Issam Hanafi

Multiple Regression Prediction Model for Cutting Forces in Turning Carbon-Reinforced PEEK CF30

Among the thermoplastic polymers available, the reinforced polyetheretherketone with 30% of carbon fibres (PEEK CF 30) demonstrates a particularly good combination of strength, rigidity, and hardness, which prove ideal for industrial applications. Considering these properties and potential areas of application, it is necessary to investigate the machining of PEEK CF30. In this study, response surface methodology was applied to predict the cutting forces in turning operations using TiN-coated cutting tools under dry conditions where the machining parameters are cutting speed ranges, feed rate, and depth of cut. For this study, the experiments have been conducted using full factorial design in the design of experiments (DOEs) on CNC turning machine. Based on statistical analysis, multiple quadratic regression model for cutting forces was derived with satisfactory 𝑅2-squared correlation. This model proved to be highly preferment for predicting cutting forces.

Multi-criteria Optimization Using Taguchi and Grey Relational Analysis in CNC Turning of PEEK CF30

The robust design of turning parameters is dealing with the optimization of surface roughness and cutting force in turning of reinforced polyetheretherketone (PEEK) with 30% of carbon fibers (PEEK CF30) using TiN-coated cutting tools. The selected turning parameters include the cutting speed, feed rate and depth of cut. Grey–Taguchi method is combining orthogonal array design of experiments with relational analysis, which enables the determination of the optimal combination of turning parameters with the multiple criteria. The basic aim of grey relational analysis is to find the grey relational grade, which can be used for the optimization conversion from a multi-criteria problem to a single objective problem. This study not only proposes a novel optimization technique, but also contributes the satisfactory solution for multiple CNC turning objectives with profound insight.

Fuzzy Logic-Based Modeling of Surface Roughness Parameters for CNC Turning of PEEK CF30 by TiN-Coated Cutting Tools

An important range of existing engineered industrial parts consists of plastic materials that are reinforced with carbon fibers. Due to their excellent mechanical and thermal properties, machined mechanical parts made from reinforced polyetheretherketone (PEEK) composite materials have become standard in many high-technology engineering fields such as aerospace, automotive, and electronics. There is however a crucial need to predict the machining criteria for reinforced PEEK composite materials in order to optimize their fabrication process. In this article, the process parameters including cutting speed, feed rate, and depth of cut are investigated. A fuzzy rule-based model was derived to predict the surface roughness parameters Ra and Rt, in dry turning of reinforced PEEK with 30% of carbon fibers using TiN-coated cutting tools. The model was identified using results of experiments carried out according to Taguchi method. Predictions of the fuzzy-based model were found to fit, very well, experimental data with a correlation coefficient as high as 99%.

Prediction of surface roughness in turning of PEEK cf30 by using an artificial neural network

Surface roughness parameters Ra and Rt are mostly used as an index to determine the surface finish quality in the process of machining. Because of the strong nonlinear character of relationships between the process inputs and outputs, it is difficult to accurately estimate roughness characteristics by using traditional modeling techniques. In this work, accurate prediction of the Ra and Rt values during machining of reinforced poly ether ether ketone (PEEK) CF30 with TiN coated tools is achieved. The modeling is performed by using artificial neural network approach to represent the complex relationships between cutting conditions and surface roughness parameters. The input cutting parameters include cutting speed, depth of cut and feed rate. The network was trained with pairs of inputs and outputs datasets generated by machining experimental results that were obtained according to a full factorial design of experiment table. Predictions of the ANN based model were found to fit experimental data very well with a correlation coefficient as high as 99%. Complementary results that were not used during derivation of the ANN model have enabled one to assess the validity of the obtained predictions.

UTILIZACIÓN DE MODELOS DE REDES NEURONALES ARTIFICIALES PARA PREDECIR LA INFLUENCIA DEL TIPO DE FRESADO EN LA CALIDAD DEL PRODUCTO

RESUMEN: Durante el proceso de fresado de piezas de superficies complejas, la eleccion de las distintas estrategias de mecanizado sugeridas por el software CAM conduce a desviaciones de la pieza mecanizada con respecto a la superficie ideal disenada. El conocimiento de las desviaciones generadas respecto de la geometria final de la pieza permite desarrollar modulos de correccion en el propio software, basados en las diferentes estrategias de mecanizado, posibilitando asi que el ejecutor genere las oportunas correcciones antes de la fabricacion, de manera que los productos acabados se encuentren dentro de las especificaciones de diseno. Al mismo tiempo, se ha estudiado el trabajo SIM en los procesos de fabricacion mediante la aplicacion de redes neuronales artificiales (ANN) como solucion a los problemas no lineales y parametros conflictivos. Por lo tanto, este documento evalua la influencia de la geometria y el acabado superficial de tres estrategias diferentes de fresado, sugeridas por un software de CAM en la fabricacion de un producto, por medio de RNA.

Modelling of machining force components during turning of PEEK CF30 by TiN coated cutting tools using artificial intelligence

Machined mechanical parts made from reinforced polyetheretherketone (PEEK) composite materials have become standard in many high-technology engineering fields. Considering their properties and potential areas of application it is necessary to investigate the machining of reinforced PEEK composite with 30% of carbon fibre (PEEK CF30). In this study, dry turning tests were carried out on PEEK CF 30 specimens using TiN coated cutting tool. An L27 orthogonal array was used for tests. A fuzzy rule-based model is developed to predict the machining force components in turning of carbon fibre-reinforced polymer (CFRP) composites. Good agreement is observed between the predictive model results and the experimental values. The fuzzy rule-based model can be used effectively for predicting the machining force components in turning CFRP composites.

Grey-fuzzy optimisation model for multi performance in CNC turning processes

The reinforced polyetheretherketone with 30% of carbon fibres (PEEK-CF30) reveals a particularly good combination of strength, rigidity, and hardness, which prove ideal for industrial applications. Considering these properties and potential areas of application, it is necessary to investigate and optimise the machining of PEEK-CF30. The Grey-fuzzy logic based on orthogonal array for optimising the machining process with multi-response has been reported. An orthogonal array and Grey-fuzzy reasoning grade are applied to study the multi performance characteristics of the machining process. The machining parameters (cutting speed, feed rate and depth of cut) with considerations of multiple responses (roughness surface and cutting force) are effective. The experimental results using the optimal setting easily clarified that the abovementioned optimum procedure greatly improved the manufacturing process in this study.

Optimization of cutting parameters in CNC turning operation using Taguchi design of experiments

Abstract Non-reinforced and reinforced Poly-Ether-Ether-Ketone (PEEK) plastics have excellent mechanical and thermal properties. Machining is an efficient process that can be used to manufacture specific mechanical parts made from PEEK composites. Researchers have focused on improving the performance of machining operations with the aim of minimizing costs and improving quality of manufactured products, in order to get the best surface roughness and the minimum cutting force. The parameters evaluated are the cutting speed, the depth of cut and the feed rate. In this paper, the effect of the mentioned parameters on surface roughness and cutting force, in dry turning of reinforced PEEK with 30% of carbon fibers (PEEK CF30) using TiN coated cutting tools, is analyzed through using robust design techniques such as Taguchis design method, signal-to-noise (S/N) ratio and statistical analysis tools such as Pareto-ANOVA. The obtained results have shown that Taguchi method and Pareto ANOVA are suitable for optimi...

Vacuum Thermoforming Process: An Approach to Modeling and Optimization Using Artificial Neural Networks

In the vacuum thermoforming process, the group effects of the processing parameters, when related to the minimizing of the product deviations set, have conflicting and non-linear values which make their mathematical modelling complex and multi-objective. Therefore, this work developed models of prediction and optimization using artificial neural networks (ANN), having the processing parameters set as the networks’ inputs and the deviations group as the outputs and, furthermore, an objective function of deviation minimization. For the ANN data, samples were produced in experimental tests of a product standard in polystyrene, through a fractional factorial design (2k-p). Preliminary computational studies were carried out with various ANN structures and configurations with the test data until reaching satisfactory models and, afterwards, multi-criteria optimization models were developed. The validation tests were developed with the models’ predictions and solutions showed that the estimates for them have prediction errors within the limit of values found in the samples produced. Thus, it was demonstrated that, within certain limits, the ANN models are valid to model the vacuum thermoforming process using multiple parameters for the input and objective, by means of reduced data quantity.

Dimensional and Geometrical Errors in Vacuum Thermoforming Products: An Approach to Modeling and Optimization by Multiple Response Optimization

Abstract In the vacuum thermoforming process, the product deviations depend on several parameters of the system, which make the analysis, the computational modeling, and the optimization of errors a multi-variable process with conflicting objectives. In this sense, the aim of this work was to study the dimensional and geometrical errors as well as the optimization (minimization) of these errors in one typical vacuum thermoforming product made of polystyrene (PS). In particular, it was intended to predict and minimize errors in a range of ideal tolerances using Multiple Response Optimization (MRO) Models. Thus, through the fractional factorial design (2k-p), initial experimental tests were performed using proposed measurement procedures, and Analysis of Variance being the data analysis is discussed. Following that, the MRO models were implemented which were also validated to represent the sample data. Through this analysis of the results, it can be concluded that the regression models of errors are not linear functions, hence, the developed models are valid for the studied process, and finally that the validation results proved the efficiency of MOR models developed, but these models will not be able to generalize to new situations in a range far from the values studied.