6533b839fe1ef96bd12a6407

RESEARCH PRODUCT

Prediction-Based Assembly Assistance System

Stefan-alexandru PrecupConstantin-bala ZamfirescuArpad GellertBogdan-constantin Pîrvu

subject

0209 industrial biotechnologyMarkov chainComputer sciencebusiness.industry02 engineering and technologycomputer.software_genreAutomationMechanism (engineering)020901 industrial engineering & automationProduct (mathematics)0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingData miningHardware_CONTROLSTRUCTURESANDMICROPROGRAMMINGbusinesscomputer

description

This paper presents the design of a prediction-based assembly assistance system for manual operations and the results obtained on the data collected from experiments of assembling a customizable product. We integrated into the proposed system a Markov predictor improved with a padding mechanism whose role is to recommend the next assembly step and to detect the worker’s errors. The predictor is trained with correct assembly patterns and tested with real assembly/manufacturing data. The proposed predictor improves the coverage and, thus, there is a significantly higher number of assembly steps which are correctly correlated with the real intentions of the workers.

yearjournalcountryeditionlanguage
2020-09-012020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)
https://doi.org/10.1109/etfa46521.2020.9212170