Muhammad Riza

Prediction of Cutting Temperatures by Using Back Propagation Neural Network Modeling when Cutting Hardened H-13 Steel in CNC End Milling

Machining of hardened steel at high cutting speeds produces high temperatures in the cutting zone, which affects the surface quality and cutting tool life. Thus, predicting the temperature in early stage becomes utmost importance. This research presents a neural network model for predicting the cutting temperature in the CNC end milling process. The Artificial Neural Network (ANN) was applied as an effective tool for modeling and predicting the cutting temperature. A set of sparse experimental data for finish end milling on AISI H13 at hardness of 48 HRC have been conducted to measure the cutting temperature. The artificial neural network (ANN) was applied to predict the cutting temperature. Twenty hidden layer has been used with feed forward back propagation hierarchical neural networks were designed with Matlab2009b Neural Network Toolbox. The results show a high correlation between the predicted and the observed temperature which indicates the validity of the models.

Cutting Temperature and Surface Roughness Optimization in CNC End Milling Using Multi Objective Genetic Algorithm

Machining of hard materials at high cutting speeds produces high temperatures in the cutting zone, which affects the surface quality. Thus, developing a model for estimating the cutting parameters and optimizing this model to minimize the cutting temperatures and surface roughness becomes utmost important to avoid any damage to the quality surface. This paper presents the development of new models and optimizing these models of machining parameters to minimize the cutting temperature in end milling process by integrating the genetic algorithm (GA) with the statistical approach. The mathematical models for the cutting temperature and surface roughness parameters have been developed, in terms of cutting speed, feed rate, and axial depth of cut by using Response Methodology Method (RSM). Two objectives have been considered, minimum cutting temperature and minimum arithmetic mean roughness (Ra). Due to complexity of this machining optimization problem, a multi objective genetic algorithm (MOGA) has been applied to resolve the problem, and the results have been analyzed.

Predicting Surface Roughness with Respect to Process Parameters Using Regression Analysis Models in End Milling

Surface roughness affects the functional attributes of finished parts. Therefore, predicting the finish surface is important to select the cutting levels in order to reach the required quality. In this research an experimental investigation was conducted to predict the surface roughness in the finish end milling process with higher cutting speed. Twenty sets of data for finish end milling on AISI H13 at hardness of 48 HRC have been collected based on five-level of Central Composite Design (CCD). All the experiments done by using indexable tool holder Sandvick Coromill R490 and the insert was PVD coated TiAlN carbide. The experimental work performed to predict four different roughness parameters; arithmetic mean roughness (Ra), total roughness (Rt), mean depth of roughness (Rz) and the root mean square (Rq).

Surface Roughness Optimization in End Milling Using the Multi Objective Genetic Algorithm Approach

In finishing end milling, not only good accuracy but also good roughness levels must be achieved. Therefore, determining the optimum cutting levels to achieve the minimum surface roughness is important for it is economical and mechanical issues. This paper presents the optimization of machining parameters in end milling processes by integrating the genetic algorithm (GA) with the statistical approach. Two objectives have been considered, minimum arithmetic mean roughness (Ra) and minimum Root-mean-square roughness (Rq). The mathematical models for the surface roughness parameters have been developed, in terms of cutting speed, feed rate, and axial depth of cut by using Response Methodology Method (RSM). Due to complexity of this machining optimization problem, a multi objective genetic algorithm (MOGA) has been applied to resolve the problem, and the results have been analyzed.

Power Consumption Optimization in CNC Turning Process Using Multi Objective Genetic Algorithm

Power consumption cost is one of the main integral parts of the total machining cost, but it has not given the proper attention when minimizing the machining cost. In this paper, the optimal machining parameters for continuous machining are determined with respect to the minimum power consumption cost with maintaining the surface roughness in the range of acceptance. The constraints considered in this research are cutting speed, feed rate, depth of cut and rake angle. Due to complexity of this machining optimization problem, a multi objective genetic algorithm (MOGA) was applied to resolve the problem, and the results have been analyzed.

Flank wears Simulation by using back propagation neural network when cutting hardened H-13 steel in CNC End Milling

High speed milling has many advantages such as higher removal rate and high productivity. However, higher cutting speed increase the flank wear rate and thus reducing the cutting tool life. Therefore estimating and predicting the flank wear length in early stages reduces the risk of unaccepted tooling cost. This research presents a neural network model for predicting and simulating the flank wear in the CNC end milling process. A set of sparse experimental data for finish end milling on AISI H13 at hardness of 48 HRC have been conducted to measure the flank wear length. Then the measured data have been used to train the developed neural network model. Artificial neural network (ANN) was applied to predict the flank wear length. The neural network contains twenty hidden layer with feed forward back propagation hierarchical. The neural network has been designed with MATLAB Neural Network Toolbox. The results show a high correlation between the predicted and the observed flank wear which indicates the validity of the models.

Effect of Cutting Parameters on Cutting Forces for Different Profile of Cutting

In machining operation of mould cavities, the tool travels in various straight and corner profiles following predetermined toolpath. Such condition results in a fluctuation of cutting forces that may produce bad surface finish. The objective of this study is to investigate the most influential parameters on cutting operation for both straight and corner profiles of pocketing operation. Cutting speeds of 150, 200 and 250m/min, feedrates from 0.05, 0.1, 0.15 mm/tooth and depths of cut of 0.1, 0.15 and 0.2 mm were selected for the cutting processes. Taguchi L9 orthogonal array with Pareto ANOVA analysis was employed to analyze the effects of the selected parameters. The result demonstrates there are different effects of cutting parameters on cutting forces for straight and corner profiles. Furthermore, it was found that cutting speed and feedrate are prevailing factors that affected cutting forces for both types of profile.

Heat Generation Performance of a Homemade Friction Stir Welding Tool

Friction Stir Welding (FSW) is getting its popularity because it is considered as an environmentally friendly manufacturing. Homemade FSW tool to be attached to a conventional milling machine was designed and fabricated. Experimental investigation of FSW process of the Aluminum alloy work piece to observe its heat generation was performed. Since heat generation is the main objective in a FSW process, the importance of identification of heat generation performance in a welded specimen is paramount. Heat generation of a welded specimen during FSW was measured using infra red thermal camera. The limitation of the measurement is it only captured the heat generation at surrounding area and surface of the welded specimen. Therefore, the heat generation inside contact area could not be identified. To overcome this problem, a finite-element model of the FSW process was developed. A model consists of a solid model of half the welded specimen since the symmetrical behavior of the geometry and boundary condition was assumed. Heat transfer analysis of a solid body model of a work piece was computed. It was observed that FSW parameters which involved dominantly in the heat generation were spindle speed, feeding rate and normal force. The heat generation model of FSW process was validated with the one from the experimental investigation. Good agreement between the numerical and the experimental investigation result has been made.

Cutting force impact to tool life of CT5015 in high speed machining by applying negative rake angles

Cermets become increasingly popular cutting insert in recent years. They are generally good when accuracy and finish are criteria for the operation. Several improvements have been made to increase their performance in machining process such as higher resistance to thermal deformation and lower conductivity than carbide tools that wear rapidly. This study is to investigate cutting force and tool wear under different rake angles in high speed machining process. Experiments were carried out by using cermet insert (CT5015). Different rake angles have been applied in the experiments which are 0o, -3o. -6o, -9o and -12o respectively with cutting speed 1000 m/minute and feed rate 800 mm/minute. For every single pass of cutting, cutting force, wear rate and cutting temperature were measured respectively by surface roughness tester, dynamometer, Scanning Electron Microscope (SEM) and infrared thermometer. The experimental results showed that the more negative angles the higher cutting force produced. Simultaneously, cutting temperature increases following the incremental of cutting force. It caused wear occurred faster and lead to reduce the life of cermet inserts.