Reinforcement Learning for Short-Term Production Scheduling with Sequence-Dependent Setup Waste

摘要

Continually?refined?and?adjusted?methods?for?production?planning?are?among?the?cornerstones?of?manufacturingexcellence.?Heuristics?and?metaheuristic?methods?developed?to?address?these?tasks?are?often?hard?to?deploy?orlead?to?suboptimal?results?under?constantly?changing?conditions?combined?with?short?response?times?of?modernproduction?planning.?Within?the?DFG-funded?Cluster?of?Excellence?“Internet?of?Production”,?a?team?of?researchersfrom?RWTH?Aachen?University?is?investigating?the?use?of?novel?deep?learning?algorithms?to?facilitate?complexdecision-making?processes?along?the?manufacturing?chain.