Adaptive neuro-fuzzy fusion of multi-sensor data for monitoring of CNC machining

Abstract

Purpose

Acoustic emission (AE) could be used for prevention and detection of tool errors in Computer Numerical Control (CNC) machining. The purpose of this study is to analyze the AE form of CNC machining operations.

Design/methodology/approach

Experimental measurements were performed with three sensors on the CNC lathe to collect the data of the CNC machining. Adaptive neuro-fuzzy inference system (ANFIS) was applied for the fusion from the sensors’ signals to determine the strength of the signal periodic component among the sensors.

Findings

There were three inputs, namely, spindle speed, feed rate and depth of cut. ANFIS was also used to determine the inputs’ influence on the prediction of strength of the signal periodic component. Variable selection process was used to select the most dominant factors which affect the prediction of strength of the signal periodic component.

Originality/value

Results were shown that the spindle speed has the most dominant effect on the strength of the signal periodic component.

Citation

Jovic, S., Anicic, O. and Jovanovic, M. (2017), "Adaptive neuro-fuzzy fusion of multi-sensor data for monitoring of CNC machining", Sensor Review, Vol. 37 No. 1, pp. 78-81. https://doi.org/10.1108/SR-06-2016-0107