A coupled artificial neural network and RSM model for the prediction of chip serration frequency in end milling of Inconel 718

• Main Authors: Patwari, Muhammed Anayet Ullah, Amin, A. K. M. Nurul, Ishtiyaq, M. H.
• Format: Book Chapter
• Language: English
• Published: IIUM Press 2011
• Subjects: TJ Mechanical engineering and machinery
• Online Access: http://irep.iium.edu.my/23594/4/chp15.pdf; http://irep.iium.edu.my/23594/; http://rms.research.iium.edu.my/bookstore/default.aspx
• Institution: Universiti Islam Antarabangsa Malaysia

Serious vibrations are often encountered due to chip segmentation that limits material removal rates. Different types of chips are formed during machining. The nature of chip formation process is extremely complicated. Chip formation process has a discrete nature, associated with the periodic shearing process of the chip during machining of Inconel 718. The instabilities of chip formation process are expressed in terms of primary or secondary serrated frequency. In order to increase productivity, tool life and chatter suppression in the machining of Inconel 718, it is necessary to study the chip segmentation phenomena and its influencing factors. Chips are formed during the machining of work-pieces. The side of the chip in contact with the cutting tool is normally shiny, flat and smooth while the other side, which is the free work-piece surface, is jagged due to shear. It is important to study the formation of chips during the machining process as the former affects the surface finish, cutting forces, temperature, tool life, dimensional tolerance and chatter. Understanding the chip formation during the machining process for the specific materials will allow us to determine the machining speeds, feed rates and depth of cuts for efficient machining and increased tool life in the specific actual machining operation as well as chatter free machining. In metal cutting, the present tendency is towards achieving increased material removal rates with very reliable machining processes, where the predictability of surface finish, work-piece accuracy, chatter and tool life are of prime importance. But to maintain stable machining, much attention must also be paid to the formation of the desired type of chip and chip controls to facilitate its easy removal. One of the restrictions limiting large material removal rates is the tendency of the machine tool to chatter. Trent, Talantov, Amin and others [1-3] considered the formation of chips with serrated teeth to be the primary cause of chatter. They found that chatter arising during turning is a result of resonance, caused by mutual interaction of the vibrations due to serrated elements of the chip and the natural vibrations of the system components, e.g. the spindle and the tool holder [2-3]. Komanduri [4-5] has made some remarkable progress in the research of chip segmentation and instability in chip formation. Nevertheless it appears that very few works have been done to investigate the nature of chip formation in end milling because of its complexity and geometrical difficulty. Amin [6] earlier established that the instability of chip formation could be lowered by preheating the work material during turning. Yuan Ning et al. [7] indicates that chatter could be reliably recognized by analysis of the chips. Ekinoviˆc et.al [8] mentioned in their work that cutting speed has significant effect on chip formation models. Similar influence of the cutting speed on the chip structure and chip compression ratio was revealed in the experiments conducted by Tonshoff et al. [9]. As the chip formation process appears to be cyclic, its frequency is of interest. The frequency of chip formation can be measured by calculating the number of teeth produced in unit time as proposed by Talantov [10]. But it is very important to investigate the effect of cutting parameters on the chip serration frequency considering nonlinearity and time variant. Compared to traditional computing methods, the artificial neural networks (ANNs) are robust and global. ANNs have the characteristics of universal approximation, parallel distributed processing, hardware implementation, learning and adaptation, and multivariable systems [11]. However, this study was inspired by the very limited work on the application of ANNs in modeling the relationship between cutting conditions and the chip serration frequency during high-speed end milling of Inconel 718.