Investigation of the optimization of machining processes for oil-hardened nitric steel material, aiming to understand the productivity and quality is carried out. Utilizing an orthogonal array design with three-level three-factor input parameters, the study assesses material removal rates (MRR) and surface finish quality. A regression model is developed using Taguchi design techniques and ANOVA for MRR with 0.059 P-value and for Surface roughness with 0.062 P-value validates the regression and the significant parameters. Further optimization is conducted using genetic algorithms. The optimization data are validated using scanning electron microscope (SEM) images for MRR and surface roughness individually. Leveraging the capabilities of MATLAB and LabVIEW, a user-friendly interface is designed and validated using the class function Object () [native code] node and core wrapper design of the Laboratory Virtual Instrument Engineering Workbench (LabVIEW). The objective is to create a software tool that enhances machining processes, addressing the needs of various industries. This research aims to develop a mathematical model incorporating statistical techniques to predict machining processes tailored to specific machine-material combinations. A framework for user interface to predict the best machining conditions for chosen outputs by the combination of machines and material is created. The experimental machining data were converted into regression equations and then into .m files using MATLAB. Based on the existing knowledge, a suitable method for optimizing (Genetic Algorithm) the machining process is chosen and the results obtained in a user friendly interface.
原文链接
分享
引用
