Hybrid approach for the integrated scheduling of production and transport processes along supply chains

Frazzon, Enzo Morosini; Albrecht, André; Pires, Matheus Cardoso; Israel, Eduardo; Kück, Mirko; Freitag, Michael

doi:10.1080/00207543.2017.1355118

Cited by 72 publications

(32 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While Industry 4.0 technology has enabled new production strategies that require highly customised supply network control (Ivanov et al 2016), another trend is the creation of resilient supply chains to cope with risks (Olson and Wu 2015, Dolgui et al 2018, Ivanov 2018. The ultimate objective of plans and future developments is therefore to facilitate developments in management DSSs for the design, scheduling and control of resilient and digital manufacturing networks and production systems (Frazzon et al 2017, Amodeo et al 2018. The vision of the overall contribution from the research community in manufacturing and logistics systems, over the next few years is to bring together researchers and practitioners presenting and discussing topics in modern manufacturing modelling, management and control in the emerging field of Industry 4.0-based resilient and innovative production SoS and supply networks (Battaïa et al 2018).…”

Section: Discussionmentioning

confidence: 99%

Challenges for the cyber-physical manufacturing enterprises of the future

Panetto

Iung

Ivanov

et al. 2019

Annual Reviews in Control

249

View full text Add to dashboard Cite

This paper summarizes a vision of the challenges facing the so-called "Industry of the Future" as studied by the research community of the IFAC Coordinating Committee 5 on Manufacturing and Logistics Systems, which includes four Technical Committees (TC). Each TC brings its own vision and puts forward trends and issues important and relevant for future research. The analysis is performed on the enterprise-level topics with an interface too other relevant systems (e.g., supply chains). The vision developed might lead to the identification of new scientific control directions such as Industry 4.0 technology-enabled new production strategies that require highly customised supply network control, the creation of resilient enterprise to cope with risks, developments in management decision-support systems for the design, and scheduling and control of resilient and digital manufacturing networks, and collaborative control. Cobots, augmented reality and adaptable workstations are a few examples of how production and logistic systems are changing supporting the operator 4.0. Sustainable manufacturing techniques, such closed-loop supply chains, is another trend in this area. Due to increasing number of elements and systems, complex and heterogeneous enterprise systems need to be considered (e.g., for decision-making). These systems are heterogeneous and build by different stakeholders. To make use of these, an environment is needed that allows the integration of the systems forming a System-of-Systems (SoS). The changing environment requires models which adapt over time. Some of the adaptation is due to learning, other mechanisms include self-organisation by intelligent agents. In general, models and systems need to be modular and support modification and (self-)adaptation. An infrastructure is needed that supports loose coupling and evolving systems of systems. The vision of the overall contribution from the research community in manufacturing and logistics systems, over the next few years is to bring together researchers and practitioners presenting and discussing topics in modern manufacturing modelling, management and control in the emerging field of Industry 4.0-based resilient and innovative production SoS and supply networks.

show abstract

Section: Discussionmentioning

confidence: 99%

Challenges for the cyber-physical manufacturing enterprises of the future

Panetto

Iung

Ivanov

et al. 2019

Annual Reviews in Control

249

View full text Add to dashboard Cite

show abstract

“…Blockchain-based contracts lead to greater assurance, lower information asymmetry, and real-time information which reduces uncertainties, risks, and transaction costs (Schmidt & Wagner, 2019 ; Kamilaris, Fonts & Prenafeta-Boldu, 2019 ). Integration of computer systems, or the ability of the MNE to monitor, at any time, the status of the vendor’s production by accessing their servers, reduces uncertainty and helps schedule the MNE’s own sales, inventories, and other processes (Frazzon et al, 2018 ). Systems integrated via 5G will further reduce GVC risks by providing real-time information in transportation pathways (Rundle, 2020 ).…”

Section: The Continuing Rationales Of International Businessmentioning

confidence: 99%

The world economy will need even more globalization in the post-pandemic 2021 decade

Contractor

2021

J Int Bus Stud

129

View full text Add to dashboard Cite

“…Scheduling can be viewed as a decision making process, in which the scheduling arranges the tasks that we should process sequentially. Moreover, scheduling is also an essential task in many application domains, including manufacturing [13], [43], [44], network [40] and supply chains [12], [36]. For example, Wang et al [36] considered production and distribution in supply chain management, and focused on the permutation flow shop scheduling problem, which addressed the problem of batch delivery to multiple customers.…”

Section: Introductionmentioning

confidence: 99%

Actor-Critic Deep Reinforcement Learning for Solving Job Shop Scheduling Problems

Liu

Chang²,

Tseng³

2020

IEEE Access

162

View full text Add to dashboard Cite

In the past decades, many optimization methods have been devised and applied to job shop scheduling problem (JSSP) to find the optimal solution. Many methods assumed that the scheduling results were applied to static environments, but the whole environments in the real world are always dynamic. Moreover, many unexpected events such as machine breakdowns and material problems may be present to adversely affect the initial job scheduling. This work views JSSP as a sequential decision making problem and proposes to use deep reinforcement learning to cope with this problem. The combination of deep learning and reinforcement learning avoids handcraft features as used in traditional reinforcement learning, and it is expected that the combination will make the whole learning phase more efficient. Our proposed model comprises actor network and critic network, both including convolution layers and fully connected layer. Actor network agent learns how to behave in different situations, while critic network helps agent evaluate the value of statement then return to actor network. This work proposes a parallel training method, combining asynchronous update as well as deep deterministic policy gradient (DDPG), to train the model. The whole network is trained with parallel training on a multi-agent environment and different simple dispatching rules are considered as actions. We evaluate our proposed model on more than ten instances that are present in a famous benchmark problem library-OR library. The evaluation results indicate that our method is comparative in static JSSP benchmark problems, and achieves a good balance between makespan and execution time in dynamic environments. Scheduling score of our method is 91.12% in static JSSP benchmark problems, and 80.78% in dynamic environments. INDEX TERMS Job shop scheduling problem (JSSP), deep reinforcement learning, actor-critic network, parallel training.

show abstract

Hybrid approach for the integrated scheduling of production and transport processes along supply chains

Cited by 72 publications

References 71 publications

Challenges for the cyber-physical manufacturing enterprises of the future

Challenges for the cyber-physical manufacturing enterprises of the future

The world economy will need even more globalization in the post-pandemic 2021 decade

Actor-Critic Deep Reinforcement Learning for Solving Job Shop Scheduling Problems

Contact Info

Product

Resources

About