Research on surface roughness detection and prediction of ti-6Al-4v titanium alloy based on multi-feature fusion

Considering that titanium alloy is a critical aviation resource, ensuring its machining quality is of significant importance. Surface roughness remains a key parameter for surface quality inspection. This article introduces a multi-sensor titanium alloy milling monitoring system aimed at accurately monitoring surface quality during titanium alloy processing. Principal component analysis is conducted on three-dimensional milling force and vibration. We propose a multi-objective cutting parameter optimization procedure to simultaneously optimize multiple cutting parameters to improve surface roughness and tool life. Considering the high dependence of visual measurement on the light source, we strive to mitigate this limitation and improve prediction accuracy by considering one-dimensional and two-dimensional feature values. We establish a multidimensional signal feature surface roughness prediction system based on milling parameters, milling vibration, milling force, and texture image features. Using particle swarm algorithm and machine learning models, the undetermined parameters in the prediction system are obtained. The results show that the prediction accuracy of the multi-signal feature fusion surface roughness prediction system is 99.12%, with a mean square error of less than 0.01. The research can provide some theoretical guidance for the accurate monitoring of the surface quality of titanium alloy processing.