Integrated Scheduling of Multi-Objective Job Shops and Material Handling Robots with Reinforcement Learning Guided Meta-Heuristics DOI Creative Commons

Zhangying Xu,

Qi Jia,

Kaizhou Gao

et al.

Mathematics, Journal Year: 2024, Volume and Issue: 13(1), P. 102 - 102

Published: Dec. 30, 2024

This study investigates the integrated multi-objective scheduling problems of job shops and material handling robots (MHR) with minimising maximum completion time (makespan), earliness or tardiness, total energy consumption. The collaborative MHR machines can enhance efficiency reduce costs. First, a mathematical model is constructed to articulate concerned problems. Second, three meta-heuristics, i.e., genetic algorithm (GA), differential evolution, harmony search, are employed, their variants seven local search operators devised solution quality. Then, reinforcement learning algorithms, Q-learning state–action–reward–state–action (SARSA), utilised select suitable during iterations. Three reward setting strategies designed for algorithms. Finally, proposed algorithms examined by solving 82 benchmark instances. Based on solutions analysis, we conclude that GA integrating SARSA first strategy most competitive one among 27 compared

Language: Английский

Review on ensemble meta-heuristics and reinforcement learning for manufacturing scheduling problems DOI
Yaping Fu, Yifeng Wang, Kaizhou Gao

et al.

Computers & Electrical Engineering, Journal Year: 2024, Volume and Issue: 120, P. 109780 - 109780

Published: Oct. 18, 2024

Language: Английский

Citations

15
A multi-dimensional co-evolutionary algorithm for multi-objective resource-constrained flexible flowshop with robotic transportation DOI
Jiake Li,

Rong-hao Li,

Junqing Li

et al.

Applied Soft Computing, Journal Year: 2025, Volume and Issue: 170, P. 112689 - 112689

Published: Jan. 2, 2025

Language: Английский

Citations

1
An Evolutionary Learning Whale Optimization Algorithm for Disassembly and Assembly Hybrid Line Balancing Problems DOI Creative Commons
Xinshuo Cui, Qingbo Meng, Jiacun Wang

et al.

Mathematics, Journal Year: 2025, Volume and Issue: 13(2), P. 256 - 256

Published: Jan. 14, 2025

In order to protect the environment, an increasing number of people are paying attention recycling and remanufacturing EOL (End-of-Life) products. Furthermore, many companies aim establish their own closed-loop supply chains, encouraging integration disassembly assembly lines into a unified production system. this work, hybrid line that combines processes, incorporating human–machine collaboration, is designed based on traditional line. A mathematical model proposed address collaboration balancing problem in layout. To solve model, evolutionary learning-based whale optimization algorithm developed. The experimental results show significantly faster than CPLEX, particularly for large-scale instances. Moreover, it outperforms CPLEX other swarm intelligence algorithms solving problems while maintaining high solution quality.

Language: Английский

Citations

0
Research on UAV Trajectory Planning Algorithm Based on Adaptive Potential Field DOI Creative Commons

Mingzhi Shao,

Xin Liu, Changshi Xiao

et al.

Drones, Journal Year: 2025, Volume and Issue: 9(2), P. 79 - 79

Published: Jan. 21, 2025

For multi-obstacle complex scenarios, the traditional artificial potential field method suffers from defects of imbalance, its capability to easily fall into local minima, and encounter unreachable targets in navigation environments. Therefore, this paper proposes a three-dimensional adaptive algorithm (SAPF) based on multi-agent reinforcement learning. First, paper, gravitational function (APF) is modified weaken effect UAV region far away target point order reduce risk collision between obstacles during moving process. Second, close point, improves ensure that can reach smoothly realize path convergence by considering relative distance UAV’s current position point. Finally, for characteristics trajectory planning, 3D state space designed coordinates UAV, nearest obstacle, point; an action displacement increment three coordinate axes; specific formulas penalties optimization rewards are re-designed, which effectively avoids entering minimal points. The experimental results show with learning plan shorter paths exhibit better planning results. In addition, more adaptable scenes has anti-interference.

Language: Английский

Citations

0
An Optimized Method for Solving the Green Permutation Flow Shop Scheduling Problem Using a Combination of Deep Reinforcement Learning and Improved Genetic Algorithm DOI Creative Commons

Yongxin Lu,

Yiping Yuan, Yasenjiang Jiarula

et al.

Mathematics, Journal Year: 2025, Volume and Issue: 13(4), P. 545 - 545

Published: Feb. 7, 2025

This paper tackles the green permutation flow shop scheduling problem (GPFSP) with goal of minimizing both maximum completion time and energy consumption. It introduces a novel hybrid approach that combines end-to-end deep reinforcement learning an improved genetic algorithm. Firstly, PFSP is modeled using (DRL) approach, named PFSP_NET, which designed based on characteristics PFSP, actor–critic algorithm employed to train model. Once trained, this model can quickly directly produce relatively high-quality solutions. Secondly, further enhance quality solutions, outputs from PFSP_NET are used as initial population for (IGA). Building upon traditional algorithm, IGA utilizes three crossover operators, four mutation incorporates hamming distance, effectively preventing prematurely converging local optimal Then, optimize consumption, energy-saving strategy proposed reasonably adjusts job order by shifting jobs backward without increasing time. Finally, extensive experimental validation conducted 120 test instances Taillard standard dataset. By comparing method algorithms such (SGA), elite (EGA), (HGA), discrete self-organizing migrating (DSOMA), water wave optimization (DWWO), monkey search (HMSA), results demonstrate effectiveness method. Optimal solutions achieved in 28 instances, latest updated Ta005 Ta068 values 1235 5101, respectively. Additionally, experiments 30 including 20-10, 50-10, 100-10, indicate reduce

Language: Английский

Citations

0
Addressing Due Date and Storage Restrictions in the S-Graph Scheduling Framework DOI Creative Commons
Krisztián Attila Bakon, Tibor Holczinger

Machines, Journal Year: 2025, Volume and Issue: 13(2), P. 131 - 131

Published: Feb. 9, 2025

This paper addresses the Flexible Job Shop Scheduling Problem (FJSP) with objective of minimizing both earliness/tardiness (E/T) and intermediate storage time (IST). An extended S-graph framework that incorporates E/T IST minimization while maintaining structural advantages original approach is presented. The further enhanced by integrating linear programming (LP) techniques to adjust machine assignments operation timings dynamically. following four methodological approaches are systematically analyzed: a standalone for minimization, an combined hybrid LP comprehensive addressing IST. Computational experiments on benchmark problems demonstrate efficacy proposed methods, showing efficiency smaller instances offering improved solution quality more complex scenarios. research provides insights into trade-offs between computational across different problem configurations policies. work contributes field production scheduling versatile capable multi-objective nature modern manufacturing environments.

Language: Английский

Citations

0
A Q-learning-driven genetic algorithm for the distributed hybrid flow shop group scheduling problem with delivery time windows DOI

Qianhui Ji,

Yuyan Han, Yuting Wang

et al.

Information Sciences, Journal Year: 2025, Volume and Issue: unknown, P. 121971 - 121971

Published: Feb. 1, 2025

Language: Английский

Citations

0
Development and Design of an Optimal Fuzzy Logic Two Degrees of Freedom-Proportional Integral Derivative Controller for a Two-Area Power System Using the Bee Algorithm DOI Creative Commons

Sitthisak Audomsi,

Supannika Wattana, Narongkorn Uthathip

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(4), P. 915 - 915

Published: Feb. 14, 2025

This study introduces a fuzzy logic-based two-degree-of-freedom PID (FL2DOF-PID) controller that is optimized using the Bee Algorithm (BA) to control load frequency in two-area linked power system has both reheat thermal plants and hydro plants. To test how well it works, MATLAB/Simulink simulations compared with PID, 2DOF-PID controllers, looking at overshoot, undershoot, settling time, steady-state error integral of absolute (IAE). The results showed FL2DOF-PID had lowest RMSE (0.0054, 0.0089) MAE (0.0041, 0.0065), as smallest IAE (0.1308) overshoot (69.3% less). It also fastest time (5.1528 s) (0.1338 These works reduce changes, improve flow stability make whole more reliable under changing conditions.

Language: Английский

Citations

0
Deep reinforcement learning-based memetic algorithm for solving dynamic distributed green flexible job shop scheduling problem with finite transportation resources DOI
Xinxin Zhou, Feimeng Wang, Bin Wu

et al.

Swarm and Evolutionary Computation, Journal Year: 2025, Volume and Issue: 94, P. 101885 - 101885

Published: Feb. 21, 2025

Language: Английский

Citations

0
Mathematical modeling and optimization of multi-period fourth-party logistics network design problems with customer satisfaction-sensitive demand DOI
Yuxin Zhang, Min Huang, Yaping Fu

et al.

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127219 - 127219

Published: March 1, 2025

Language: Английский

Citations

0