Multi-objective optimization of the textile manufacturing process using deep-Q-network based multi-agent reinforcement learning

He, Zhenglei; Tran, Kim Phuc; Thomassey, Sébastien; Zeng, Xiaoyang; Xu, Jie; Yi, Changhai

doi:10.1016/j.jmsy.2021.03.017

Cited by 48 publications

(14 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fonseca et al [19] applied Q-learning to study the flow job shop scheduling problem (FSP) for minimum completion time. He et al [20] solved the dynamic FSP (DFSP) for minimum cost and energy consumption, in the context of the textile industry, using multiple deep Q-network (DQN) agents. Shahrabi et al [21] solved the dynamic JSP (DJSP) to minimize average flow time via Q-learning, dynamically adjusting the parameters of a variable neighborhood search algorithm.…”

Section: Related Workmentioning

confidence: 99%

Hierarchical Reinforcement Learning for Multi-Objective Real-Time Flexible Scheduling in a Smart Shop Floor

Chang

Zheng

et al. 2022

Machines

View full text Add to dashboard Cite

With the development of intelligent manufacturing, machine tools are considered the “mothership” of the equipment manufacturing industry, and the associated processing workshops are becoming more high-end, flexible, intelligent, and green. As the core of manufacturing management in a smart shop floor, research into the multi-objective dynamic flexible job shop scheduling problem (MODFJSP) focuses on optimizing scheduling decisions in real time according to changes in the production environment. In this paper, hierarchical reinforcement learning (HRL) is proposed to solve the MODFJSP considering random job arrival, with a focus on achieving the two practical goals of minimizing penalties for earliness and tardiness and reducing total machine load. A two-layer hierarchical architecture is proposed, namely the combination of a double deep Q-network (DDQN) and a dueling DDQN (DDDQN), and state features, actions, and external and internal rewards are designed. Meanwhile, a personal computer-based interaction feature is designed to integrate subjective decision information into the real-time optimization of HRL to obtain a satisfactory compromise. In addition, the proposed HRL framework is applied to multi-objective real-time flexible scheduling in a smart gear production workshop, and the experimental results show that the proposed HRL algorithm outperforms other reinforcement learning (RL) algorithms, metaheuristics, and heuristics in terms of solution quality and generalization and has the added benefit of real-time characteristics.

show abstract

Section: Related Workmentioning

confidence: 99%

Hierarchical Reinforcement Learning for Multi-Objective Real-Time Flexible Scheduling in a Smart Shop Floor

Chang

Zheng

et al. 2022

Machines

View full text Add to dashboard Cite

show abstract

“…Gloy et al (2015) have addressed the optimization of the weaving process, proposing a model for self-optimization that leads to the most efficient weaving machine usage. He et al (2022), similar to the authors mentioned in Table 2, recently envisioned a multi-agent reinforcement learning methodology to deal with the complex textile manufacturing process, understanding it as a multi-objective optimization problem. The authors also applied this methodology to a case study, focusing on the color-fading process.…”

Section: Literature Reviewmentioning

confidence: 99%

A simultaneous balancing and sequencing algorithm to plan assembly lines in the fashion industry

Perret

2022

RJTA

View full text Add to dashboard Cite

Purpose The purpose of the study is to fill a gap in the literature on mathematical production planning (joint balancing and sequencing) in the fashion industry. It considers in particular situations of mass customization, made-to-measure or small lot sizes. Design/methodology/approach The paper develops a mathematical model based on product options and attributes instead of fixed variants. It proposes an easy-to-use genetic algorithm to solve the resulting optimization problem. Functionality and performance of the algorithm are illustrated via a computational study. Findings An easy-to-implement, yet efficient algorithm to solve the multi-objective implementation of a problem structure that becomes increasingly relevant in the fashion industry is proposed. Implementation of the algorithm revealed that the algorithm is ideally suited to generate significant savings and that these savings are impervious to problem and thus company size. Practical implications The solutions from the algorithm (Pareto-efficient frontier) offer decision-makers more flexibility in selecting those solutions they deem most fitting for their situation. The computational study illustrates the significant monetary savings possible by implementing the proposed algorithm to practical situations. Originality/value In contrast to existing papers, for the first time, to the best of the author’s knowledge, the focus of the joint balancing and sequencing approach has been applied in the fashion instead of the automotive industry. The applicability of the approach to specific fields of the fashion industry is discussed. An option and attributes-based model, rarely used in general assembly line sequencing per se, is used for more flexibility in representing a diverse set of model types.

show abstract

“…Nouiri et al set up a flexible workshop-scheduling multitarget optimization model with the processing time, energy cost, and machine completion time of sand-casting as optimization targets [ 22 ]. However, traditional heuristic algorithms do not perform well in the face of the large number of complex parameter variables and high-dimensional decision space in the process industry [ 23 ]. In contrast, deep reinforcement learning (DRL) has shown better optimization performance than heuristic algorithms in many fields [ 24 ].…”

Section: Introductionmentioning

confidence: 99%

Multi-Objective Optimization of Sugarcane Milling System Operations Based on a Deep Data-Driven Model

Chen

Meng

et al. 2022

Foods

View full text Add to dashboard Cite

The extraction of sugarcane juice is the first step of sugar production. The optimal values of process indicators and the set values of operating parameters in this process are still determined by workers’ experience, preventing adaptive adjustment of the production process. To address this issue, a multi-objective optimization framework based on a deep data-driven model is proposed to optimize the operation of sugarcane milling systems. First, the sugarcane milling process is abstracted as the interaction of material flow, energy flow, and information flow (MF–EF–IF) by introducing synergetic theory, and each flow’s order parameters and state parameters are obtained. Subsequently, the state parameters of the subsystems are taken as inputs, and the order parameters—including the grinding capacity, electric consumption per ton of sugarcane, and sucrose extraction—are produced as outputs. A collaborative optimization model of the MF–EF–IF of the milling system is established by using a deep kernel extreme learning machine (DK-ELM). The established milling system model is applied for an improved multi-objective chicken swarm optimization (IMOCSO) algorithm to obtain the optimal values of the order parameters. Finally, the milling process is described as a Markov decision process (MDP) with the optimal values of the order parameters as the control objectives, and an improved deep deterministic policy gradient (DDPG) algorithm is employed to achieve the adaptive optimization of the operating parameters under different working conditions of the milling system. Computational experiments indicate that enhanced performance is achieved, with an increase of 3.2 t per hour in grinding capacity, a reduction of 660 W per ton in sugarcane electric consumption, and an increase of 0.03% in the sucrose extraction.

show abstract

Multi-objective optimization of the textile manufacturing process using deep-Q-network based multi-agent reinforcement learning

Cited by 48 publications

References 53 publications

Hierarchical Reinforcement Learning for Multi-Objective Real-Time Flexible Scheduling in a Smart Shop Floor

Hierarchical Reinforcement Learning for Multi-Objective Real-Time Flexible Scheduling in a Smart Shop Floor

A simultaneous balancing and sequencing algorithm to plan assembly lines in the fashion industry

Multi-Objective Optimization of Sugarcane Milling System Operations Based on a Deep Data-Driven Model

Contact Info

Product

Resources

About