Prediction of cutting force by using ANFIS

• Published in: International journal of system assurance engineering and management Vol. 9; no. 5; pp. 1137 - 1146
• Main Authors: Jain, Vineet, Raj, Tilak
• Format: Journal Article
• Language: English
• Published: New Delhi Springer India 01.10.2018; Springer Nature B.V
• Subjects: Adaptive systems; Artificial neural networks; Correlation coefficients; Cutting force; Cutting forces; Cutting parameters; Cutting speed; Cutting wear; Engineering; Engineering Economics; Fuzzy logic; Fuzzy systems; Logistics; Marketing; Mathematical models; Modelling; Organization; Original Article; Predictions; Quality Control; Reliability; Safety and Risk; Surface roughness; Tool life; Turning (machining); Cutting force estimation; Modelling; ANFIS; Cutting force
• ISSN: 0975-6809; 0976-4348
• DOI: 10.1007/s13198-018-0717-x

The aim of this research is to develop a model to predict the cutting forces of a turning operation. This paper focuses on to design a monitoring system that can recognize cutting force on the basis of cutting parameters like spindle speed, feed and depth of cut by using adaptive neuro-fuzzy inference system (ANFIS). Cutting force is one of the important characteristic variables to be watched and controlled in the cutting processes to determine tool life and surface roughness of the work piece. The principal assumption was that the cutting forces increase due to the wearing of the tool. So, ANFIS model is used to express the cutting force signal. In this paper, ANFIS is used to predict the cutting force. The correlation coefficient (R) and average percentage error found in this modeling are 0.9976 and 2.59% respectively. The predicted cutting force values derived from ANFIS were compared with experimental data. The comparison indicates that the ANFIS achieved very satisfactory accuracy. The correlation coefficient (R) and average percentage error found in this modeling are 0.9976 and 2.59% respectively. The prediction accuracy of ANFIS reached is as high as 97%.