Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.5
2.4
Journals
Mathematics
Special Issues
Ensemble Evolutionary Algorithms and Machine Learning for Solving Complex Optimization...
share announcement

Ensemble Evolutionary Algorithms and Machine Learning for Solving Complex Optimization and Scheduling Problems

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Computational and Applied Mathematics".

Deadline for manuscript submissions: 31 December 2024 | Viewed by 5019

Special Issue Editors

Dr. Kaizhou Gao

E-Mail Website
Guest Editor
Department of Engineering Science, Macau Institute of Systems Engineering, Macau University of Science and Technology, Macau, China
Interests: artificial intelligence; intelligent optimization theory, methods and applications; reinforcement learning; complex systems modeling, optimization and scheduling; intelligent transportation; intelligent manufacturing; smart city
Prof. Dr. Naiqi Wu

E-Mail Website
Guest Editor
Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and Systems, Macau University of Science and Technology, Macao 999078, China
Interests: intelligent manufacturing; discrete event systems, and petri net theory and applications; production planning, scheduling and control; intelligent logistics and transportation; energy systems
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Yaping Fu

E-Mail Website
Guest Editor
Department of Management Science and Engineering, Qingdao University, Qingdao, China
Interests: production planning and scheduling; evolutionary multi-objective optimization; simulation optimization; reinforcement learning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Swarm and evolutionary algorithms have been successfully employed and improved for solving complex optimization and scheduling problems in various areas due to their applicability and interesting computational aspects. This Special Issue deals with modeling, optimizing and scheduling challenges of engineering problems by integrating swarm/evolutionary algorithms and machine learning. It specifically aims at the most recent developments in swarm and evolutionary algorithms, meta-heuristics, ensemble and machine learning algorithms, and applications for various complex scheduling and optimization problems.

Potential topics include (but are not limited to) the following:

  • Multi-objective, multi-task, and multi-constraint optimization
  • Large-scale global optimization
  • Ensemble swarm and evolutionary algorithms with machine learning algorithms
  • Learning-based meta-heuristics

Swarm and evolutionary algorithms for:

  • Production scheduling problems
  • Energy-efficiency scheduling problems
  • Traffic signal control, optimization, and scheduling
  • Vehicle routing problems
  • Unmanned vehicles/unmanned surface vessels task assignment and routing planning
  • Project scheduling
  • Grid/cloud scheduling
  • Scheduling and optimization in smart city
  • Scheduling and optimization in smart building and home
  • Scheduling and optimization in sustainability systems
  • New real-world and innovative applications of ensemble with machine learning algorithms

Dr. Kaizhou Gao
Prof. Dr. Naiqi Wu
Prof. Dr. Yaping Fu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • multi-objective, multi-task, and multi-constraint optimization
  • large-scale global optimization
  • ensemble swarm and evolutionary algorithms with machine learning algorithms
  • learning-based meta-heuristics
  • production scheduling problems
  • energy-efficiency scheduling problems
  • traffic signal control, optimization, and scheduling
  • vehicle routing problems
  • unmanned vehicles/unmanned surface vessels task assignment and routing planning
  • project scheduling
  • grid/cloud scheduling
  • scheduling and optimization in smart city
  • scheduling and optimization in smart building and home
  • scheduling and optimization in sustainability systems
  • new real-world and innovative applications of ensemble with machine learning algorithms

Published Papers (7 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

19 pages, 1706 KiB  
Article
An Optimized Advantage Actor-Critic Algorithm for Disassembly Line Balancing Problem Considering Disassembly Tool Degradation
by Shujin Qin, Xinkai Xie, Jiacun Wang, Xiwang Guo, Liang Qi, Weibiao Cai, Ying Tang and Qurra Tul Ann Talukder
Mathematics 2024, 12(6), 836; https://doi.org/10.3390/math12060836 - 12 Mar 2024
Viewed by 547
Abstract
The growing emphasis on ecological preservation and natural resource conservation has significantly advanced resource recycling, facilitating the realization of a sustainable green economy. Essential to resource recycling is the pivotal stage of disassembly, wherein the efficacy of disassembly tools plays a critical role. [...] Read more.
The growing emphasis on ecological preservation and natural resource conservation has significantly advanced resource recycling, facilitating the realization of a sustainable green economy. Essential to resource recycling is the pivotal stage of disassembly, wherein the efficacy of disassembly tools plays a critical role. This work investigates the impact of disassembly tools on disassembly duration and formulates a mathematical model aimed at minimizing workstation cycle time. To solve this model, we employ an optimized advantage actor-critic algorithm within reinforcement learning. Furthermore, it utilizes the CPLEX solver to validate the model’s accuracy. The experimental results obtained from CPLEX not only confirm the algorithm’s viability but also enable a comparative analysis against both the original advantage actor-critic algorithm and the actor-critic algorithm. This comparative work verifies the superiority of the proposed algorithm. Full article
(This article belongs to the Special Issue Ensemble Evolutionary Algorithms and Machine Learning for Solving Complex Optimization and Scheduling Problems)
►▼ Show Figures

Figure 1

17 pages, 1116 KiB  
Article
An Improved Moth-Flame Algorithm for Human–Robot Collaborative Parallel Disassembly Line Balancing Problem
by Qi Zhang, Bin Xu, Man Yao, Jiacun Wang, Xiwang Guo, Shujin Qin, Liang Qi and Fayang Lu
Mathematics 2024, 12(6), 816; https://doi.org/10.3390/math12060816 - 11 Mar 2024
Viewed by 533
Abstract
In the context of sustainable development strategies, the recycling of discarded products has become increasingly important with the development of electronic technology. Choosing the human–robot collaborative disassembly mode is the key to optimizing the disassembly process and ensuring maximum efficiency and benefits. To [...] Read more.
In the context of sustainable development strategies, the recycling of discarded products has become increasingly important with the development of electronic technology. Choosing the human–robot collaborative disassembly mode is the key to optimizing the disassembly process and ensuring maximum efficiency and benefits. To solve the problem of human–robot cooperative parallel dismantling line balance, a mixed integer programming model is established and verified by CPLEX. An improved Moth-Flame Optimization (IMFO) algorithm is proposed to speed up convergence and optimize the disassembly process of various products. The effectiveness of IMFO is evaluated through multiple cases and compared with other heuristics. The results of these comparisons can provide insight into whether IMFO is the most appropriate algorithm for the problem presented. Full article
(This article belongs to the Special Issue Ensemble Evolutionary Algorithms and Machine Learning for Solving Complex Optimization and Scheduling Problems)
►▼ Show Figures

Figure 1

22 pages, 1289 KiB  
Article
An Improved Discrete Bat Algorithm for Multi-Objective Partial Parallel Disassembly Line Balancing Problem
by Qi Zhang, Yang Xing, Man Yao, Jiacun Wang, Xiwang Guo, Shujin Qin, Liang Qi and Fuguang Huang
Mathematics 2024, 12(5), 703; https://doi.org/10.3390/math12050703 - 28 Feb 2024
Viewed by 583
Abstract
Product disassembly is an effective means of waste recycling and reutilization that has received much attention recently. In terms of disassembly efficiency, the number of disassembly skills possessed by workers plays a crucial role in improving disassembly efficiency. Therefore, in order to effectively [...] Read more.
Product disassembly is an effective means of waste recycling and reutilization that has received much attention recently. In terms of disassembly efficiency, the number of disassembly skills possessed by workers plays a crucial role in improving disassembly efficiency. Therefore, in order to effectively and reasonably disassemble discarded products, this paper proposes a partial parallel disassembly line balancing problem (PP-DLBP) that takes into account the number of worker skills. In this paper, the disassembly tasks and the disassembly relationships between components are described using AND–OR graphs. In this paper, a multi-objective optimization model is established aiming to maximize the net profit of disassembly and minimize the number of skills for the workers. Based on the bat algorithm (BA), we propose an improved discrete bat algorithm (IDBA), which involves designing adaptive composite optimization operators to replace the original continuous formula expressions and applying them to solve the PP-DLBP. To demonstrate the advantages of IDBA, we compares it with NSGA-II, NSGA-III, SPEA-II, ESPEA, and MOEA/D. Experimental results show that IDBA outperforms the other five algorithms in real disassembly cases and exhibits high efficiency. Full article
(This article belongs to the Special Issue Ensemble Evolutionary Algorithms and Machine Learning for Solving Complex Optimization and Scheduling Problems)
►▼ Show Figures

Figure 1

20 pages, 3037 KiB  
Article
Fusion Q-Learning Algorithm for Open Shop Scheduling Problem with AGVs
by Xiaoyu Wen, Haobo Zhang, Hao Li, Haoqi Wang, Wuyi Ming, Yuyan Zhang and Like Zhang
Mathematics 2024, 12(3), 452; https://doi.org/10.3390/math12030452 - 31 Jan 2024
Viewed by 541
Abstract
In accordance with the actual production circumstances of enterprises, a scheduling problem model is designed for open-shop environments, considering AGV transport time. A Q-learning-based method is proposed for the resolution of such problems. Based on the characteristics of the problem, a hybrid encoding [...] Read more.
In accordance with the actual production circumstances of enterprises, a scheduling problem model is designed for open-shop environments, considering AGV transport time. A Q-learning-based method is proposed for the resolution of such problems. Based on the characteristics of the problem, a hybrid encoding approach combining process encoding and AGV encoding is applied. Three pairs of actions are constituted to form the action space. Decay factors and a greedy strategy are utilized to perturb the decision-making of the intelligent agent, preventing it from falling into local optima while simultaneously facilitating extensive exploration of the solution space. Finally, the proposed method proved to be effective in solving the open-shop scheduling problem considering AGV transport time through multiple comparative experiments. Full article
(This article belongs to the Special Issue Ensemble Evolutionary Algorithms and Machine Learning for Solving Complex Optimization and Scheduling Problems)
►▼ Show Figures

Figure 1

21 pages, 695 KiB  
Article
Linear Disassembly Line Balancing Problem with Tool Deterioration and Solution by Discrete Migratory Bird Optimizer
by Shujin Qin, Jiaxin Wang, Jiacun Wang, Xiwang Guo, Liang Qi and Yaping Fu
Mathematics 2024, 12(2), 342; https://doi.org/10.3390/math12020342 - 20 Jan 2024
Viewed by 626
Abstract
In recent years, the global resource shortage has become a serious issue. Recycling end-of-life (EOL) products is conducive to resource reuse and circular economy and can mitigate the resource shortage issue. The disassembly of EOL products is the first step for resource reuse. [...] Read more.
In recent years, the global resource shortage has become a serious issue. Recycling end-of-life (EOL) products is conducive to resource reuse and circular economy and can mitigate the resource shortage issue. The disassembly of EOL products is the first step for resource reuse. Disassembly activities need tools, and tool deterioration occurs inevitably during the disassembly process. This work studies the influence of tool deterioration on disassembly efficiency. A disassembly line balancing model with the goal of maximizing disassembly profits is established, in which tool selection and assignment is a critical part. A modified discrete migratory bird optimizer is proposed to solve optimization problems. The well-known IBM CPLEX optimizer is used to verify the correctness of the model. Six real-world products are used for disassembly experiments. The popular fruit fly optimization algorithm, whale optimization algorithm and salp swarm algorithm are used for search performance comparison. The results show that the discrete migratory bird optimizer outperforms all three other algorithms in all disassembly instances. Full article
(This article belongs to the Special Issue Ensemble Evolutionary Algorithms and Machine Learning for Solving Complex Optimization and Scheduling Problems)
►▼ Show Figures

Figure 1

23 pages, 7387 KiB  
Article
Solving Heterogeneous USV Scheduling Problems by Problem-Specific Knowledge Based Meta-Heuristics with Q-Learning
by Zhenfang Ma, Kaizhou Gao, Hui Yu and Naiqi Wu
Mathematics 2024, 12(2), 339; https://doi.org/10.3390/math12020339 - 19 Jan 2024
Cited by 2 | Viewed by 856
Abstract
This study focuses on the scheduling problem of heterogeneous unmanned surface vehicles (USVs) with obstacle avoidance pretreatment. The goal is to minimize the overall maximum completion time of USVs. First, we develop a mathematical model for the problem. Second, with obstacles, an A* [...] Read more.
This study focuses on the scheduling problem of heterogeneous unmanned surface vehicles (USVs) with obstacle avoidance pretreatment. The goal is to minimize the overall maximum completion time of USVs. First, we develop a mathematical model for the problem. Second, with obstacles, an A* algorithm is employed to generate a path between two points where tasks need to be performed. Third, three meta-heuristics, i.e., simulated annealing (SA), genetic algorithm (GA), and harmony search (HS), are employed and improved to solve the problems. Based on problem-specific knowledge, nine local search operators are designed to improve the performance of the proposed algorithms. In each iteration, three Q-learning strategies are used to select high-quality local search operators. We aim to improve the performance of meta-heuristics by using Q-learning-based local search operators. Finally, 13 instances with different scales are adopted to validate the effectiveness of the proposed strategies. We compare with the classical meta-heuristics and the existing meta-heuristics. The proposed meta-heuristics with Q-learning are overall better than the compared ones. The results and comparisons show that HS with the second Q-learning, HS + QL2, exhibits the strongest competitiveness (the smallest mean rank value 1.00) among 15 algorithms. Full article
(This article belongs to the Special Issue Ensemble Evolutionary Algorithms and Machine Learning for Solving Complex Optimization and Scheduling Problems)
►▼ Show Figures

Figure 1

19 pages, 1986 KiB  
Article
Improved Brain-Storm Optimizer for Disassembly Line Balancing Problems Considering Hazardous Components and Task Switching Time
by Ziyan Zhao, Pengkai Xiao, Jiacun Wang, Shixin Liu, Xiwang Guo, Shujin Qin and Ying Tang
Mathematics 2024, 12(1), 9; https://doi.org/10.3390/math12010009 - 19 Dec 2023
Viewed by 568
Abstract
Disassembling discarded electrical products plays a crucial role in product recycling, contributing to resource conservation and environmental protection. While disassembly lines are progressively transitioning to automation, manual or human–robot collaborative approaches still involve numerous workers dealing with hazardous disassembly tasks. In such scenarios, [...] Read more.
Disassembling discarded electrical products plays a crucial role in product recycling, contributing to resource conservation and environmental protection. While disassembly lines are progressively transitioning to automation, manual or human–robot collaborative approaches still involve numerous workers dealing with hazardous disassembly tasks. In such scenarios, achieving a balance between low risk and high revenue becomes pivotal in decision making for disassembly line balancing, determining the optimal assignment of tasks to workstations. This paper tackles a new disassembly line balancing problem under the limitations of quantified penalties for hazardous component disassembly and the switching time between adjacent tasks. The objective function is to maximize the overall profit, which is equal to the disassembly revenue minus the total cost. A mixed-integer linear program is formulated to precisely describe and optimally solve the problem. Recognizing its NP-hard nature, a metaheuristic algorithm, inspired by human idea generation and population evolution processes, is devised to achieve near-optimal solutions. The exceptional performance of the proposed algorithm on practical test cases is demonstrated through a comprehensive comparison involving its solutions, exact solutions obtained using CPLEX to solve the proposed mixed-integer linear program, and those of competitive peer algorithms. It significantly outperforms its competitors and thus implies its great potential to be used in practice. As computing power increases, the effectiveness of the proposed methods is expected to increase further. Full article
(This article belongs to the Special Issue Ensemble Evolutionary Algorithms and Machine Learning for Solving Complex Optimization and Scheduling Problems)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-7
Back to TopTop