Fuzzy logic based model for predicting surface roughness of machined Al–Si–Cu–Fe die casting alloy using different additives-turning. (February 2015)

• Record Type: Journal Article
• Authors: Marani Barzani, Mohsen; Zalnezhad, Erfan; Sarhan, Ahmed A.D.; Farahany, Saeed; Ramesh, Singh
• Is Part Of: Measurement. Volume 61(2015:Feb.)
• Page Start: 150
• Page End: 161
• Publication Date: 2015-02
• Subjects: Fuzzy logic -- Aluminum -- Turning -- Surface roughness -- Antimony -- Bismuth; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2014.10.003
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: Artificial intelligence technique, fuzzy logic was used to predicting the surface roughness. The Pareto-ANOVA optimization method was used to obtain optimum parameter conditions. Surface roughness increased with increasing feed rate and improved with rising cutting speed. The workpiece containing Bi exhibited the lowest surface roughness. Abstract: This paper presents a fuzzy logic artificial intelligence technique for predicting the machining performance of Al–Si–Cu–Fe die casting alloy treated with different additives including strontium, bismuth and antimony to improve surface roughness. The Pareto-ANOVA optimization method was used to obtain the optimum parameter conditions for the machining process. Experiments were carried out using oblique dry CNC turning. The machining parameters of cutting speed, feed rate and depth of cut were optimized according to surface roughness values. The results indicated that a cutting speed of 250 m/min, a feed rate of 0.05 mm/rev, and a depth of cut of 0.15 mm were the optimum CNC dry turning conditions. The results also indicated that Sr and Sb had a negative effect on workpiece machinability. The workpiece containing Bi exhibited the lowest surface roughness value, likely due to the formation of pure Bi that acted as lubricant during turning. A confirmation experiment was performed to check the validity of the model developed in this paper, and the predicted surface roughness came had an error rate of only 5.4%.