With the continuous improvement of the performance of modern aerospace aircraft, the overall strength and lightweight control of aircraft has become a significant feature of modern aerospace parts. With the wide application of thin-walled parts, the requirements for dimensional accuracy and surface quality of workpieces are increasing. In this paper, a numerical model for predicting surface topography of thin-walled parts after elastic deformation is proposed. In view of the geometric characteristics in the cutting process, the cutting force model of thin-walled parts is established, and the meshing relationship between the tool and the workpiece is studied. In addition, the influence of workpiece deformation is considered based on the beam deformation model. Cutting force is calculated based on deformed cutting thickness, and the next cutting–meshing relationship is predicted. The model combines the radial deflection of the workpiece in the feed direction and the changing meshing relationship of the tool–workpiece to determine the three-dimensional topography of the workpiece. The error range between the experimental and the simulation results of surface roughness is 7.45–13.09%, so the simulation three-dimensional morphology has good similarity. The surface topography prediction model provides a fast solution for surface quality control in the thin-walled parts’ milling process.

No abstract

No abstract

Generally, off-line methods are used for surface roughness prediction of titanium alloy milling. However, studies show that these methods have poor prediction accuracy. In order to resolve this shortcoming, a prediction method based on Cloudera's Distribution Including Apache Hadoop (CDH) platform is proposed in the present study. In this regard, data analysis and process platform is designed based on the CDH, which can upload, calculate and store data in real-time. Then this platform is combined with the Harris hawk optimization (HHO) algorithm and pattern search strategy, and an improved hybrid optimization (IHHO) method is proposed accordingly. Then this method is applied to optimize the SVM algorithm and predict the surface roughness in the CDH platform. The obtained results show that the prediction accuracy of IHHO method reaches 95%, which is higher than the conventional methods of SVM, BAT-SVM, GWO-SVM and WOA-SVM.

No abstract