Neural network–based transfer learning to improve stiffness modeling of industrial robots with small experimental data sets

• Published in: International journal of advanced manufacturing technology Vol. 135; no. 11; pp. 5253 - 5265
• Main Authors: Wu, Kai, Zhang, Yuanhui, Gao, Dehua, Deng, Shuhan, Li, Weihua, Wang, Mingfeng
• Format: Journal Article
• Language: English
• Published: London Springer London 01.12.2024; Springer Nature B.V
• Subjects: Accuracy; CAE) and Design; Computer-Aided Engineering (CAD; Deformation effects; Dynamic loads; End effectors; Engineering; Industrial and Production Engineering; Industrial robots; Machine learning; Mechanical Engineering; Media Management; Modelling; Motion control; Multilayers; Original Article; Robot control; Robot dynamics; Robots; Stiffness; Virtual joint modeling; Industrial robots; Stiffness modeling; Transfer learning; Artificial neural networks

Stiffness modeling is an essential subject for the composition of robot control. Accurate stiffness modeling is helpful for improving the control accuracy of industrial robots, particularly under dynamic load circumstances. The classic virtual joint modeling (VJM) method is challenging in predicting...