Estimation of tool-chip contact length using optimized machine learning in orthogonal cutting

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@Article{QAZANI:2022:engappai,

• author = "Mohammad Reza Chalak Qazani and Vahid Pourmostaghimi and Mehdi Moayyedian and Siamak Pedrammehr",
• title = "Estimation of tool-chip contact length using optimized machine learning in orthogonal cutting",
• journal = "Engineering Applications of Artificial Intelligence",
• volume = "114",
• pages = "105118",
• year = "2022",
• ISSN = "0952-1976",
• DOI = "doi:10.1016/j.engappai.2022.105118",
• URL = "https://www.sciencedirect.com/science/article/pii/S0952197622002524",
• keywords = "genetic algorithms, genetic programming, Tool-chip contact length, Optimization, Adaptive network-based fuzzy inference system",
• abstract = "Tool-chip contact length has a significant effect on the various characteristics of metal cutting, including cutting pressures, chip formation, tool wear, tool life, and cutting temperatures. It should be added that there is a direct relationship between the tool-chip contact length and secondary shear zone thickness in the metal cutting process. The cutting force and shear zone temperature decrease by the reduction of tool-chip contact length. In addition, the tool-chip contact length affects the tool life and workpiece surface roughness. Lots of researchers have conducted extensive research to calculate the tool-chip contact length using mathematical or machine learning methods. The main objective of this study is to calculate the tool-chip contact length using a highly advanced machine learning method without any time-consuming and expensive experiments. However, an adaptive network-based fuzzy inference system (ANFIS) is not used yet in the prediction of the tool-chip contact length. In this study, we proposed the ANFIS to predict the tool-chip contact length for the first time in orthogonal cutting using depth of cut, feed-rate, and cutting speed as inputs of the proposed model. As the second contribution of this study, three evolutionary-based optimization techniques, including genetic algorithm, particle swarm optimization, and grey wolf optimization, as well as global-based Bayesian optimization, are employed to select the optimal hyperparameters of the proposed ANFIS model known as GA-ANFIS, PSO-ANFIS, GWO-ANFIS, and B-ANFIS, respectively. The proposed methods are designed and developed in MATLAB software to be compared with the previous method using genetic programming (GP). The outcomes of this research demonstrate that the GWO-ANFIS can decrease the mean square error between the actual and predicted tool-chip contact length of 15.60percent, 3.67percent, 89.75percent, and 92.17percent in comparison with those of GA-ANFIS, PSO-ANFIS, B-ANFIS, and GP, respectively. In addition, the fuzzy logic rule surface of the GWO-ANFIS shows 57.20percent, 30.95percent, and 11.85percent dependency of tool-chip contact length to cutting speed, feed-rate, and depth of cut as the inputs of the orthogonal cutting process, respectively",

}

Genetic Programming entries for Mohammad Reza Chalak Qazani Vahid Pourmostaghimi Mehdi Moayyedian Siamak Pedrammehr

Citations