Experimental Study of Surface Roughness of Pine Wood by High-Speed Milling

Abstract

The surface roughness of wood has a great influence on its performance and is a very important indicator in processing and manufacturing. In this paper, we use the central composite design experiment (CCD experiment) and artificial neural network (ANN) model to study the changing pattern of surface roughness during the high-speed milling process of pine wood. In the CCD experiments, the spindle speed, feed speed, and depth of cut are used as the influencing factors, and the surface roughness is used as the index to analyze the variation law and fit the surface roughness parameter equation. By measuring the chip size in each group in the CCD experiment, the ANN model is used to predict the surface roughness under this machining parameter by measuring the chip size in each test group. The experimental results showed that the mean error of the surface roughness prediction values in the CCD experiment (12.2%) was larger than that of the ANN model (7.8%), and the mean squared error (MSE) of the ANN model was 0.025, the mean absolute percentage error(MAPE) was 0.01, and the coefficient of determination R2 was 0.95. Compared with the CCD experiment, the ANN model had a higher prediction accuracy. The results of this paper can provide some guidance for the prediction of surface roughness during wood processing.

Structural Optimization Design of Dual Robot Gripper Unloading Device Based on Intelligent Optimization Algorithms and Generative Design

“…A central composite design (CCD) [39,40] was employed to explore the entire design space. The core idea of CCD is to select a central point and a series of factor variable levels and to construct a set of experimental points to cover the range of variable values.…”