Pattern recognition based surface roughness prediction in turning hybrid metal matrix composite using random forest algorithm

The purpose of this paper is surface roughness prediction using pattern recognition for the aluminium hybrid metal matrix composite (HMMC).

Hybrid composites were manufactured using liquid metallurgy technique. The cast HMMC was machined using an industrial CNC turning centre and the machining vibration signals were acquired using an accelerometer. The acquired signals were processed and used to build a machine learning model for predicting surface finish based on the tool signature.

The authors established a technique for predicting and monitoring the surface quality during machining using a low cost accelerometer. It is capable of being integrated with the machine controller for online warning of deviations in surface roughness. The system is reconfigurable for any machining condition with a very short training period. The use of this model facilitates online surface roughness monitoring, avoiding the need for costly measuring equipment.

The model developed is innovative and not reported widely to the best of the authors' knowledge. The use of accelerometer‐based surface roughness prediction and control is an innovative approach for automation of machining process monitoring. These can be integrated into any existing machining centre as a standalone system or can be integrated into the CNC controller like Fanuc or Siemens.