Double deep Q-network-based self-adaptive scheduling approach for smart shop floor

Ma, Yumin; Cai, Jingwen; Li, Shengyi; Liu, Juan; Xing, Jun; Qiao, Fei

doi:10.1007/s00521-023-08877-3

Cited by 2 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other popular areas of proposed DRL applications are order selection and scheduling, in particular, dynamic scheduling [19,25]. In [31], a self-adaptive scheduling approach based on DDQN is proposed. To validate the effectiveness of the self-adaptive scheduling approach, the simulation model of a semiconductor production demonstration unit was used.…”

Section: Deep Reinforcement Learning In Production Systemsmentioning

confidence: 99%

“…This gap motivated research in the area of using DTs of production systems based on modern computer discrete simulation systems as an environment for the interaction of reinforced machine learning agents, the results of which are presented in this paper. Additionally, many studies provide the parameters of the RL algorithms used (e.g., [31]). Still, there is no analysis or discussion of the impact of their values on the results obtained or the speed of the training process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Reinforcement Learning and Discrete Simulation-Based Digital Twin for Cyber–Physical Production Systems

Krenczyk

2024

Applied Sciences

View full text Add to dashboard Cite

One of the goals of developing and implementing Industry 4.0 solutions is to significantly increase the level of flexibility and autonomy of production systems. It is intended to provide the possibility of self-reconfiguration of systems to create more efficient and adaptive manufacturing processes. Achieving such goals requires the comprehensive integration of digital technologies with real production processes towards the creation of the so-called Cyber–Physical Production Systems (CPPSs). Their architecture is based on physical and cybernetic elements, with a digital twin as the central element of the “cyber” layer. However, for the responses obtained from the cyber layer, to allow for a quick response to changes in the environment of the production system, its virtual counterpart must be supplemented with advanced analytical modules. This paper proposes the method of creating a digital twin production system based on discrete simulation models integrated with deep reinforcement learning (DRL) techniques for CPPSs. Here, the digital twin is the environment with which the reinforcement learning agent communicates to find a strategy for allocating processes to production resources. Asynchronous Advantage Actor–Critic and Proximal Policy Optimization algorithms were selected for this research.

show abstract

Section: Deep Reinforcement Learning In Production Systemsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%