Multi-Agent Based Hyper-Heuristics for Multi-Objective Flexible Job Shop Scheduling: A Case Study in an Aero-Engine Blade Manufacturing Plant

Zhou, Yong; Yang, Jianjun; Zheng, Lianyu

doi:10.1109/access.2019.2897603

Cited by 36 publications

(19 citation statements)

References 98 publications

(117 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The authors of [ 11 ] presented an industrial application connected to an aero-engine blade manufacturing factory which produces different kinds of aero-engines for jet fighter, transport aircraft and passenger planes. The authors found a certain problem of bottleneck through the rough-cut capability planning in the MES while using a 4-axis CNC milling machine.…”

Section: Literature Reviewmentioning

confidence: 99%

“…plays a significant role in the daily on-time operation of modern enterprises [ 9 ]. As it was mentioned in [ 10 , 11 ], producing companies have relied heavily on manual feedback in MES in the past decade. Nevertheless, expansions of new technologies such as CPSs and IoT have allowed producing companies to collect data from multiple data sources through Radio Frequency Identification Devices (RFID), bar code, Manufacturing Data Collection (MDC), and other data acquisition systems, it was enumerated in [ 10 , 11 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Personalization of the MES System to the Needs of Highly Variable Production

Zwolińska

Tubis

Chamier-Gliszczyński

et al. 2020

Sensors

View full text Add to dashboard Cite

The new generation Manufacturing Executions System (MES) is considered as one of the most important solutions supporting the idea of Industry 4.0. This is confirmed by research conducted among companies interested in the implementation of the Industry 4.0 concept, as well as the publications of researchers who study this issue. However, if MES software is a link that connects the world of machines and business systems, it must take into account the specifics of the supported production systems. This is especially true in case of production systems with a high level of automation, which are characterised by flexibility and agility at the operational level. Therefore, personalization of the MES software is proposed for this class of production systems. The aim of the article is to present the MES system personalization method for a selected production system. The proposed approach uses the rules of Bayesian inference and the area of customisation is the technological structure of production, taking into account the required flexibility of the processes. As part of the developed approach, the variability index was proposed as a parameter evaluating the effectiveness of the production system. Then, the results of evaluation of the current system effectiveness by use of this index are presented. The authors also present the assumptions for the developed MES personalization algorithm. The algorithm uses the rules of Bayesian inference, which enable multiple adjustments of the model to the existing environmental conditions without the need to formulate a new description of reality. The application of the presented solution in a real facility allowed for determining production areas which are the determinants of system instability. The implementation of the developed algorithm enabled control of the generated variability in real time. The proposed approach to personalization of MES software for a selected class of production systems is the main novelty of the presented research and contributes to the development of the described area of research.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Personalization of the MES System to the Needs of Highly Variable Production

Zwolińska

Tubis

Chamier-Gliszczyński

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…to cope with complex problems, MAM has become an effective and popular paradigm penetrating into the field of supply chain. With respect to MAM, many problems on supply chain have been studied, such as platform supply chain networks [38], [39], production scheduling [40], [41], and products management [42], [43].…”

Section: Literature Reviewmentioning

confidence: 99%

Backup or Reliability Improvement Strategy for a Manufacturer Facing Heterogeneous Consumers in a Dynamic Supply Chain

Jiang

2019

IEEE Access

View full text Add to dashboard Cite

This paper examines a manufacturer's supply management strategies for mitigating yield risk in a complex dynamic supply chain. Two strategies can be adopted for the manufacturer: backup and reliability improvement. Consumers may select to leave (instant consumers) or wait (delaying consumers) when they confront the manufacturer's insufficient inventory. Utilizing the method of multi-agent modeling, a manufacturer and a supplier are modeled as the intelligent agents with the reinforcement learning behavior. The study shows that: 1) when the number of instant consumers is small, reliability improvement strategy should be selected; otherwise, the manufacturer should adopt a backup strategy; 2) only when mean yield is large enough, reliability improvement strategy is the optimal choice; and 3) if yield uncertainty is small, the manufacturer should choose reliability improvement strategy; otherwise, it is suitable to use a backup strategy. In addition, when the main supplier can determine its own wholesale price, it is found that: 1) when the mean yield is small, a lower wholesale price should be designed for the main supplier, to induce higher order quantity under backup strategy; and 2) the impact of yield uncertainty on the manufacturer's supply management strategy can be changed by the main supplier's adaptive pricing behavior. INDEX TERMS Consumer behavior, multi-agent modeling, supply chain management, yield risk.

show abstract

“…Lu et al [21] employed a cellular grey wolf optimizer (GWO) for the multi-objective scheduling problem with the objectives of noise and energy, while Qin et al [22] tried to overcome the premature convergence of the GWO in solving MOJSSP by combining an improved tabu search algorithm. Zhou et al [23] proposed three agent-based hyper-heuristics to solve scheduling policies with constrains of dynamic events. Fu et al [24] designed a multi-objective brain storm optimization algorithm to minimize the total tardiness and energy consumption.…”

Section: Literature Reviewmentioning

confidence: 99%

A Hybrid Machine Learning and Population Knowledge Mining Method to Minimize Makespan and Total Tardiness of Multi-Variety Products

Qiu

Zhang

2019

Applied Sciences

View full text Add to dashboard Cite

Nowadays, the production model of many enterprises is multi-variety customized production, and the makespan and total tardiness are the main metrics for enterprises to make production plans. This requires us to develop a more effective production plan promptly with limited resources. Previous research focuses on dispatching rules and algorithms, but the application of the knowledge mining method for multi-variety products is limited. In this paper, a hybrid machine learning and population knowledge mining method to minimize makespan and total tardiness for multi-variety products is proposed. First, through offline machine learning and data mining, attributes of operations are selected to mine the initial population knowledge. Second, an addition–deletion sorting method (ADSM) is proposed to reprioritize operations and then form the rule-based initial population. Finally, the nondominated sorting genetic algorithm II (NSGA-II) hybrid with simulated annealing is used to obtain the Pareto solutions. To evaluate the effectiveness of the proposed method, three other types of initial populations were considered under different iterations and population sizes. The experimental results demonstrate that the new approach has a good performance in solving the multi-variety production planning problems, whether it is the function value or the performance metric of the acquired Pareto solutions.

show abstract

Multi-Agent Based Hyper-Heuristics for Multi-Objective Flexible Job Shop Scheduling: A Case Study in an Aero-Engine Blade Manufacturing Plant

Cited by 36 publications

References 98 publications

Personalization of the MES System to the Needs of Highly Variable Production

Personalization of the MES System to the Needs of Highly Variable Production

Backup or Reliability Improvement Strategy for a Manufacturer Facing Heterogeneous Consumers in a Dynamic Supply Chain

A Hybrid Machine Learning and Population Knowledge Mining Method to Minimize Makespan and Total Tardiness of Multi-Variety Products

Contact Info

Product

Resources

About