Improved Estimation of End-Milling Parameters from Acoustic Emission Signals Using a Microphone Array Assisted by AI Modelling.

This paper presents the implementation of a measurement system that uses a four microphone array and a data-driven algorithm to estimate depth of cut during end milling operations. The audible range acoustic emission signals captured with the microphones are combined using a spectral subtraction and a blind source separation algorithm to reduce the impact of noise and reverberation. Afterwards, a set of features are extracted from these signals which are finally fed into a nonlinear regression algorithm assisted by machine learning techniques for the contactless monitoring of the milling process. The main advantages of this algorithm lie in relatively simple implementation and good accuracy in its results, which reduce the variance of the current noncontact monitoring systems. To validate this method, the results have been compared with the values obtained with a precision dynamometer and a geometric model algorithm obtaining a mean error of 1% while maintaining an STD below 0.2 mm.

Non-Invasive Estimation of Machining Parameters during End-Milling Operations Based on Acoustic Emission.

This work presents a non-invasive and low-cost alternative to traditional methods for measuring the performance of machining processes directly on existing machine tools. A prototype measuring system has been developed based on non-contact microphones, a custom designed signal conditioning board and signal processing techniques that take advantage of the underlying physics of the machining process. Experiments have been conducted to estimate the depth of cut during end-milling process by means of the measurement of the acoustic emission energy generated during operation. Moreover, the predicted values have been compared with well established methods based on cutting forces measured by dynamometers.