Reinforcement learning in real-time geometry assurance
| Autor: | Oskar Wigstrom, Lucas Brynte, Emilio Jorge, Constantin Cronrath, Kristofer Bengtsson, Bengt Lennartson, Mats Jirstrand, Emil Gustavsson |
|---|---|
| Přispěvatelé: | Publica |
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
0209 industrial biotechnology
Computer science business.industry media_common.quotation_subject Geometry 02 engineering and technology 010501 environmental sciences computer.software_genre 01 natural sciences Expert system System model 020901 industrial engineering & automation Software General Earth and Planetary Sciences Production (economics) Reinforcement learning Quality (business) Limit (mathematics) business Advice (complexity) computer 0105 earth and related environmental sciences General Environmental Science media_common |
| Popis: | To improve the assembly quality during production, expert systems are often used. These experts typically use a system model as a basis for identifying improvements. However, since a model uses approximate dynamics or imperfect parameters, the expert advice is bound to be biased. This paper presents a reinforcement learning agent that can identify and limit systematic errors of an expert systems used for geometry assurance. By observing the resulting assembly quality over time, and understanding how different decisions affect the quality, the agent learns when and how to override the biased advice from the expert software. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|