcement Learning (DRL) algorithms on a cable-driven parallel robot. A key contribution of this work as specific advancement is the integration of a Proportional-Integral-Derivative (PID) controller within the RL framework, establishing a unique approach to CDPR control that leverages adaptive learning capabilities. A Reinforcement Learning (RL) agent for reference tracking is trained using the novel application of the adaptive-featured Twin Delayed Deep Deterministic (td3) policy gradient algorithm, tailored to enhance CDPR adaptability and precision in dynamic environments. The first step is to test the performance of the trained agent on point-to-point robotic application tasks. As a result of such tasks, it is possible to evaluate the level of adaptability and performance of the RL agent. Multiple experiments are conducted to assess the versatility of the RL agent involving linear and circular scenarios. This research significantly advances the field by demonstrating the applicability of RL for complex robotic structures like CDPRs, showcasing promising results that underline the robustness and adaptability of the proposed approach. As a result of the td3 adaptive learning process, the trained agent is able to perform the designated action in order to determine which policy stands out as the most rewarding.

关键词： Parallel robots Robots End effectors Cables Process control Power cables Accuracy Robot kinematics Actuators Stability analysis Reinforcement learning td3 algorithm proportional-integral-derivative (PID) cable driven parallel robots

来源：评论

学校读者我要写书评

暂无评论

Intelligent control strategy for subway overhead line substation outputs based on controllable rectifiers

引用

JOURNAL OF POWER ELECTRONICS 2025年 1-13页

作者： Li, Hongyi Li, Jiyuan Hu, Yujie Yang, Tongshuo Zhu, Qinyue Tongji Univ Dept Elect Engn Shanghai Peoples R China

The global metro system is experiencing rapid development due to the benefits of subway transportation as a clean mode of travel and its expansion in many cities worldwide. Therefore, reducing energy consumption and minimizing voltage fluctuations in the contact network have become urgent issues. Aiming to address these challenges, a control strategy for the output voltage of metro line substations, based on fully controlled rectifiers, is proposed. This strategy uses an intelligent agent model for the substation voltage source converter, incorporating a reward function designed to optimize energy conservation and voltage stabilization in the catenary system. A traction power system simulator is used to emulate the natural environment, and the agent's actions are refined through each training cycle using the twin-delayed deep deterministic policy gradient (td3) algorithm. The proposed strategy was validated through simulations based on the Guangzhou Subway Line 6, demonstrating its capability to dynamically adjust substation rectifier voltage for highly efficient distribution of regenerative braking energy over time. Results indicate considerable improvements in energy savings and voltage stabilization when compared to multi-pulse rectifiers (diode rectifier unit) and constant voltage control strategies.

关键词： Electrical railway power supply system Renewable energies in railway energy saving td3 algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel reinforcement learning controller for the DC-DC boost converter

引用

ENERGY 2025年 321卷

作者： Cheng, Hangyu Jung, Seunghun Kim, Young-Bae Chonnam Natl Univ Dept Mech Engn Gwangju South Korea

In this paper, a robust control for the DC/DC boost converter to regulate capacitor output voltage is studied. Boost converters are highly nonlinear systems that exhibit interconnected state variables and system parameter variations due to load changes. To cope with these characteristics, A DC/DC boost converter controller that uses the twin delayed deep deterministic policy gradient algorithm (td3) control in continuous state is developed. This controller objective is to keep the output voltage constant under input voltage variations with fast response, little overshoot/undershoot, and ripples. As large fluctuation occurs in the actions under direct td3 control, a new control that uses a compensatory-td3 (C-td3) controller is newly proposed to address this issue. This study proposes a detailed method for verifying policy networks through hardware-in-the-loop (HIL) testing and experimentation. Under three different operating conditions, the C-td3 controller reduced settling times by 0.27s, 0.22s, and 0.18s compared to the PI controller, improving the response time of 22.5 %, 19.2 %, and 15.7 %, respectively. In addition, the integral absolute error of the C-td3 controller was decreased by 0.279 V, 0.366 V, and 0.493 V, respectively. The results show that under C-td3 control, voltage fluctuations were smaller, the response time was faster, and the duty cycle signal was more stable compared with those under PI control.

关键词： DC/DC boost converter Voltage regulation td3 algorithm Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Beyond diagonal-IRS assisted UAVs in terahertz network utilizing twin-delayed deep deterministic policy gradient approach

引用

TELECOMMUNICATION SYSTEMS 2025年第2期88卷 1-20页

作者： Omar, Shereen S. Abd EL-Haleem, Ahmed M. Ibrahim, Ibrahim I. Saleh, Amany M. Helwan Univ Elect & Commun Engn Dept Cairo 11792 Egypt

This paper presents an innovative approach in Terahertz (THz) band communications in 6G network, utilizing the integration of a Beyond Diagonal Intelligent Reflective Surface (BD-IRS) and Unmanned Aerial Vehicle (UAV) communications. This work examines the significance of THz downlink communication system in achieving an optimal trade-off between system performance and the circuit topology complexity of BD-IRS. An optimization framework named a (BD-IRS UAV) that optimizes the beyond diagonal BD-IRS phase shift in the reflective mode and finds the optimal UAVs locations, aiming to maximize the system data rate has been proposed. The multi BD-IRS UAV formulated problem is modeled as a Markov Decision Process. Nevertheless, this optimization problem is a non-convex and it is difficult to solve optimally. To tackle this difficulty, a Deep Reinforcement Learning based framework utilizing Twin-Delayed Deep Deterministic Policy Gradient (td3) algorithm is proposed to achieve an efficient solution. Finally, simulation results demonstrate the emphasis for the proposed robust algorithm-assisted THz system which significantly improves the system data rate and impacts on performance of the system when compared with the benchmark approaches.

关键词： 6G network THz network BD-IRS UAVs Outage probability DRL td3 algorithm

来源：评论

学校读者我要写书评

暂无评论

Intelligent Orchestrating of IoT Microservices Based on Reinforcement Learning

引用

Chinese Journal of Electronics 2022年第5期31卷 930-937页

作者： WU Yuqin SHEN Congqi CHEN Shuhan WU Chunming LI Shunbin WEI Ruan College of Computer Science and Technology Zhejiang University College of Information and Electrical Engineering Ningde Normal University Zhejiang Lab College of Control Science and Engineering Zhejiang University

With the recent increase in the number of Internet of things(IoT) services, an intelligent scheduling strategy is needed to manage these services. In this paper, the problem of automatic choreography of microservices in IoT is explored. A type of reinforcement learning(RL) algorithm called td3 is used to generate the optimal choreography policy under the framework of a softwaredefined network. The optimal policy is gradually reached during the learning procedure to achieve the goal, despite the dynamic characteristics of the network environment. The simulation results show that compared with other methods, the td3 algorithm converges faster after a certain number of iterations, and it performs better than other non-RL algorithms by obtaining the highest reward. The td3 algorithm can effciently adjust the traffic transmission path and provide qualified IoT services.

关键词： software-defined network telecommunication scheduling intelligent orchestrating nonRL algorithms reinforcement learning software defined networking optimal choreography policy reinforcement learning algorithm Internet of things services network environment IoT microservices td3 algorithm traffic transmission path Internet of Things qualified IoT services intelligent scheduling strategy dynamic characteristics

来源：评论

学校读者我要写书评

暂无评论

Cooperative Adaptive Cruise Control Based on Reinforcement Learning for Heavy-Duty BEVs

引用

IEEE ACCESS 2023年 11卷 127145-127156页

作者： Acquarone, Matteo Miretti, Federico Misul, Daniela Sassara, Luca Politecn Torino Ctr Automot Res & Sustainable Mobil CARSPolito Dipartimento Energia Galileo Ferraris I-10129 Turin Italy

This study proposes a novel approach for cooperative adaptive cruise control (CACC) based on the twin delayed deep deterministic policy gradient algorithm (td3) for heavy duty battery electric vehicles (BEVs). CACC is an advanced driver assistance systems (ADAS) that exploits vehicle connectivity to bring new advantages to cruise control technologies. The td3 algorithm, which is a deep reinforcement learning (DRL) algorithm, was selected because it is currently at the forefront of the state of the art for problems with continuous states and actions. Furthermore, compared to state-of-the-art techniques, such as linear MPC, a DRL approach is more effective in dealing with highly nonlinear objectives. This enables us to explicitly model the effect of air drag reduction in the ego vehicle, which positively affects energy savings. The air drag reduction characteristic was modeled through experimental data from a previous work. At the same time, driving comfort was also optimized with respect to the reference driving cycle, chosen as the HHDDT driving cycle. Three different types of spacing strategies have been investigated that involve minimum time headway and time-to-collision (TTC) to study the safety guarantee of the algorithm, particularly when facing critical and unexpected situations such as sudden hard braking. The results achieved show how the Ego vehicle can reduce energy consumption by up to 19.8% without the comfort worsening with respect to the preceding vehicle, still guaranteeing safe driving conditions, when considering the spacing strategy based only on TTC, developed to obtain the highest air drag reduction.

关键词： Cooperative adaptive cruise control reinforcement learning td3 algorithm heavy-duty vehicle air drag reduction BEV

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：