A multi-objective reinforcement learning approach for resequencing scheduling problems in automotive manufacturing systems

Leng, Jinling; Wang, Xingyuan; Wu, Shaochuan; Jin, Chun; Tang, Meng; Li, Rui; Vogl, Alexander; Liu, Huiyu

doi:10.1080/00207543.2022.2098871

Cited by 16 publications

(5 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Non-dominated sorting genetic algorithms and other algorithms based on the genetic algorithm combine the use the random numbers and information from previous iterations to evaluate and improve a population of points [ 25 ]. Recently, the Pareto Q-learning algorithm was used for solving MOO, learning deterministic, non-stationary, and non-dominated multi-objective policies while mapping the entire Pareto front [ 26 , 27 ].…”

Section: Related Workmentioning

confidence: 99%

A Bi-Objective Home Health Care Routing and Scheduling Problem under Uncertainty

Zhao,

Wang,

Monteiro

2024

IJERPH

View full text Add to dashboard Cite

Home health care companies provide health care services to patients in their homes. Due to increasing demand, the provision of home health care services requires effective management of operational costs while satisfying both patients and caregivers. In practice, uncertain service times might lead to considerable delays that adversely affect service quality. To this end, this paper proposes a new bi-objective optimization problem to model the routing and scheduling problems under uncertainty in home health care, considering the qualification and workload of caregivers. A mixed-integer linear programming formulation is developed. Motivated by the challenge of computational time, we propose the Adaptive Large Neighborhood Search embedded in an Enhanced Multi-Directional Local Search framework (ALNS-EMDLS). A stochastic ALNS-EMDLS is introduced to handle uncertain service times for patients. Three kinds of metrics for evaluating the Pareto fronts highlight the efficiency of our proposed method. The sensitivity analysis validates the robustness of the proposed model and method. Finally, we apply the method to a real-life case and provide managerial recommendations.

show abstract

Section: Related Workmentioning

confidence: 99%

A Bi-Objective Home Health Care Routing and Scheduling Problem under Uncertainty

Zhao,

Wang,

Monteiro

2024

IJERPH

View full text Add to dashboard Cite

show abstract

“…With the objective of improving scheduling efficiency and diminishing operating costs, Leng et al (2022) developed a multi-objective DQN algorithm to determine the Pareto frontier. The purpose of reward shaping is to enhance the convergence of the neural network.…”

Section: Applications Of ML In Solving Scheduling Problemsmentioning

confidence: 99%

Enhancing multi-objective evolutionary algorithms with machine learning for scheduling problems: recent advances and survey

Zhang,

Xiao,

Gen

et al. 2024

Front. Ind. Eng.

View full text Add to dashboard Cite

Multi-objective scheduling problems in workshops are commonly encountered challenges in the increasingly competitive market economy. These scheduling problems require a trade-off among multiple objectives such as time, energy consumption, and product quality. The importance of each optimization objective typically varies in different time periods or contexts, necessitating decision-makers to devise optimal scheduling plans accordingly. In actual production, decision-makers confront intricate multi-objective scheduling problems that demand balancing clients’ requirements and corporate interests while concurrently striving to reduce production cycles and costs. In solving various problems, multi-objective evolutionary algorithms have attracted the attention of researchers and gradually become one of the mainstream methods to solve these problems. In recent years, research combining multi-objective evolutionary algorithms with machine learning technology has shown great potential, opening up new prospects for improving the performance of multi-objective evolutionary methods. This article comprehensively reviews the latest application progress of machine learning in multi-objective evolutionary algorithms for scheduling problems. We review various machine learning techniques employed for enhancing multi-objective evolutionary algorithms, particularly focusing on different types of reinforcement learning methods. Different categories of scheduling problems addressed using these methods were also discussed, including flow-shop scheduling issues, job-shop scheduling challenges, and more. Finally, we highlighted the challenges faced by the field and outlined future research directions.

show abstract

“…Besides the printing industry, the PCPSP is rich in application possibilities, such as pharmaceutical packaging facility [26], printed circuit boards (PCBs) [27], automotive paint shops [22], [28], [29], [30], the printing and dyeing industry [31], [32], personalized printing design for artworks and so on. The reason is that the color batching problem has a great impact on the scheduling in these fields.…”

Section: Related Workmentioning

confidence: 99%

A Job Sequence Optimization Approach for Parallel Machine Scheduling Problem in Printing Manufacturing Systems

Li,

Zheng,

Sun

et al. 2024

IEEE Access

View full text Add to dashboard Cite

This paper investigated a parallel machine scheduling problem in the printing manufacturing systems due to operational requirements on the color-batching of the printed matter and sequential requirements on the sequence adherence of a printing press. Resequencing printing jobs as color-oriented batches reduced the costs of color changes and operational costs for printing shop. Also, post press workshop required printing shops to print jobs with minimal makespan so that high sequence adherence with its demand is assured. Based on real-world applications, we investigated two contradictory objectives-color change costs and minimal makespan-in a parallel high-fidelity printing press scheduling environment. A job sequence optimization approach is proposed. Moving interpolation algorithm and color sequence mapping algorithm are designed to reduce frequency of replacing ink. Base on iterative greedy algorithm, color sequence job groups with the same or similar color sequence are scheduled to the printing presses. Three experiments are conducted and showed that the proposed approach has good feasibility and effectiveness, and convergence in solving minimum completion time. Therefore, the proposed approach can be used in printing shops to improve scheduling efficiency and reduce production costs.INDEX TERMS Printing manufacturing systems; parallel machine scheduling problem; minimal makespan; color sequence comparison; iterated greedy algorithm

show abstract

A multi-objective reinforcement learning approach for resequencing scheduling problems in automotive manufacturing systems

Cited by 16 publications

References 36 publications

A Bi-Objective Home Health Care Routing and Scheduling Problem under Uncertainty

A Bi-Objective Home Health Care Routing and Scheduling Problem under Uncertainty

Enhancing multi-objective evolutionary algorithms with machine learning for scheduling problems: recent advances and survey

A Job Sequence Optimization Approach for Parallel Machine Scheduling Problem in Printing Manufacturing Systems

Contact Info

Product

Resources

About