材料科学
因科镍合金
刀具磨损
机械加工
涂层
表面粗糙度
表面光洁度
刀具
灰色关联分析
机械工程
冶金
复合材料
工程类
合金
数学
数理经济学
作者
Ananda Kumar Sahoo,Susanta Kumar Sahoo,Suvranshu Pattanayak,Manoj Kumar Moharana
标识
DOI:10.1177/09544089221139629
摘要
Modern manufacturing processes require materials like Inconel 825 that have high strength, hardness, and corrosion resistance for applications in aerospace, biomedical, and marine industries. But their low thermal conductivity and higher affinity towards cutting tools limit their machining through conventional turning due to high cutting force and excessive tool wear. Here, the UVAT process is employed during the turning of Inconel 825, and its turning characteristics are analysed through grey relational analysis methodology to determine the optimum turning condition. TiAlN/TiAlCrN-coated WC insert has been adopted during UVAT to identify the effect of coating on turning performances. Also, an attempt has been made to develop a feed-forward artificial neural network model to simulate the turning process and predict the surface roughness, cutting force and temperature at work–tool interface. The proposed 4-16-3 model is reliable and accurate while estimating the turning characteristics for an actual machining condition because of the low error rate and nearer to one regression score. UVAT process substantially reduces the surface roughness, cutting force and interface temperature due to the intermittent cutting action. Whereas, multilayer TiAlN/TiAlCrN coating reduces the intensive friction at the work–tool interface by enhancing the lubricity action at the interface due to the formation of complex alumina and chromia-like tribo-film. It provides a highly finished surface with low cutting force and temperature while improving the cutting tool life. Tool wear and chip morphology is analysed through a scanning electron microscope. X-ray diffraction analysis is also performed on the workpiece and chip to identify the crystallographic phases, crystallite size, and lattice strain.
科研通智能强力驱动
Strongly Powered by AbleSci AI