Litcius/Paper detail

Automated scenario analysis of reinforcement learning controlled line-less assembly systems

Amon Göppert, Jonas Rachner, Robert Schmitt

2020Procedia CIRP16 citationsDOIOpen Access PDF

Abstract

The concept of line-less matrix-structured assembly systems with dynamical job routes is an alternative concept to line configurations with a promising performance for complex production scenarios. Due to the dynamical environment, fast online decisions for controlling the job routes are required. A reinforcement-learning algorithm based on Monte Carlo tree search for time-efficient online decision-making is proposed. For the performance comparison of matrix assembly systems with line configurations, a seamlessly automated scenario analysis tool generates, simulates and processes the results for a large set of assembly scenarios. The results show a significant improvement in the utilization of work stations especially for a high number of variants.

Topics & Concepts

Reinforcement learningComputer scienceSet (abstract data type)Line (geometry)Monte Carlo methodAssembly lineMatrix (chemical analysis)Decision treeTree (set theory)Distributed computingIndustrial engineeringMachine learningEngineeringMathematicsMathematical analysisMechanical engineeringComposite materialGeometryStatisticsMaterials scienceProgramming languageAssembly Line Balancing OptimizationScheduling and Optimization AlgorithmsManufacturing Process and Optimization
Automated scenario analysis of reinforcement learning controlled line-less assembly systems | Litcius