Offline digital twin for simulation and assessment of product surface quality.

Product surface quality which significantly influences a product's wear resilience and fatigue strength is an important technical characteristic. A frequently used indicator of surface quality, precise mating surface fit, and fatigue life is average surface roughness. Unstable machining leads to an unacceptable surface roughness of the workpieces. Effective surface quality control is significant in improving machining efficiency and reducing costs. A method for controlling the quality of product surfaces based on an offline digital twin and artificial intelligence is developed. To reduce average surface roughness, genetic algorithms are used to optimize machining settings. Actual machining data is used to test and validate the digital twin developed. The simulated results agree with the machining trials results and the root means square error is found to be between 0.128 and 0.135 µm. The developed offline digital twin accurately predicts the surface finish and significantly improves manufacturing and production intelligence. [ABSTRACT FROM AUTHOR]