Amir Mahyar Khorasani

Tool Life Prediction in Face Milling Machining of 7075 Al by Using Artificial Neural Networks (ANN) and Taguchi Design of Experiment (DOE)

30 Abstract—Tool life is an important indicator of the milling operation in manufacturing process. Studies and analyses of milling process are usually based on three main parameters composed of cutting speed, feed rate and depth of cut. The aim of this study is to discover the role of these parameters in tool life prediction in milling operations by using artificial neural networks and Taguchi design of experiment. Machining experiments were performed under various cutting conditions by using sample specimens. A very good agreement between predicted model and experimental results was obtained. The correlation between the estimated and experimental data was 0.96966 for train and 0.94966 for test.

Production of Ti-6Al-4V acetabular shell using selective laser melting: possible limitations in fabrication

Purpose The purpose of this paper is to improve the manufacturing of a prosthetic acetabular shell by analyzing the main factors leading to failure during the selective laser melting (SLM) additive manufacturing (AM) process. Design/methodology/approach Different computer-aided design and computer-aided manufacturing processes have been applied to fabricate acetabular parts. Then, various investigations into surface quality, mechanical properties and microstructure have been carried out to scrutinize the possible limitations in fabrication. Findings Geometrical measurements showed 1.59 and 0.27 per cent differences between the designed and manufactured prototypes for inside and outside diameter, respectively. However, resulting studies showed that unstable surfaces, cracks, an interruption in powder delivery and low surface quality were the main problems that occurred during this process. These results indicate that SLM is an accurate and promising method for production of intricate shapes, provided that the appropriate settings of production conditions are considered to minimize possible limitations. Originality/value The contributions of this paper are discussions covering different issues in the AM fabrication of acetabular shells to improve the mechanical properties, quality and durability of the produced parts.

On the role of different annealing heat treatments on mechanical properties and microstructure of selective laser melted and conventional wrought Ti-6Al-4V

Purpose The purpose of this study was to conduct various heat treatments (HT) such as stress relief annealing, mill annealing, recrystallization (α + β) annealing and β annealing followed by furnace cooling (FC) that were implemented to determine the effect of these on mechanical properties and the microstructure of selective laser melted and wrought samples. The mentioned annealings have been carried out to achieve the related standards in the fabrication of surgery implants. Design/methodology/approach In this paper, based on F2924-14 ASTM standard SLM and conventionally wrought parts were prepared. Then HT was performed and different characteristics such as microstructure, mechanical properties, macro-hardness and fracture surface for selective laser melted and wrought parts were analysed. Findings The results show that the high cooling rate in selective laser melting (SLM) generates finer grains. Therefore, tensile strength and hardness increase along with a reduction in ductility was noticed. Recrystallization annealing appears to give the best combination of ductility, strength and hardness for selective laser melted parts, whilst for equivalent wrought samples, increasing HT temperature results in reduction of mechanical properties. Originality/value The contributions of this paper are discussing the effect of different annealing on mechanical properties and microstructural evolution based on new ASTM standards for selective laser melted samples and comparing them with wrought parts.

Optimizing time delay feedback for active vibration control of a cantilever beam using a genetic algorithm

Active vibration control using time delay for a cantilever beam is developed in this paper. The equation of motion of the system is developed using the discrete standard formulation, and the discrete quadratic function is used to design the controller. The original contribution in this paper is using a genetic algorithm to determine the optimal time delay feedback for active vibration control of a cantilever beam. Simulations of the beam demonstrated that the genetic algorithm correctly identified the time delay which produced the quickest attenuation of unwanted vibrations for both mode one and mode two. In terms of frequency response, the optimal time delay for both modes reduced the resonant amplitude. In a mixed mode situation, the simulation demonstrated that an optimal time delay could be identified.

CVD and PVD coating process modelling by using artificial neural networks

Thin-film coating plays a prominent role on the manufacture of many industrial devices. Coating can increase material performance due to the deposition process. Having adequate and precise model that can predict the hardness of PVD and CVD processes is so helpful for manufacturers and engineers to choose suitable parameters in order to obtain the best hardness and decreasing cost and time of industrial productions. This paper proposes the estimation of hardness of titanium thin-film layers as protective industrial tools by using multi-layer perceptron (MLP) neural network. Based on the experimental data that was obtained during the process of chemical vapor deposition (CVD) and physical vapor deposition (PVD), the modeling of the coating variables for predicting hardness of titanium thin-film layers, is performed. Then, the obtained results are experimentally verified and very accurate outcomes had been attained.

Tool vibration prediction and optimisation in face milling of Al 7075 and St 52 by using neural networks and genetic algorithm

Tool vibration generated under unsuitable cutting conditions is an extremely serious problem during face milling as it causes excessive tool wear, noise, tool breakage, and deterioration of the surface quality. In the current study, an artificial neural network (ANN) was used to predict tool vibration stability during face milling for different materials: Al 7075 and St 52. The testing of the ANN after training had a correlation of 99.206% with experimentally determined results. A generic algorithm (GA) was then used to minimise the vibration experienced during face milling and machining was performed using the GA recommended parameters. Measurement of the vibration during machining showed that the GA had a calculated error of 0.124%.

An accurate PSO-GA based neural network to model growth of carbon nanotubes

By combining particle swarm optimization (PSO) and genetic algorithms (GA) this paper offers an innovative algorithm to train artificial neural networks (ANNs) for the purpose of calculating the experimental growth parameters of CNTs. The paper explores experimentally obtaining data to train ANNs, as a method to reduce simulation time while ensuring the precision of formal physics models. The results are compared with conventional particle swarm optimization based neural network (CPSONN) and Levenberg–Marquardt (LM) techniques. The results show that PSOGANN can be successfully utilized for modeling the experimental parameters that are critical for the growth of CNTs.

Investigation on the Effect of a Pre-Center Drill Hole and Tool Material on Thrust Force, Surface Roughness, and Cylindricity in the Drilling of Al7075

Drilling is one of the most useful metal cutting processes and is used in various applications, such as aerospace, electronics, and automotive. In traditional drilling methods, the thrust force, torque, tolerance, and tribology (surface roughness) are related to the cutting condition and tool geometry. In this paper, the effects of a pre-center drill hole, tool material, and drilling strategy (including continuous and non-continuous feed) on thrust force, surface roughness, and dimensional accuracy (cylindricity) have been investigated. The results show that using pre-center drill holes leads to a reduction of the engagement force and an improvement in the surface quality and cylindricity. Non-continuous drilling reduces the average thrust force and cylindricity value, and High Speed Steels HSS-Mo (high steel speed + 5–8% Mo) reduces the maximum quantity of cutting forces. Moreover, cylindricity is directly related to cutting temperature and is improved by using a non-continuous drilling strategy.

MODELING AND OPTIMIZATION OF THE CUTTING FLUID FLOW AND PARAMETERS FOR INCREASING TOOL LIFE IN SLOT MILLING ON St52

In this paper the CNC machining of St52 was modeled using an artificial neural network (ANN) in the form of a four-layer multi-layer perceptron (MLP). The cutting parameters used in the model were cutting fluid flow, feed rate, spindle speed and the depth of cut and the model output was the tool life. For obtaining more accuracy and spending less time Taguchi design of experiment (DOE) has been used and correlation between the output of the ANN and the experimental results was 96%. Further optimization process has been done by use of a genetic algorithm (GA). After optimization process tool life was increased about 8% equal to 33 min and was corroborated by experimental tests. This demonstrates that the coupling of an ANN with the GA optimization technique is a valid and useful approach to use.