Spring International Engineering Research Journal

ISSN 2384-5058

Prediction and Optimization of Material Chip size required to enhance the Tool Life of some selected Materials


Abstract: Because of its exceptional mechanical qualities, pitting resistance, stress-corrosion cracking, production features, and uses in oil and gas, nuclear power, thermal power generation, chemical processing, saltwater treatment, and pipeline infrastructure, duplex stainless steel has emerged as one of the stainless steel family's fastest-growing materials. However, because of its great toughness, poor heat conductivity, and ductility, it is more challenging to process. In order to answer and meet the industrial need, the experiment was carried out utilizing 2205 Duplex Stainless Steel bars taking into account carbide cutting tools, estimating machining time employing a CNC lathe. The Central Composite Design was the experimental design adopted, that was produced using the design 7.1 software and the Response Surface Methodology achieved a desirability value of 0.973, indicating optimal machining conditions. These conditions included a depth of cut of 0.4, a cutting velocity of 250, and a feed rate of 0.5, yielded a machined component with a material chip size of 0.141. The ANN model was used in conjunction with the RSM model to forecast the output parameters. Due to its greater coefficient of determination, the Response Surface Methodology is chosen to be the superior predictive model over the Artificial Neural Network based on the data obtained.

 

Keywords:: Chip size, Machining, Response surface methodology, Artificial neural network