Spindle thermal error modeling based on selective ensemble BP neural networks
- 38 Downloads
This paper proposes a modeling method based on selective ensemble BP neural networks for the thermal error of machine tool spindle. The fuzzy c-means clustering (FCM) algorithm and the correlation analysis were utilized in combination to select the temperature-sensitive points. A certain number of individual BP neural network models but with instable prediction performance were generated using different training sets and random initial parameters. Then, each individual BP neural network model was assigned a weight, and the genetic algorithm was used to evolve the weights. Afterwards, a prespecified threshold value was applied to select the individual BP neural network models to constitute the ensemble model. Taking a horizontal machining center THM6380 as an example, the thermal error experiment was carried out, and the prediction performance and generalization performance of the selective ensemble BP neural network model were compared with the single BP neural network model, the multiple linear regression (MLR) model, and the least-square support vector machine (LS-SVM) model. The comparison results indicated the superiority of the proposed modeling method, which provides a new idea for thermal error modeling and subsequent thermal error compensation of machine tool spindle.
KeywordsSpindle thermal error BP neural network Selective ensemble model Temperature-sensitive points Prediction performance
Unable to display preview. Download preview PDF.
This research was financially supported by the National Science and Technology Major Project of China (grant no. 2017ZX04020001-005) and the Science and Technology Support Plan Project of Sichuan Province, China (grant no. 2017GZ0057).
- 10.Guo QJ, Yang JG (2011) Application of projection pursuit regression to thermal error modeling of a CNC machine tool. Int J Adv Manuf Technol 55(5):623–629Google Scholar
- 14.Liang RJ, Ye WH, Zhang HY, Yang QF (2012) The thermal error optimization models for CNC machine tools. Int J Adv Manuf Technol 63(9):1167–1176Google Scholar
- 19.Ma C, Zhao L, Mei XS, Shi H, Yang J (2017) Error compensation based on genetic algorithm and artificial neural network of the shaft in the high-speed spindle system. P I Mech Eng B-J Eng 231(5):753–767Google Scholar
- 22.230-3 ISO (2007) Test code for machine tools part 3: determination of thermal effects. ISO copyright office, GenevaGoogle Scholar
- 28.Houck CR, Joines J, Kay MG (1995) A genetic algorithm for function optimization: a Matlab implementation. NCSU-IE TR 95(5):1–14Google Scholar