Deep reinforcement learning in smart manufacturing: A review and prospects

CIRP journal of manufacturing science and technology, Journal Year: 2022, Volume and Issue: 40, P. 75 - 101

Published: Dec. 2, 2022

Language: Английский

---

Dynamic scheduling for flexible job shop using a deep reinforcement learning approach

Computers & Industrial Engineering, Journal Year: 2023, Volume and Issue: 180, P. 109255 - 109255

Published: April 21, 2023

Language: Английский

---

Integration of deep reinforcement learning and multi-agent system for dynamic scheduling of re-entrant hybrid flow shop considering worker fatigue and skill levels

Robotics and Computer-Integrated Manufacturing, Journal Year: 2023, Volume and Issue: 84, P. 102605 - 102605

Published: June 16, 2023

Language: Английский

---

Job shop smart manufacturing scheduling by deep reinforcement learning

Journal of Industrial Information Integration, Journal Year: 2024, Volume and Issue: 38, P. 100582 - 100582

Published: Feb. 9, 2024

Smart manufacturing scheduling (SMS) requires a high degree of flexibility to successfully cope with changes in operational decision level planning processes today's production environments, which are usually subject uncertainty. In such unique and complex scenario as the real job shop, modelling SMS Markov process (MDP), its approach by deep reinforcement learning (DRL), is research field growing interest given characteristics. It allows us consider achieving levels promoting automation, autonomy making, ability act time when faced disturbances disruptions highly dynamic environment. This paper addresses problem quasi-realistic shop environment characterised machines receiving jobs from buffers that accumulate numerous using wide variety parts multimachine routes diverse number operation phases developing digital twin based on MDP DRL methodology. approached by: OpenAI Gym; designing an observation space 18 features; action composed three priority heuristic rules; shaping single reward function multi-objective characteristic; implementation proximal policy optimisation (PPO) algorithm Stable Baselines 3 library. approach, dubbed smart (JS-SMS), deterministic formulation implementation. The model subjected validation comparing it several best-known rules. main findings this methodology allow replicate, great extent, positive aspects rules mitigate negative ones, achieves more balanced behaviour most measures established performance indicators outperforms perspective. Finally, further oriented stochastic approaches address reality Industry 4.0 context.

Language: Английский

---

DeepMAG: Deep reinforcement learning with multi-agent graphs for flexible job shop scheduling

Knowledge-Based Systems, Journal Year: 2022, Volume and Issue: 259, P. 110083 - 110083

Published: Nov. 3, 2022

Language: Английский

---

Dynamic distributed flexible job-shop scheduling problem considering operation inspection

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 224, P. 119840 - 119840

Published: March 11, 2023

Language: Английский

---

Dynamic production scheduling towards self-organizing mass personalization: A multi-agent dueling deep reinforcement learning approach

Journal of Manufacturing Systems, Journal Year: 2023, Volume and Issue: 68, P. 242 - 257

Published: April 9, 2023

Language: Английский

---

Scheduling of Resource Allocation Systems with Timed Petri Nets: A Survey

ACM Computing Surveys, Journal Year: 2022, Volume and Issue: 55(11), P. 1 - 27

Published: Nov. 3, 2022

Resource allocation systems (RASs) belong to a kind of discrete event system commonly seen in the industry. In such systems, available resources are allocated concurrently running processes optimize some performance criteria. Search strategies reachability graph (RG) timed Petri net (PN) attracted much attention past decades cope with RAS scheduling problems (RSPs), since PNs very suitable model and analyze RASs their RGs fully reflect systems’ behavior. However, there has been no existing related survey review paper till now. this work, we present tutorial comprehensive literature RG-based RSP methods. Many state-of-the-art reviewed summarized. First, framework RSPs classify terms resource usage structures. The differences relations among also given. Then, introduce PN construction methods for objectives search RSPs. Next, summarize different heuristic functions adopted frequently used A * solve Finally, discuss important future research directions open issues.

Language: Английский

---

Manufacturing in the Age of Human-Centric and Sustainable Industry 5.0: Application to Holonic, Flexible, Reconfigurable and Smart Manufacturing Systems

Sustainability, Journal Year: 2023, Volume and Issue: 15(13), P. 10169 - 10169

Published: June 27, 2023

This paper provides a classification of manufacturing types in terms new technological tools provided the Industry 5.0 framework. The agile, holonic, flexible and reconfigurable benefit from are potentially changed by 4.0 technologies human-centric focus 5.0. Furthermore, use Lifecycle Analysis (LCA) holistic method for estimating true value emissions emitted during carrying out decisions. As result, LCA may be used as central guiding framework, addition to Circular Economy metrics, decisions whose results could presented humans part scenario-generation system using visualisations within Digital Twin environment. enables decision maker make informed regarding current future production needs. Regardless size facility, this integrated approach is perhaps most significant gap research identified survey systems when viewed through lens makes contribution providing an assessment major context 5.0, highlighting gaps sustainable agenda supported with modern methodologies.

Language: Английский

---

Solving job shop scheduling problems via deep reinforcement learning

Applied Soft Computing, Journal Year: 2023, Volume and Issue: 143, P. 110436 - 110436

Published: May 20, 2023

Language: Английский

---