An Application of ANFIS to Predict the Hot Flow Behavior of 6063 Aluminum Alloy

• Published in: Journal of materials engineering and performance Vol. 21; no. 7; pp. 1160 - 1166
• Main Authors: Chunlei, Gan, Mengjun, Wang
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01.07.2012; Springer Nature B.V
• Subjects: Alloy development; Alloy systems; Aluminum base alloys; Characterization and Evaluation of Materials; Chemistry and Materials Science; Corrosion and Coatings; Engineering Design; Fuzzy; Inference; Materials Science; Mathematical models; Quality Control; Reliability; Safety and Risk; Strain; Strain rate; Tribology; flow stress; 6063 aluminum alloy; ANFIS
• ISSN: 1059-9495; 1544-1024
• DOI: 10.1007/s11665-011-0033-y

In order to determine the optimum hot-forming processing parameters for 6063 aluminum alloy, the compressive deformation behavior of 6063 aluminum alloy was investigated at the temperatures from 300 to 500 °C and strain rates from 0.5 to 50 s −1 on a Gleeble-1500 Thermal Simulator. Based on the compression experimental data, a novel adaptive network-based fuzzy inference system (ANFIS) model is developed to predict the flow behavior of 6063 aluminum alloy. In the ANFIS system, the inputs of the ANFIS are the strain, the strain rate and the temperature, whereas the flow stress is the output. The effects of strain, strain rate, and temperature on the flow behavior of 6063 aluminum alloy have been studied by comparing the experimental and the predicted results using the developed ANFIS model. The results show that predicted values using the developed model are in good agreement with the experimental data, which demonstrates the reliability of the developed ANFIS model.