检索结果-内蒙古大学图书馆

Coherent beam combination based on q-learning algorithm

OPTICS COMMUNICATIONS 2021年 490卷 126930-126930页

作者： Zhang, Xi Li, Pingxue Zhu, Yunchen Li, Chunyong Yao, Chuanfei Wang, Luo Dong, Xueyan Li, Shun Beijing Univ Technol Fac Mat & Mfg Inst Ultrashort Pulsed Laser & Applicat Beijing 10024 Peoples R China Univ Durham Dept Phys South Rd Durham DH1 3LE England

Coherent beam combination (CBC) is an effective method to break the limiting power of a single fiber laser. The q-learning algorithm is one of the reinforcement learning algorithms. We use the q-learning algorithm to do phase compensation in the field of CBC. The performance difference between the q-learning algorithm and the stochastic parallel gradient descent optimization algorithm (SPGD) is analyzed by simulating time-domain coherent synthesis. The results show that the q-learning algorithm is easier to debug and has better stability.

关键词： Coherent beam combination q-learning algorithm Stochastic parallel gradient descent optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

An Experimental Safety Response Mechanism for an Autonomous Moving Robot in a Smart Manufacturing Environment Using q-learning algorithm and Speech Recognition

引用

SENSORS 2022年第3期22卷 941-941页

作者： Kiangala, Kahiomba Sonia Wang, Zenghui Univ South Africa Coll Sci Engn & Technol CSET ZA-1710 Johannesburg South Africa Univ South Africa Dept Elect & Min Engn ZA-1710 Johannesburg South Africa

The industrial manufacturing sector is undergoing a tremendous revolution moving from traditional production processes to intelligent techniques. Under this revolution, known as Industry 4.0 (I40), a robot is no longer static equipment but an active workforce to the factory production alongside human operators. Safety becomes crucial for humans and robots to ensure a smooth production run in such environments. The loss of operating moving robots in plant evacuation can be avoided with the adequate safety induction for them. Operators are subject to frequent safety inductions to react in emergencies, but very little is done for robots. Our research proposes an experimental safety response mechanism for a small manufacturing plant, through which an autonomous robot learns the obstacle-free trajectory to the closest safety exit in emergencies. We implement a reinforcement learning (RL) algorithm, q-learning, to enable the path learning abilities of the robot. After obtaining the robot optimal path selection options with q-learning, we code the outcome as a rule-based system for the safety response. We also program a speech recognition system for operators to react timeously, with a voice command, to an emergency that requires stopping all plant activities even when they are far away from the emergency stops (ESTOPs) button. An ESTOP or a voice command sent directly to the factory central controller can give the factory an emergency signal. We tested this functionality on real hardware from an S7-1200 Siemens programmable logic controller (PLC). We simulate a simple and small manufacturing environment overview to test our safety procedure. Our results show that the safety response mechanism successfully generates paths without obstacles to the closest safety exits from all the factory locations. Our research benefits any manufacturing SME intending to implement the initial and primary use of autonomous moving robots (AMR) in their factories. It also impacts manufacturin

关键词： autonomous moving robot obstacle-free path planning q-learning algorithm reinforcement learning (RL) safety response smart manufacturing speech recognition

来源：评论

学校读者我要写书评

暂无评论

Disassembly sequence planning for target parts of end-of-life smartphones using q-learning algorithm

引用

Procedia CIRP 2023年 116卷 684-689页

作者： Zepeng Chen Lin Li Fu Zhao John W. Sutherland Fengfu Yin College of Electromechanical Engineering Qingdao University of Science and Technology Qingdao 266061 China School of Environmental and Ecological Engineering Purdue University West Lafayette IN 47907 USA School of Mechanical Engineering Purdue University West Lafayette IN 47907 USA

Owing to increasing environmental concerns, disassembly has become an important step in value recovery from end-of-life (EoL) products. As one of the prevalent electronic devices, smartphones are especially challenging to manage at the end of life. They have a diverse internal structure that leads to difficulties in modeling and developing general plans for disassembly. Given this background, an improved method that uses a q-learning algorithm is proposed to optimize the disassembly sequence of EoL smartphones. A constraint relationship is first developed of EoL smartphone parts. The disassembly sequence planning problem is then formalized with a Markov Decision Process. The optimization objective is the disassembly time to obtain the target parts. The disassembly time and the target parts are converted into a reward value for the q-learning algorithm. A State-Action-Reward Matrix is established based on converted reward value and disassembly sequence planning problem. A q-table is trained to find the best action for each state using the State-Action-Reward Matrix. The disassembly sequence with the maximum reward value is secured through the trained q-table and objective function. A case study of the ‘Xiaomi 5’ is conducted to verify the applicability of the proposed method. The experimental results demonstrate that the proposed method can provide feasible sequence planning for targeted parts in the disassembly of EoL smartphones.

关键词： EoL smartphones Disassembly sequence q-learning algorithm Disassembly time Target parts

来源：评论

学校读者我要写书评

暂无评论

An optimized q-learning algorithm for mobile robot local path planning

引用

KNOWLEDGE-BASED SYSTEMS 2024年 286卷

作者： Zhou, qian Lian, Yang Wu, Jiayang Zhu, Mengyue Wang, Haiyong Cao, Jinli Nanjing Univ Posts & Telecommun Sch Modern Posts Nanjing 210003 Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Sch Comp Sci Sch Software Nanjing 210037 Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Sch Cyberspace Secur Nanjing 210037 Jiangsu Peoples R China La Trobe Univ Dept Comp Sci & Comp Engn Melbourne Australia

The q-learning algorithm is a reinforcement learning technique widely used in various fields such as path planning, intelligent transportation, penetration testing, among others. It primarily involves the interaction between an agent and its environment, enabling the agent to learn an optimal strategy that maximizes cumulative rewards. Most non-agent-based path planning algorithms face challenges in exploring completely unknown environments effectively, lacking efficient perception in unfamiliar settings. Additionally, many qlearning-based path planning algorithms suffer from slow convergence and susceptibility to getting stuck in local optimal solutions. To address these issues, an optimized version of the q-learning algorithm (Optimized q-learning, O-qL) is proposed and applied to local path planning of mobile robots. O-qL introduces novel q -table initialization methods, incorporates a new action-selection policy, and a new reward function, and adapts the Root Mean Square Propagation (RMSprop) method in the learning rate adjustment. This adjustment dynamically tunes the learning rate based on gradient changes to accelerate learning and enhance path planning efficiency. Simulation experiments are carried out in three maze environments with different complexity levels, and the performance of the algorithm in local path planning is evaluated using steps, exploration reward, learning rate change and running time. The experimental results demonstrate that O-qL exhibits improvements across all four metrics compared to existing algorithms.

关键词： Mobile robot q-learning algorithm Local path planning Reinforcement learning Adaptive learning rate

来源：评论

学校读者我要写书评

暂无评论

DE Based q-learning algorithm to Improve Speed of Convergence In Large Search Space Applications

DE Based Q-learning Algorithm to Improve Speed of Convergenc...

引用

International Conference on Electronic Systems, Signal Processing and Computing

作者： Zenefa Rahaman Jaya Sil Dept. of Computer Science and Technology Bengal Engineering and Science University Shibpur Howrah India

ISBN: (纸本)9781479921041

The main drawback of reinforcement learning is that it learns nothing from an episode until it is over. So the learning procedure is very slow in case of large space applications. Differential Evolution (DE) algorithm is a population-based evolutionary optimization algorithm able to learn the search space in iterative way. In the paper, improvement of q-learning method has been proposed using DE algorithm where guided randomness has been incorporated in the search space resulting fast convergence. Markov Decision Process (MDP), a mathematical framework has been used to model the problem in order to learn the large search space efficiently. The proposed algorithm exhibits better result in terms of speed and performance compare to basic q-learning algorithm.

关键词： Differential Evolution algorithm q-learning algorithm Markov Decision Process Convergence

来源：评论

学校读者我要写书评

暂无评论

Divide and Conquer q-learning (DCqL) algorithm based Photovoltaic (PV) array reconfiguration scheme for alleviating the partial shading influence

引用

SOLAR ENERGY 2023年 249卷 21-39页

作者： Gao, Xin Deng, Fang Wu, Guoqiang Pan, qiufeng Zheng, Chengyu Wang, Wei Cai, Tianwang Jiang, Liyuan China Aerosp Sci & Technol Corp Acad Unmanned Syst Ctr 9 Beijing 100094 Peoples R China Aerosp Times FeiHong Technol Co Ltd Beijing 100094 Peoples R China Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China

Nonuniform irradiance on the Photovoltaic (PV) array would cause mismatch problem and decrease the generated power. To relieve the negative effects of partial shading, reconfiguring the interconnection of the PV array is a favorable solution. However, the current reconfiguration techniques are usually limited by different corresponding factors, e.g., not suit for various instantaneous shade cases, the shortage of experts' knowledge or large amounts of data, easy coverage to local optima, and the strict assumptions for application. Therefore, in this paper a unsupervised adaptive PV array reconfiguration technique is proposed with a Divide and Conquer q-learning (DCqL) based array reconfiguration scheme designed to decrease the influence of partial shades. To testify the performance of the proposed PV array reconfiguration scheme, mathematic theoretical evaluation and electric characteristic analyses are made and compared with those obtained by the conventional Total -Cross-Tied (TCT) arrangement, SuDoKu connection, Genetic algorithm (GA) based scheme, as well as some lately proposed Grasshopper Optimization algorithm (GOA), Harris Hawks Optimizer (HHO), and Lo Shu (LS) technique based reconfiguration methods. Besides, additional estimation indices, including mismatch loss, fill factor, percentage power loss and percentage power enhancement are calculated with substantial analyses and comparisons. Subsequently, the application of the proposed scheme in real-time conditions is evaluated, with energy saving and income analysis estimated in comparison with other eminent challenger reconfiguration schemes. At last, a comprehensive qualitative comparison assessment, with respect to dispersion ability under partial shading conditions (PSC), sensor requirement, wiring complexity and capital investment is carried out and proves the versatility of proposed methodology.

关键词： Photovoltaic array reconfiguration Reinforcement learning q-learning algorithm Divide and conquer principle Partial shadings

来源：评论

学校读者我要写书评

暂无评论

The Development of Role-Playing Game Multimedia Using q-learning algorithm Based Inquiry Training Model

The Development of Role-Playing Game Multimedia Using Q-Lear...

引用

6th International Conference on Teaching,Education and learning(ICTEL)

作者： Enjang Ali Nurdin Muhammad Fadlian Amhar Aan Agustan Department of Computer Science Education Universitas Pendidikan Indonesia

The purpose of this research is to develop a Role-Playing Game(RPG) multimedia based Inquiry Training Model(ITM) with a q-learning algorithm for subjects Structured query Language(SqL) on vocational high school in department of software engineering. The design of study is done with phase analysis, design, development, implementation, and assessment. At this stage of the analysis carried out literature studies, field and acquisition of information about the curriculum and syllabus that applicable. Results of analysis used for designing materials, flowcharts, and storyboard. Multimedia learning related to the ITM phase. RPG game elements in the form used as a multimedia approach for learning. q-learning algorithm is added to the multimedia as a user interaction to provide advice in the RPG. To obtain multimedia learning assessment in the context of the development, validation is done by theexpert in media and content. The next assessment phase is limited trials conducted in a single unit in which student access to multimedia learning in groups. Respondent assessors are 14 people in class XI vocational high school no 11, Bandung. The results showed values in the range of "Very Good" according to expert in media and content also the student assesment.

关键词： multimedia learning RPG Inquiry Training Model q-learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on heating emergency repair path planning based on AHP and improved q-learning algorithm

Research on heating emergency repair path planning based on ...

引用

第35届中国过程控制会议

作者： Xi Zhao Yilin Han Jiahua Zhu Yunsheng Fan Dingxiao Zhu College of Marine Electrical Engineering Dalian Maritime University Dalian Thermal Power New Energy Application Technology Research Institute Co..Ltd.

Aiming at the problems of low learning efficiency and slow convergence speed of traditional q-learning method in path planning, this paper proposes an improved q-learning algorithm for heating emergency repair path planning. To solve this problem, the algorithm initializes the q-table according to the heuristic function to accelerate the learning process, leading the agent to a better strategy in the early stage of the training process;Dynamic adjustment of greedy factor is added to balance the relationship between exploration and utilization. The Tabu Search algorithm is integrated to avoid falling into local path optimization, reduce the repetition rate of topology map exploration, and accelerate the convergence speed;Finally, based on the analytic hierarchy process, the urgency of emergency repair of heating failure is graded, and the visiting order of emergency repair failure points is planned according to the emergency degree, which is helpful to improve the efficiency of emergency repair. The experimental results show that the efficiency of the improved algorithm is better than that of the traditional algorithm in the path length and the number of path nodes, and it can converge better in the training process.

关键词： Route planning q-learning algorithm Tabu Search algorithm Analytic hierarchy process Emergency repair Heating system

来源：评论

学校读者我要写书评

暂无评论

A q-learning-based Deep Deterministic Policy Gradient algorithm for the Re-entrant Hybrid Flow Shop Joint Scheduling Problem with Dual-gripper

引用

Engineering Letters 2025年第5期33卷 1632-1647页

作者： Wang, Jiajia Zhou, Hongming Guo, Jian Si, Hongwei Chen, Xu Zhang, Minghai Zhang, Yaqi Zhou, Guixuan School of Mechanical and Electrical Engineering Wenzhou University Zhejiang Wenzhou 325035 China College of Mechanical and Electrical Engineering Wenzhou University Zhejiang Wenzhou 325035 China Senken Group Co. Ltd. Zhejiang Wenzhou 325029 China

This paper addresses the re-entrant hybrid flow shop joint scheduling problem with dual-gripper (RHFSJSPD). In RHFSJSPD, multiple machines and dual-gripper robots are capable of simultaneously handling different workpieces, which gives rise to a complex problem involving job sequencing, task allocation and speed control across multiple workstations. It is characterized by a higher state space dimension and finer action division, thus requiring an efficient integrated scheduling approach. Traditional intelligent algorithms often struggle with the dynamic, combined discrete, and continuous challenges of RHFSJSPD. First, an integrated production and transportation mathematical model aimed at minimizing the maximum completion time and total delay is established to describe RHFSJSPD. Then, a q-learning-based Deep Deterministic Policy Gradient (DDPG) algorithm(q-DDPG) is developed to handle RHFSJSPD. The algorithm employs q-learning for macroscopic job scheduling and DDPG for microscopic dual-gripper control. Greedy strategies are combined with heuristic rules to enhance the search efficiency of q-learning. The convergence rate of DDPG in the microscopic continuous action space is improved by means of target networks and experience replay. Finally, to evaluate the efficiency of q-DDPG, two comparative numerical experiments are conducted on a benchmark of 30 instances of RHFSJSPD with different scales. The statistical results reveal that q-DDPG surpasses the other three q-learning-based variant algorithms and achieves the highest utilization rates of machines and dual-gripper robots in the actual scheduling process. Furthermore, the integrated scheduling approach leads to an average reduction of 9.41% in makespan and 16.14% in total delay time. © 2025, International Association of Engineers. All rights reserved.

关键词： dual-gripper multi-agent system q-learning algorithm re-entrant flow shop

来源：评论

学校读者我要写书评

暂无评论

An improved particle swarm optimization using q-learning and tangent flight strategy for the combined cooling, heating, and power system

引用

ELECTRICAL ENGINEERING 2025年 1-18页

作者： Zhang, Zhaojun Luo, Hongjie Tan, Simeng Zou, Kuansheng Zhou, Shengwu Jiangsu Normal Univ Sch Elect Engn & Automat Xuzhou 221116 Jiangsu Peoples R China Land Surveying & Mapping Inst Shandong Prov Jinan 250102 Shandong Peoples R China

In this paper, the storage battery and photovoltaic generator set are integrated into the combined cooling, heating, and power (CCHP) system to reduce its operating cost. Four scenarios with or without storage battery are investigated for the CCHP system. qTPSO that combines the q-learning algorithm and tangent flight strategy is proposed for the four CCHP scenarios in spring and winter. The q-learning algorithm enables the population to utilize information from previous iterations, adaptively selecting the optimal speed and position update formula based on the environment and population state. The tangent flight strategy expands the search space of the population and improves the global search capability of the algorithm. Experimental results indicate that the qTPSO outperforms four other algorithms, achieving the lowest operating cost among the four CCHP scenarios. Additionally, the CCHP system with battery exhibits a lower operating cost. In spring, the operating cost of the CCHP system with battery is 8.2% lower than that the system without battery. In winter, the operating costs for CCHP systems with battery is 8.42% lower than that the system without battery.

关键词： Combined cooling heating and power Storage battery q-learning algorithm Tangent flight strategy

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：