Towards an Automated Application for Order Release
Procedia CIRP, vol. 107, pp. 1323–1328
Abstract
The demand for customer-specific product variants leads to a shift to job shop production, in which order scheduling takes a mayor role to increase logistical target values without ad-hoc interventions into the running production. Agent applications, e.g. combinations of reinforcement learning (RL) and simulation, are promising solutions to solve the scheduling problem. This paper designs a methodology for automating the order release decision of real production scenarios by applying a RL agent, which has been trained on an application-specific simulation model. By an integrated validation unit the performance can be measured against known order release strategies.
Authors 5
-
Affiliation as printed
Laboratory for Machine Tools and Production Engineering (WZL) of the RWTH Aachen University, Campus-Boulevard 30, 52074 Aachen, Germany
-
Affiliation as printed
Laboratory for Machine Tools and Production Engineering (WZL) of the RWTH Aachen University, Campus-Boulevard 30, 52074 Aachen, Germany
-
Affiliation as printed
Laboratory for Machine Tools and Production Engineering (WZL) of the RWTH Aachen University, Campus-Boulevard 30, 52074 Aachen, Germany
-
Affiliation as printed
Laboratory for Machine Tools and Production Engineering (WZL) of the RWTH Aachen University, Campus-Boulevard 30, 52074 Aachen, Germany
-
Affiliation as printed
Laboratory for Machine Tools and Production Engineering (WZL) of the RWTH Aachen University, Campus-Boulevard 30, 52074 Aachen, Germany
Cited by 2 stored of 2
2 results
No patents citing this paper on Lens.org (checked 2026-10-06).