Taguchi Method–GONNS integration: Complete procedure covering from experimental design to complex optimization

Determination of the optimal operating conditions from the experimental data without fitting any analytical or empirical models is very convenient for manufacturing applications. In this paper, integration of Taguchi Method and Genetically Optimized Neural Networks (GONNS) is proposed. The proposed procedure covers all the steps from experimental design to complex optimization. The feasibility of the approach was evaluated by estimating the optimal cutting conditions for the milling of Ti6Al4V titanium alloy with PVD coated inserts. The test conditions were determined by the Taguchi Method. The optimal cutting condition and influences of the cutting speed, feed rate and cutting depth on the surface roughness were analyzed with the same method. GONNS estimated that the optimal cutting conditions were very close to the Taguchi Method when the same criterion was used. GONNS was also capable to minimize or maximize one of the output parameters while the others were kept within the desired range. Study demonstrated that Taguchi Method and GONNS complement each other for creation of a robust procedure for determination of the test conditions, analysis of the quality of the collected data, estimation of the influence of each parameter on the output(s) and estimation of optimal conditions with complex optimization objective functions.     

Zigzag machining surface roughness modelling using evolutionary approach

Milling is one of the common machining methods that cannot be abandoned especially for machining of metallic materials. The cutters with appropriate cutting parameters remove material from the workpiece. Surface roughness has the major influence on both obtaining dimensional accuracy and quality of the product. A number of cutter path strategies are employed to obtain the required surface quality. Zigzag machining is one of the mostly appealing cutting processes. Modeling of surface roughness with traditional methods often results in inadequate solutions and can be very costly in terms of the efforts and the time spent. In this research Genetic Programming (GP) has employed to predict a surface roughness model based on the experimental data. The model has produced an accuracy of 86.43%. In order to compare GP performance, Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) techniques were utilized. It was seen that the surface roughness model produced by GP not only outperforms but also enables to produce more explicit models than of the other techniques. The effective parameters can easily be investigated based on the appearances in the model and they can be used in prediction of surface roughness in zigzag machining process.     

A comparative study on modelling material removal rate by ANFIS and polynomial methods in electrical discharge machining process

Due to the controversy associated with modelling Electrical Discharge Machining (EDM) processes based on physical laws; this task is predominantly accomplished using empirical modelling methods. The modelling studies reported in the literature deal predominantly with quantitative parameters i.e. ones with numerical levels. In fact, modelling categorical parameters has been devoted a scant attention. This study reports the results of an EDM experiment conducted on the Ti–6Al–4V alloy. Its aim was to model the relationship between the Material Removal Rate (MRR) and the parameters of the process, namely, current, pulse on-time and pulse off-time along with a categorical factor (electrode material). The modelling process was accomplished using adaptive neuro-fuzzy inference system (ANFIS) and polynomial modelling approaches. In fact, one purpose of this study was to compare the performance of these modelling approaches as no study was found contrasting their prediction capability in the literature. Regarding the polynomial model, two numerical parameters (current and pulse on-time) were declared significant in the ANOVA together with the electrode material and its interaction with pulse on-time. Thus, they were all incorporated in the developed polynomial model. Furthermore, five ANFIS models with 6, 9, 19, 21 and 51 rules were developed utilizing the first order Sugeno fuzzy approach by back-propagation neural networks training algorithm. Of these, the ANFIS model with 21 rules was the best. This model also outperformed the polynomial model remarkably in terms of predicting error, residuals range and the correlation coefficient between the experimental and predicted MRR values. The study sheds light on the powerful learning capability of ANFIS models and its superiority over the conventional polynomial models in terms of modelling complex non-linear machining processes.     

Optimization of magnetic field assisted EDM using the continuous ACO algorithm

In this paper, a rotary tool with rotary magnetic field has been used to better flushing of the debris from the machining zone in electrical discharge machining (EDM) process. Two adaptive neuro-fuzzy inference system (ANFIS) models have been designed to correlate the EDM parameters to material removal rate (MRR) and surface roughness (SR) using the data generated based on experimental observations. Then continuous ant colony optimization (CACO) technique has been used to select the best process parameters for maximum MRR and specified SR. Here, the process parameters are magnetic field intensity, rotational speed and product of current and pulse on-time. Also, ANFIS models of MRR and SR are the objective and constraint functions for CACO, respectively. Experimental trials divided into three main regimes of low energy, the middle energy and the high energy. Results showed that the CACO technique which used the ANFIS models as objective and constrain functions can successfully optimize the input conditions of the magnetic field assisted rotary EDM process.     

An adaptive neuro-fuzzy inference system (ANFIS) model for wire-EDM

A wire electrical discharge machined (WEDM) surface is characterized by its roughness and metallographic properties. Surface roughness and white layer thickness (WLT) are the main indicators of quality of a component for WEDM. In this paper an adaptive neuro-fuzzy inference system (ANFIS) model has been developed for the prediction of the white layer thickness (WLT) and the average surface roughness achieved as a function of the process parameters. Pulse duration, open circuit voltage, dielectric flushing pressure and wire feed rate were taken as model’s input features. The model combined modeling function of fuzzy inference with the learning ability of artificial neural network; and a set of rules has been generated directly from the experimental data. The model’s predictions were compared with experimental results for verifying the approach.     

MACHINED SURFACE ROUGHNESS PREDICTION USING ADAPTIVE NEUROFUZZY INFERENCE SYSTEM

This work considers the effect of the depth of cut, feed, and number of revolutions on the roughness of the machined surface. The results obtained by experimentally investigating the workpiece “diving manifold” were used to model the input/output data plan for the adaptive neurofuzzy inference system (ANFIS). Those data were used to generate a fuzzy inference system that made it possible to predict the output (surface roughness) based on the given inputs (feed, number of revolutions, and depth of cut). The surface roughness results obtained by the fuzzy inference system (FIS) were compared with the surface roughness results obtained by neural networks, moving linear least square method and moving linear least absolute deviation method on the same set of experimental data. These methods and systems for prediction of surface roughness are helpful when solving practical technological problems in a manufacturing process, first by determining the cutting parameter values that will add to the demanded quality of a product, and later when optimizing the technological process.     

Prediction of surface roughness during hard turning of AISI 4340 steel (69 HRC)

In this study, 39 sets of hard turning (HT) experimental trials were performed on a Mori-Seiki SL-25Y (4-axis) computer numerical controlled (CNC) lathe to study the effect of cutting parameters in influencing the machined surface roughness. In all the trials, AISI 4340 steel workpiece (hardened up to 69 HRC) was machined with a commercially available CBN insert (Warren Tooling Limited, UK) under dry conditions. The surface topography of the machined samples was examined by using a white light interferometer and a reconfirmation of measurement was done using a Form Talysurf. The machining outcome was used as an input to develop various regression models to predict the average machined surface roughness on this material. Three regression models – Multiple regression, Random forest, and Quantile regression were applied to the experimental outcomes. To the best of the authors’ knowledge, this paper is the first to apply random forest or quantile regression techniques to the machining domain. The performance of these models was compared to ascertain how feed, depth of cut, and spindle speed affect surface roughness and finally to obtain a mathematical equation correlating these variables. It was concluded that the random forest regression model is a superior choice over multiple regression models for prediction of surface roughness during machining of AISI 4340 steel (69 HRC).     

Investigation of surface roughness in the milling of Al7075 and open-cell SiC foam composite and optimization of machining parameters

In the present study, aluminum alloy 7075 (Al7075)-based open-cell silicon carbide (SiC) foam composite was fabricated and the machinability of both Al7075 and the open-cell SiC foam Al metal matrix composite was investigated during milling using an uncoated carbide tool. The machining trials were conducted using the Taguchi L₂₇ full-factorial orthogonal array, and the milling parameters were optimized for surface roughness. Analysis of variance was employed to determine the effect of the cutting variables on surface roughness. The experimental results were evaluated by signal-to-noise ratio, 3D surface graphs, artificial neural networks (ANNs) and main effect graphs. The analysis results show that the feed rate was the most significant milling parameter affecting surface roughness of both Al7075 and the open-cell SiC foam composite. Prediction models have been developed for the surface roughness through regression analysis and ANNs. Confirmation experiments were performed to identify the performance of mathematical models, and the surface roughness was predicted with a mean squared error equal to 1.6 and 0.24 % in the milling of Al7075 and open-cell SiC foam composite, respectively. The test result showed that the three-dimensional open-pore SiC foam network reinforcement was restricted the movement of the soft matrix and provided an acceptable surface quality in the milling of MMCs.

     

Optimization studies in high speed turning of Ti-6Al-4V

Surface roughness is a major concern to the present manufacturing sector without the wastage of material. Hence, in order to achieve good surface roughness and reduce production time, optimization is necessary. In this study optimization techniques based on swarm intelligence (SI) namely firefly algorithm (FA), particle swarm optimization (PSO) and a newly introduced metaheuristic algorithm namely bat algorithm (BA) has been implemented for optimizing machining parameters namely cutting speed, feed rate, depth of cut and tool flank wear and cutting tool vibrations in order to achieve minimum surface roughness. Two parameters R_a and R_t have been considered for evaluating the surface roughness. The performance of BA algorithm has been compared with FA algorithm and PSO, which is a commonly and widely used optimization algorithm in machining. The results conclude that BA produces better optimization, when compared to FA and PSO. Based on the literature review carried out, this work is a first attempt at using a metaheuristic algorithm namely BA in machining applications.     

Estimation of optimal machining control parameters using artificial bee colony

Modern machining processes such as abrasive waterjet (AWJ) are widely used in manufacturing industries nowadays. Optimizing the machining control parameters are essential in order to provide a better quality and economics machining. It was reported by previous researches that artificial bee colony (ABC) algorithm has less computation time requirement and offered optimal solution due to its excellent global and local search capability compared to the other optimization soft computing techniques. This research employed ABC algorithm to optimize the machining control parameters that lead to a minimum surface roughness (R \(_{a})\) value for AWJ machining. Five machining control parameters that are optimized using ABC algorithm include traverse speed (V), waterjet pressure (P), standoff distance (h), abrasive grit size (d) and abrasive flow rate (m). From the experimental results, the performance of ABC was much superior where the estimated minimum R \(_{a }\) value was 28, 42, 45, 2 and 0.9 % lower compared to actual machining, regression, artificial neural network (ANN), genetic algorithm (GA) and simulated annealing (SA) respectively.     

Glowworm swarm optimization (GSO) for optimization of machining parameters

This study proposes glowworm swarm optimization (GSO) algorithm to estimate an improved value of machining performance measurement. GSO is a recent nature-inspired optimization algorithm that simulates the behavior of the lighting worms. To the best our knowledge, GSO algorithm has not yet been used for optimization practice particularly in machining process. Three cutting parameters of end milling that influence the machining performance measurement, minimum surface roughness, are cutting speed, feed rate and depth of cut. Taguchi method is performed for experimental design. The analysis of variance is applied to investigate effects of cutting speed, feed rate and depth of cut on surface roughness. GSO has improved machining process by estimating a much lower value of minimum surface roughness compared to the results of experimental and particle swarm optimization.     

Shear localization sensitivity analysis for Johnson–Cook constitutive parameters on serrated chips in high speed machining of Ti6Al4V

This research aims to investigate the influence of material constitutive parameters on the serrated chip formation during high speed machining (HSM) of Ti6Al4V alloys with finite element simulations and cutting experiments. The Johnson–Cook (JC) constitutive model and JC fracture model with an energy-based ductile failure criterion are adopted to simulate the HSM process. Five JC constitutive model parameters such as initial yield stress, hardening modulus, strain hardening coefficient, strain rate dependency coefficient, and thermal softening coefficient are included in this research. Shear localization sensitivity is novelly proposed to describe variations of serrated chips under different JC constitutive model parameters. Shear localization sensitivity is subdivided into chip serration sensitivity and chip bending sensitivity. The research finds that the influences of initial yield stress and thermal softening coefficient parameters on the chip serration and bending are much more prominent than those of the rest three JC constitutive model parameters. With initial yield stress or hardening modulus in JC constitutive model increasing, the chip serration sensitivity increases and the chip bending sensitivity decreases. However, the influences of the rest three parameters on chip serration sensitivity are opposite. High speed orthogonal cutting experiments of Ti6Al4V are carried out to validate the simulation results under different cutting speeds ranging from 50 m/min to 3000 m/min and fixed uncut chip thickness with 0.1 mm. The results show that the serrated degree of chips increases with the cutting speed increasing until the chips become completely fragmented. The cutting speed break point of chip morphology from serrated to fragmented ones for Ti6Al4V is about 2500 m/min. The average cutting force decreases with the cutting speed increasing, which is a prominent advantage for HSM. This paper can help to get deeper insights into the serrated chip formation mechanism in HSM.     

Kernel based regression and genetic algorithms for estimating cutting conditions of surface roughness in end milling machining process

We observe a surface roughness in end milling machining process which is influenced by machine parameters, namely radial rake angle, speed and feed rate cutting condition. In this machining, we need to minimize and to obtain as low as possible the surface roughness by determining the optimum values of the three parameters. In previous works, some researchers used a response surface methodology (RSM) and a soft-computing approach, which was based on ordinary linear regression and genetic algorithms (GAs), to estimate the minimum surface roughness and its corresponding values of the parameters. However, the construction of the ordinary regression models was conducted without considering the existence of multicollinearity which can lead to inappropriate prediction. Beside that it is known the relation between the surface roughness and the three parameters is nonlinear, which implies that a linear regression model can be inappropriate model to approximate it. In this paper, we present a technique developed using hybridization of kernel principal component analysis (KPCA) based nonlinear regression and GAs to estimate the optimum values of the three parameters such that the estimated surface roughness is as low as possible. We use KPCA based regression to construct a nonlinear regression and to avoid the effect of multicollinearity in its prediction model. We show that the proposed technique gives more accurate prediction model than the ordinary linear regression’s approach. Comparing with the experiment data and RSM, our technique reduces the minimum surface roughness by about 45.3% and 54.2%, respectively.     

Digital twin-driven surface roughness prediction and process parameter adaptive optimization

In the process of parts machining, the real-time state of equipment such as tool wear will change dynamically with the cutting process, and then affect the surface roughness of parts. The traditional process parameter optimization method is difficult to take into account the uncertain factors in the machining process, and cannot meet the requirements of real-time and predictability of process parameter optimization in intelligent manufacturing. To solve this problem, a digital twin-driven surface roughness prediction and process parameter adaptive optimization method is proposed. Firstly, a digital twin containing machining elements is constructed to monitor the machining process in real-time and serve as a data source for process parameter optimization; Then IPSO-GRNN (Improved Particle Swarm Optimization-Generalized Regression Neural Networks) prediction model is constructed to realize tool wear prediction and surface roughness prediction based on data; Finally, when the surface roughness predicted based on the real-time data fails to meet the processing requirements, the digital twin system will warn and perform adaptive optimization of cutting parameters based on the currently predicted tool wear. Through the development of a process-optimized digital twin system and a large number of cutting tests, the effectiveness and advancement of the method proposed in this paper are verified. The organic combination of real-time monitoring, accurate prediction, and optimization decision-making in the machining process is realized which solves the problem of inconsistency between quality and efficiency of the machining process.     

A particle swarm approach for multi-objective optimization of electrical discharge machining process

This paper proposes an experimental investigation and optimization of various machining parameters for the die-sinking electrical discharge machining (EDM) process using a multi-objective particle swarm (MOPSO) algorithm. A Box–Behnken design of response surface methodology has been adopted to estimate the effect of machining parameters on the responses. The responses used in the analysis are material removal rate, electrode wear ratio, surface roughness and radial overcut. The machining parameters considered in the study are open circuit voltage, discharge current, pulse-on-time, duty factor, flushing pressure and tool material. Fifty four experimental runs are conducted using Inconel 718 super alloy as work piece material and the influence of parameters on each response is analysed. It is observed that tool material, discharge current and pulse-on-time have significant effect on machinability characteristics of Inconel 718. Finally, a novel MOPSO algorithm has been proposed for simultaneous optimization of multiple responses. Mutation operator, predominantly used in genetic algorithm, has been introduced in the MOPSO algorithm to avoid premature convergence. The Pareto-optimal solutions obtained through MOPSO have been ranked by the composite scores obtained through maximum deviation theory to avoid subjectiveness and impreciseness in the decision making. The analysis offers useful information for controlling the machining parameters to improve the accuracy of the EDMed components.     

Modeling and prediction of machining quality in CNC turning process using intelligent hybrid decision making tools

Decision-making process in manufacturing environment is increasingly difficult due to the rapid changes in design and demand of quality products. To make decision making process (selection of machining parameters) online, effective and efficient artificial intelligent tools like neural networks are being attempted. This paper proposes the development of neural network models for prediction of machining parameters in CNC turning process. Experiments are designed based on Taguchi's Design of Experiments (DoE) and conducted with cutting speed, feed rate, depth of cut and nose radius as the process parameters and surface roughness and power consumption as objectives. Results from experiments are used to train the developed neuro based hybrid models. Among the developed models, performance of neural network model trained with particle swarm optimization model is superior in terms of computational speed and accuracy. Developed models are validated and reported. Signal-to-noise (S/N) ratios of responses are calculated to identify the influences of process parameters using analysis of variance (ANOVA) analysis. The developed model can be used in automotive industries for deciding the machining parameters to attain quality with minimum power consumption and hence maximum productivity.     

Adaptive network-based fuzzy inference system for prediction of surface roughness in end milling process using hybrid Taguchi-genetic learning algorithm

In this paper, an adaptive network-based fuzzy inference system (ANFIS) with the genetic learning algorithm is used to predict the workpiece surface roughness for the end milling process. The hybrid Taguchi-genetic learning algorithm (HTGLA) is applied in the ANFIS to determine the most suitable membership functions and to simultaneously find the optimal premise and consequent parameters by directly minimizing the root-mean-squared-error performance criterion. Experimental results show that the HTGLA-based ANFIS approach outperforms the ANFIS methods given in the Matlab toolbox and reported recently in the literature in terms of prediction accuracy.     

Thermodynamic assessment of the ordered B2 phase in the Ti-V-Cr-Al quaternary system

Thermodynamic assessment of the ordered B2 phase in the quaternary Ti-V-Cr-Al system is carried out. A set of self-consistent thermodynamic parameters is presented. A two-sublattice model (Al,Cr,Ti,V )_0.5: (Al,Cr,Ti,V )_0.5 is used. The predicted phase equilibria and order/disorder transformation temperature are in good agreement with experimental information, both in the Ti-V-Cr-Al quaternary and in the important binary and ternary subsystems. The thermodynamic dataset can be used to predict compositions which are prone to the order/disorder reaction.     

YSZ表面粗糙度对氧传感器性能的影响

借助表面粗糙度测试技术和循环伏安方法,研究了用Pt浆法制备Pt/YSZ电极过程中,YSZ表面粗糙度对其性能的影响。研究表明:Pt/YSZ电极制作时,所用金刚石磨片粒径大小对YSZ表面粗糙度间距参数无明显影响,但YSZ表面粗糙度高度参数则随着金刚石磨片粒径的增大而增大;当所用金刚石磨片粒径为44μm时,电极阴极活性(电位为-0.4 V时)最低,10μm时最高,约为44μm所制电极的2倍,其他电极则介于两者之间。     

Evolutionary neuro-fuzzy system for surface roughness evaluation

The paper presents a system that, according to the requirements referring to the product quality given in surface roughness, with minimum machining time and maximum metal removal rate, recommends optimal cutting parameters with the possibility of surface roughness control during the machining process. The suggested evolutionary neuro-fuzzy system for evaluation of surface roughness is composed of three units: surface roughness prediction by cutting parameters, multi-objective optimization of cutting parameters aimed at minimum machining time and maximum metal removal rate and control of obtained or required surface roughness by means of the features quantified from digital image of the observed machined surface. The paper outlines the idea and architecture of the system as well as the possibilities of implementation. The obtained results, illustrated by experimental research, justify the application and further development of the suggested evolutionary neuro-fuzzy system for evaluation of surface roughness within the given constraints.