The problem with modern machining sectors
The problem to the modern machining sectors has mainly accentuated achievement of high quality, in relation to the work piece dimensional accuracy and reliability , surface finish , less wear on the cutting tools, substantial production rate and economy of machining with regards to cost saving and increase in performance ( Adnan et al. 2015). End milling is a typically employed machining process in the industry. The capability to control this method is much better quality to the final product. The surface roughness to the machined design specification that is recognized is considerable impact to properties such as wear resistance and fatigue strength (Adnan et al. 2015). Presently, the manufacturers in the manufacturing industry they are specializing in providing quality and efficiency of the product (Tamilarasan, Rajamani and Renugambal, 2015). To have the ability to increase on the productivity of the product, computer numerically machine tools they have been utilized in the past decades (Cao, Zhang and Ding, 2018). Surface roughness is amongst the crucial parameters with regards to determining the quality of the product. The mechanisms that are behind the formation of the surface roughness are extremely dynamic; process reliant and complex (Cao, Zhang and Ding, 2018). There are several factors which can affect the final surface roughness in the CNC milling operations for example controllable components and ungovernable aspects.
Some of the machine operators are using trial and error approaches to establish milling machine cutting situations. This approach is inefficient and effective and achievement of the desirable value is repetitive and in addition empirical process which can be time consuming (Vasile, Fetecau, Amarandei and Serban, 2016).
Therefore, the mathematical model utilizing statistical approach offers a much better solution. Multiple regression evaluation happens to be ideal to finding the best combination for the independent factors which is spindle speed, depth of cut and feed rate to attain desired surface roughness (Subramanian, Sakthivel and Sudhakaran, 2014). It is unfortunate; multiple regression models could be obtained from the statistical analysis which requires a large sample of the data. Realizing on that particular matter, Artificial Neural Network is the state of the art artificial intelligent approach which has some possibility in enhancing the prediction of the surface roughness (Gupta, Krishna and Suresh, 2017). This review is from the previous research which is related to this research problem of modeling of milling process to predict surface roughness utilizing artificial intelligent approach in engineering (Gupta, Krishna and Suresh, 2017). The review try to address the issue of conventional try and error approach which has been time consuming and costly (Gupta, Krishna and Suresh, 2017). There have been numerous researchers on surface roughness in the end milling utilizing various materials, experiment design, cutting tool along with other approaches to obtain the surface roughness model.
To be able to model surface roughness, various approaches had been utilized in the previous research Hadad and Ramezani (2016) developed a surface area roughness prediction model for the 6061-T6 Aluminum Alloy machining employing statistical approach. The reason behind this literature is within the progression of the forecasting model of the surface area roughness, to analyze on the vital predominant variables among the cutting speed, feed rate, radial deepness and in optimizing of the surface Roughness forecast Model (Wiedenmann and Zaeh, 2015).
Mathematical modeling utilizing statistical approach offers better solutions
Adnan et al. (2015) carried study on the influence of the tools of geometry on surface roughness in the widespread lathe. Out of this research ANN methods was utilized precisely to the turning when it comes to predicting the surface roughness. The primary merit to ANN method is its simpleness and the speed of computations (Mamedov and Lazoglu, 2016). The current work is related to exploring on the possibility to predict the surface finish. It has been found that the neutral network could possibly be applied to find effective approximations of the surface roughness. Nevertheless, the proposed methodology provided by this author has been confirmed by means of the experimental information to the dry transforming of the carbide tools (Mamedov and Lazoglu, 2016). The methodology has been discovered to be effective and uses lesser training and also testing data. Conversely, experimental data and system which was designed showed that ANN decreases the drawbacks for instance, time, economical losses and materials to a minimum (Mamedov and Lazoglu, 2016).
Uros et al. (2004) had suggested that selection of the machining variables is essential step to the process of planning. Thus, new evolutionary computation approach is designed in optimizing machining process. Particle Swarm Optimization (PSO) is employed to effectively enhance on the machining variables simultaneously to the milling processes in which several contradictory objectives they are present (Tamilarasan, Rajamani and Renugambal, 2015). At first, Artificial Neutral Network predictive model is issued to be able to forecast on the cutting forces throughout machining and then the PSO algorithm is utilized in obtaining of the optimum cutting feed rates and speed. The purpose of optimization is determining the objective function maximum by consideration of the cutting constraints (Zhou et al. 2015).
Hazim et al. (2009) designed surface roughness model with regards to End Milling via employing Swarm Intelligence. Out of this selected studies, information that was amassed from the CNC chopping investigations utilizing Design of Tests approaches. The data that is achieved was then employed when considering calibration and verification (Tian et al .2017). These kinds of inputs to the model are comprised of the Feed, Depth and Speed of cut whilst the outcome from the design is surface area roughness. The design is validated by means of evaluation to the experimental values with their forecasted alternatives. There is certainly the ideal agreement that is found from this specific research (Zhang, Yu and Wang, 2017). The proved approach has open door for the new, simple as well as economical approaches which can be employed on calibration of other empirical designs for the machining.
Mandara et al. (2001) designed multilevel, in process surface roughness reputation system in evaluating the surface roughness in the process and in the real time. The major aspects associated with the surface roughness throughout the machining process were depth of the cut, feed rate, vibration that have generated between tool and work piece (Wan, Feng, Ma and Zhang, 2017). The over-all MR-M-ISRR system which shown 82% of precision of the forecast average, and creating promising step to additional development in the in process surface area to recognizing system (Wan and Altintas, 2014).
Artificial Neural Network is an effective solution
Wan and Altintas (2014) had searched on surface roughness of brass machined by the micro end milling miniaturized equipment tool. The cutting variables consisted of spindle speed, depth of the cut, feed rate as well as aspect tool (Wan and Altintas, 2014). These kinds of authors they employed the statistical approach, for instance, ANONA and RSM in assessing the test data. From their experiment, they discovered the evaluation on the surface roughness develop the linearly with the increase of the tool dimension and spindle speed.
Conclusion
Based on this literature review, the most parameters which have been used hen looking into the optimal surface roughness are the spindle speed, feed rate and depth of the cut. These kinds of studies had not regarded as the uncontrolled parameters for example the chips formations, tool wear, chip loads, tool wear and properties of the materials of the tool and work piece. In the review it has identified the gap which is present in the surface roughness approximations and the more effective approach that might be employed.
References
Adnan, M.M., Sarkheyli, A., Zain, A.M. and Haron, H., 2015. Fuzzy logic for modeling machining process: a review. Artificial Intelligence Review, 43(3), pp.345-379.
Bajpai, V., Lee, I. and Park, H.W., 2014. Finite element modeling of three-dimensional milling process of Ti–6Al–4V. Materials and Manufacturing Processes, 29(5), pp.564-571.
Cao, C., Zhang, X.M. and Ding, H., 2018. An analytical method in modeling of milling process damping considering cutting edge radius. Procedia CIRP, 77, pp.106-109.
Gupta, A., Krishna, C.M. and Suresh, S., 2017. Modeling and Analysis of CNC Milling Process Parameters on Aluminium Silicate Alloy.
Hadad, M. and Ramezani, M., 2016. Modeling and analysis of a novel approach in machining and structuring of flat surfaces using face milling process. International Journal of Machine Tools and Manufacture, 105, pp.32-44.
Mamedov, A. and Lazoglu, I., 2016. An evaluation of micro milling chip thickness models for the process mechanics. The International Journal of Advanced Manufacturing Technology, 87(5-8), pp.1843-1849.
Subramanian, M., Sakthivel, M. and Sudhakaran, R., 2014. Modeling and analysis of surface roughness of AL7075-T6 in end milling process using response surface methodology. Arabian Journal for Science and Engineering, 39(10), pp.7299-7313.
Tamilarasan, A., Rajamani, D. and Renugambal, A., 2015. An Approach on Fuzzy and Regression Modeling for Hard Milling Process. Applied Mechanics & Materials.
Tian, Y., Liu, Y., Wang, F., Jing, X., Zhang, D. and Liu, X., 2017. Modeling and analyses of helical milling process. The International Journal of Advanced Manufacturing Technology, 90(1-4), pp.1003-1022.
Vasile, G., Fetecau, C., Amarandei, D. and Serban, A., 2016. Experimental Research on the Milling Process of Some Composite Materials. MATERIALE PLASTICE, 53(1), pp.157-165.
Wiedenmann, R. and Zaeh, M.F., 2015. Laser-assisted milling—Process modeling and experimental validation. CIRP Journal of Manufacturing Science and Technology, 8, pp.70-77.
Wan, M. and Altintas, Y., 2014. Mechanics and dynamics of thread milling process. International Journal of Machine Tools and Manufacture, 87, pp.16-26.
Wan, M., Feng, J., Ma, Y.C. and Zhang, W.H., 2017. Identification of milling process damping using operational modal analysis. International Journal of Machine Tools and Manufacture, 122, pp.120-131.
Zhang, X., Yu, T. and Wang, W., 2017. Instantaneous uncut chip thickness modeling for micro-end milling process. Machining Science and Technology, 21(4), pp.582-602.
Zhou, L., Peng, F.Y., Yan, R., Yao, P.F., Yang, C.C. and Li, B., 2015. Analytical modeling and experimental validation of micro end-milling cutting forces considering edge radius and material strengthening effects. International Journal of Machine Tools and Manufacture, 97, pp.29-41.
Order an Essay Now & Get These Features For Free:
Turnitin Report
Formatting
Title Page
Citation
Outline
