scispace - formally typeset
Search or ask a question
Author

A. Khellaf

Bio: A. Khellaf is an academic researcher from École Normale Supérieure. The author has contributed to research in topics: Surface roughness & SCADA. The author has an hindex of 4, co-authored 7 publications receiving 96 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: In this article, the effects of the process inputs, namely cutting speed, depth of cut, feed rate, and tool nose radius on the output responses are evaluated using response surface methodology (RSM).
Abstract: This paper aims at modeling surface roughness and cutting force in finish turning of AISI 4140 hardened steel with mixed ceramic tool. For this purpose, an attempt is made to improve prediction by using Artificial Neural Networks (ANN) technique. The effects of the process inputs, namely cutting speed, depth of cut, feed rate, and tool nose radius on the output responses are evaluated using response surface methodology (RSM). Also, this paper provides a profound examination of the surface roughness through the bearing area curve analysis (BAC) of the three-dimensional topographic maps of the machined surfaces, where relevant criteria representing surface roughness are used. It was established that machining with larger nose radius and lower feed rate produces surfaces with better functional characteristics and that the undesired effect of feed rate can be reduced by increasing the cutting speed. Desirability function approach (DF) and the Non-dominated Sorting Genetic Algorithm (NSGA-II) coupled with ANN models are used to solve different multi-objective optimization problems. It is found that NSGA-II is more efficient than DF method and offers diverse sets of non-dominated solutions that satisfy the requirements of parts quality, productivity, and cutting force, which lead to better competitiveness. Furthermore, the NSGA-II coupled with ANN models allowed to predict minimal value of Ra much less than the values of the experimental data.

55 citations

Journal ArticleDOI
TL;DR: In this article, a comparison of surface roughness between both ceramic cutting tools namely, TiN coated mixed ceramic CC6050 and uncoated mixed ceramics CC650 when machining hardened hot work steel X38CrMoV5-1 [AISI H11] treated at 50 HRC was presented.
Abstract: This paper presents a comparison of surface roughness between both ceramic cutting tools namely, TiN coated mixed ceramic CC6050 and uncoated mixed ceramic CC650 when machining hardened hot work steel X38CrMoV5-1 [AISI H11] treated at 50 HRC. A mathematical model, relating surface roughness criteria and main factors such as cutting radius, cutting speed, feed rate, and depth of cut, was developed using response surface methodology (RSM) and its adequacy was checked by regression analysis. The effect of cutting parameters on surface roughness is evaluated and the optimum cutting conditions to minimize the surface roughness are determined. A multiple linear models have been established between the cutting parameters and the surface roughness using response surface methodology. The experimental results reveal that the most significant machining parameter for surface roughness is the feed followed by cutting radius. Also the determined optimal conditions really reduce the surface roughness on the machining of AISI H11 steels within the ranges of parameters studied. In addition, excellent surface roughness was obtained in hard turning using CC650 tools. The coated ceramic tools had no advantage over CC650 from the point of view of surface roughness.

42 citations

Journal ArticleDOI
TL;DR: In this paper, the effects of cutting speed, feed rate, depth of cut and workpiece hardness on surface roughness, cutting pressure, and cutting power in the hard turning of hardened AISI H11 (X38CrMoV5-1) using CBN7020 tools were experimentally investigated.
Abstract: The surface finish of machined parts is known to have considerable effect on some properties such as wear resistance and fatigue strength. Thus, the quality of the surface has a significant importance for evaluating the productivity of machine tools, and mechanical parts. In this paper, the effects of cutting speed, feed rate, depth of cut and workpiece hardness on surface roughness, cutting pressure, and cutting power in the hard turning of hardened AISI H11 (X38CrMoV5-1) using CBN7020 tools were experimentally investigated. The response surface methodology (RSM) and analysis of variance (ANOVA) were used to check the validity of quadratic regression model and to determine the significant parameter affecting the output responses. The mathematical models for output parameters have been developed using Box–Behnken design with 29 runs. The results indicated that the surface roughness parameters are influenced principally by the feed rate and workpiece hardness while the depth of cut has no significant influence. In addition, cutting speed is the main influencing factor on the cutting power. Also, the results show that the tool life is influenced principally by the cutting speed and in the second level by the feed rate.

36 citations

Journal ArticleDOI
TL;DR: In this paper, the authors investigated the cutting performance of coated CC6050 and uncoated CC650 mixed ceramics in hard turning of hardened steel, mainly evaluated by cutting force components and tool wear.
Abstract: This study investigated the cutting performance of coated CC6050 and uncoated CC650 mixed ceramics in hard turning of hardened steel. The cutting performance was mainly evaluated by cutting force components and tool wear. The planning of experiments was based on Taguchi’s L36 orthogonal array. The response surface methodology and analysis of variance were used to check the validity of multiple linear regression models and to determine the significant parameter affecting the cutting force components. Tool wear progressions and, hence, tool life, different tool wear forms and wear mechanisms observed for tools coated with TiN and uncoated mixed ceramics are presented along with the images captured by digital and electron microscope. Experimental observations indicate higher tool life with uncoated ceramic tools, which shows encouraging potential of these tools to hard turning of AISI H11 (50 HRC). Finally, tool performance indices are based on units which characterise machined cutting force components and wear when hard turning.

12 citations

Proceedings ArticleDOI
01 Dec 2015
TL;DR: This article focuses on the high level open protocol of SCADA systems: IEC 60870-5-101 as well as its implementation and the design of aRTU TESTER and the conception of a RTU.
Abstract: As the choice of the communications protocol for a given application represents one of the most significant tasks in the development of information technical solutions, this article focuses on the high level open protocol of SCADA systems: IEC 60870-5-101 as well as its implementation and the design of a RTU TESTER and the conception of a RTU.

10 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: In this paper, the authors focused on the determination of the optimum cutting conditions leading to minimum surface roughness as well as cutting force, cutting power and maximum productivity, in the case of the turning of the polyoxymethylene polymer POM C using cemented carbide cutting tool.

82 citations

Journal ArticleDOI
TL;DR: In this paper, the influence of different machining parameters represented by the cutting speed (Vc), the depth of cut (ap), and the feed rate (f) on the output performance parameters expressed through the surface roughness, the cutting force and power, and the material removal rate (i.e., Ra, Fz, Pc, and MRR) during dry hard turning operation of martensitic stainless steel treated at 59HRC.
Abstract: The present study aims at investigating the influence of the different machining parameters represented by the cutting speed (Vc), the depth of cut (ap), and the feed rate (f) on the output performance parameters expressed through the surface roughness, the cutting force and power, and the material removal rate (i.e., Ra, Fz, Pc, and MRR) during dry hard turning operation of martensitic stainless steel (AISI 420) treated at 59HRC. The machining tests were carried out using the coated mixed ceramic insert (CC6050) according to the Taguchi design (L25). The analysis of the variance (ANOVA) and the Pareto chart analysis led to quantifying the influence of the (Vc, ap, and f) on the output parameters. The response surface methodology (RSM) and the artificial neural networks (ANN) approaches were applied and compared for output parameters modeling. Attempt was further made to optimize the machining parameters using the desirability function (DF). Four objectives were considered including the maximization of the quality and the productivity (through minimizing Ra and maximizing MRR), and reducing the energy consumption over minimizing both (Fz) and (Pc). The results indicated that (Ra) is strongly influenced by the feed rate (in the order of 80.71%), while the depth of cut seems to be the property having the most influence on the cutting force (65.31%), the cutting power (37.56%), and the material removal rate (36.45%). Furthermore, ANN and RSM models were found to predict well experimental results with the former showing higher accuracy. The machining of AISI 420 (59 HRC) steel with coated ceramic led to achieving a quality surface comparable to that found in grinding (i.e., Ra < 0.4 μm).

71 citations

Journal ArticleDOI
TL;DR: In this article, a comparative study of the surface roughness criterion (Ra), the tangential cutting force (Fz), the cutting power (Pc), and the material removal rate (MRR) in turning of EN-GJL-250 cast iron using both coated and uncoated silicon nitride ceramics (Si3N4).
Abstract: A comparative study is undertaken in terms of the surface roughness criterion (Ra), the tangential cutting force (Fz), the cutting power (Pc), and the material removal rate (MRR) in turning of EN-GJL-250 cast iron using both coated and uncoated silicon nitride ceramics (Si3N4). The experimental procedure is carried out according to L27 Taguchi design process, and the analysis of variance ANOVA approach used to identify the cutting parameters that most influence the responses gathered. The artificial neural network approach (ANN) and the response surface methodology (RSM) were adopted to developing the mathematical prediction models applied in the optimization procedure that used genetic algorithm (GA). The predictive capabilities of the ANN and RSM models were further compared in terms of their mean absolute deviation (MAD), mean absolute error in percent (MAPE), mean square error (RMSE), and coefficient of determination (R2). It has been found that the ANN method provides more precise results compared to those of the RSM approach. Moreover, the coated ceramic tool has been found to lead to a better surface quality and a minimum cutting force compared to those obtained by uncoated ceramic. The wear tests undertaken show that, when the flank wear reaches the admissible value of [Vb] = 0.3 mm, the ratios (tool life CC1690/tool life CC6090), (RaCC1690/RaCC6090), and (FzCC1690/FzCC6090) are found to equal 0.88, 1.4, and 0.94, respectively.

62 citations

Journal ArticleDOI
TL;DR: In this paper, two hybrid artificial neural network (ANN) models are used to predict the process responses after training them using the experimental results, and the prediction accuracy of the two models are enhanced via integration with two different metaheuristic optimization algorithms, namely particle swarm optimization (PSO) and flower pollination algorithm (FPA).
Abstract: Residual stresses (RS) induced in machined components have substantial impact on the quality and lifetime of the final products. There are several cutting parameters and conditions that affect the generation of RS, so understanding the relationship between the RS generation and those parameters to minimize the induced tensile RS is a crucial issue. This paper presents a study on the utilization of artificial intelligence-based methods to model the RS generation during dry turning of DT4E pure iron. The experiments were designed based on central composite design method. The effects of the cutting parameters such as cutting speed, feed and cutting depth on the generated RSes in both circumferential and radial directions are investigated. Two hybrid artificial neural network (ANN) models are used to predict the process responses after training them using the experimental results. The prediction accuracy of the two models are enhanced via integration with two different metaheuristic optimization algorithms, namely particle swarm optimization (PSO) and flower pollination algorithm (FPA). These optimization algorithms are used as subroutine algorithms to determine the optimal parameters of the ANN model. The predicted results by the proposed models were compared with the experimental results as well as those obtained by standalone ANN. The accuracy of all models was evaluated using different statistical measures. The ANN-FPA had the best prediction accuracy followed by ANN-PSO. The coefficient of determination of ANN-FPA has high values of 0.996 and 0.997 for radial RS and circumferential RS, while they were 0.971 and 0.992 for ANN-PSO and 0.649 and 0.815 for standalone ANN.

55 citations

Journal ArticleDOI
TL;DR: Different artificial intelligence techniques, such as artificial regression trees, multilayer perceptrons (MLPs), radial basis networks (RBFs), and Random Forest, were tested considering the isotropy level as either a nominal or a numeric attribute, to evaluate improvements in the accuracy of surface roughness and loss-of-mass predictions.
Abstract: Currently, a key industrial challenge in friction processes is the prediction of surface roughness and loss of mass under different machining processes, such as Electro-Discharge Machining (EDM), and turning and grinding processes. Under industrial conditions, only the sliding distance is easily evaluated in friction processes, while the acquisition of other variables usually implies expensive costs for production centres, such as the integration of sensors in functioning machine-tools. Besides, appropriate datasets are usually very small, because the testing of different friction conditions is also expensive. These two restrictions, small datasets and very few inputs, make it very difficult to use Artificial Intelligence (AI) techniques to model the industrial problem. So, the use of the isotropy level of the surface structure is proposed, as another input that is easily evaluated prior to the friction process. In this example, the friction processes of a cubic sample of 102Cr6 (40 HRC) steel and a further element made of X210Cr12 (60 HRC) steel are considered. Different artificial intelligence techniques, such as artificial regression trees, multilayer perceptrons (MLPs), radial basis networks (RBFs), and Random Forest, were tested considering the isotropy level as either a nominal or a numeric attribute, to evaluate improvements in the accuracy of surface roughness and loss-of-mass predictions. The results obtained with real datasets showed that RBFs and MLPs provided the most accurate models for loss of mass and surface roughness prediction, respectively. MLPs have slightly higher surface prediction accuracy than Random Forest, although MLP models are very sensitive to the tuning of their parameters (a small mismatch between the learning rate and the momentum in the MLP will drastically reduce the accuracy of the model). In contrast, Random Forest has no parameter to be tuned and its prediction is almost as good as MLPs for surface roughness, so Random Forest will be more suitable for industrial use where no expert in AI model tuning is available. Moreover, the inclusion of the isotropy level in the dataset, especially as a numeric attribute, greatly improved the accuracy of the models, in some cases, by up to 52% for MLPs, and by a smaller proportion of 16% in the Random Forest models in terms of Root Mean Square Error. Finally, Random Forest ensembles only trained with low and very high isotropy level experimental datasets generated reliable models for medium levels of isotropy, thereby offering a solution to reduce the size of training datasets.

54 citations