Surface roughness prediction in machining using soft computing

The present research work explores the implementation of three smart hybrid predictive models based on the adaptive neuro-fuzzy inference system (ANFIS), ANFIS and genetic algorithm (GA), and ANFIS and particle swarm optimization (PSO). All such strategies have been used to determine and compare machining key elements including material removal rate (MRR) and surface roughness (SR) during the gas-assisted electrical discharge (GAEDM) process. In this study, inert gas-based EDM with a multi-hole rotating tool has been carried out. In this experimentation, pulse-on time, peak current, duty cycle, electrode rotation, and gas discharge pressure were selected as input factors. The proposed method is to upgrade ANFIS with GA and PSO techniques. The GA and PSO algorithms are used to enhance the accuracy of the ANFIS model. The models have been trained, tested, and validated with observational results. Statistical techniques were applied to assess the effectiveness of the predictive capability models established through the ANFIS, ANFIS-GA, and ANFIS-PSO techniques. The actual and predicated estimates of MRR and SR of the GAEDM, obtained by ANFIS, ANFIS-GA, and ANFIS-PSO, were observed to be as per one another. In addition, the ANFIS-PSO framework proved to be even more responsive when compared with the ANFIS and the ANFIS-GA system. In particular, the assertion of this work is that modified algorithms such as ANFIS-GA and ANFIS-PSO are an efficient and productive approach to accurate EDM response estimation.

This study evaluates the impacts of machining parameters on the milling of general-purpose poly (methyl methacrylate) (PMMA) with respect to cutting point temperature, maximum machining temperature, and surface roughness. The machining parameters used in the analysis are spindle speed (rpm), depth of cut (mm), and feed rate (mm/min). The extreme ranges of the machining parameters for the material are obtained from trial experiments. From these experiments, four values of each parameter are adopted. This yields 12 experiments, which are divided into three sets. In the first set of experiments, the depth of cut and feed rate are held constant at 0.2 mm and 25 mm/min, while the spindle speed is varied from 1000 rpm to 4000 rpm. In the second set of experiments, the spindle speed and feed rate are held constant at 1000 rpm and 25 mm/min, respectively, while the depth of cut is varied from 0.2 mm to 1.1 mm. In the last set of experiments, the spindle speed and depth of cut are held constant at 1000 rpm and 0.2 mm, respectively, as the feed rate is varied from 25 mm/min to 100 mm/min. Thermal images are obtained during milling, where the cutting point and maximum machining temperatures are obtained. The milled surfaces are then investigated for surface roughness. The chips are also collected from each experiment and used in conducting chip morphology. From the results, it is observed that to obtain the least temperatures and best surface quality, the least machining parameters should be chosen. These parameters are identified as 1000 rpm, 0.2 mm, and 25 mm/min for the spindle speed, depth of cut, and feed rate, respectively. An increase in spindle speed seems to increase the milling temperatures and surface roughness, which is attributed to the reducing chip thickness. An increase in the depth of cut does not affect the generation of chips, and the thickness is relatively constant. However, an increase in milling feed increases the chip thickness, which increases the surface roughness.

In the power diode laser beam machining (DLBM) process, the kerf width (KW) and surface roughness (SR) are important factors in evaluating the cutting quality of the machined specimens. Apart from determining the influence of process parameters on these factors, it is also very important to adopt multi-response optimization approaches for them, in order to achieve better processing of specimens, especially for hard-to-cut materials. In this investigation, adaptive neuro-fuzzy inference system (ANFIS) and genetic algorithm tuned ANFIS (GA-ANFIS) were used to predict the KW on a titanium alloy workpiece during DLBM. Five machining process factors, namely power diode, standoff distance, feed rate, duty cycle, and frequency, were used for the development of the model due to their correlation with KW. As in some cases, traditional soft computing methods cannot achieve high accuracy; in this investigation, an endeavor was made to introduce the GA-assisted ANFIS technique to predict kerf width while machining grooves in a titanium alloy workpiece using the DLBM process based on experimental results of a total of 50 combinations of the process parameters. It was observed that FIS was tuned well using the ANN in the ANFIS model with an R2 value of 0.99 for the training data but only 0.94 value for the testing dataset. The predicting performance of the GA-ANFIS model was better with less value for error parameters (MSE, RMSE, MAE) and a higher R2 value of 0.98 across different folds. Comparison with other state-of-the-art models further indicated the superiority of the GA-ANFIS predictive model, as its performance was superior in terms of all metrics. Finally, the optimal process parameters for minimum KW and SR, from gray relational–based (GRB) multi-response optimization (MRO) approach, were found as 20 W (level 2) for laser power, 22 mm (level 5) for standoff distance, 300 mm/min (level 5) for feed rate, 85% (level 5) for duty cycle, and 18 kHz (level 3) for frequency.

ABSTRACTThe paper deals with the parametric analysis and ANFIS-based modeling of process parameters during turning operation of stainless steel 202. In this experimental work, the Taguchi L16 DOE was utilized for designing the experiments considering three turning parameters namely feed rate, spindle speed as well as depth of cut. All the experiment was conducted at different parametric combinations and the performance namely material removal rate (MRR) and surface roughness (Ra) were evaluated. With the help of a suitable plot, the influences of process parameters on performance were analyzed. It was observed that depth of cutis is the majority influencing parameter for varying (parametric contribution is 53.33%) the MRR, whereas in case of surface roughness, the most contributing parameter is the spindle speed (parametric contribution is 95.71%). Further, the adaptive network-based fuzzy inference system (ANFIS) based modeling has been done to understand and establish the input-output relationship. The experimental results and ANFIS predicted results were compared and it is found that the ANFIS predicted results are accurate for predicting the responses during turning operation of stainless steel 202.

In this paper, a hybrid meta-heuristic artificial intelligence (AI) method, named “ANFIS–PSOGA,” is developed for modeling the discharge coefficient of circular side orifices for the first time. For this purpose, the adaptive neuro fuzzy inference system (ANFIS) network is optimized by means of two robust optimization algorithms: the genetic algorithm (GA) and the particle swarm optimization (PSO) algorithm. Furthermore, the Monte Carlo simulations are utilized to enhance the performance of the AI hybrid model. Besides, the k-fold cross-validation method is employed in order to verify the numerical results. Initially, the performance of three fuzzy inference system (FIS) generations of the ANFIS model including grid partitioning, subtractive clustering and fuzzy C-means clustering are evaluated. After that, using the parameters affecting the discharge coefficient, eleven ANFIS models are defined and then the best ANFIS model and the most influencing input parameters are identified through the conduction of a sensitivity analysis. For the superior ANFIS model, mean absolute percentage error, root-mean-square error and the correlation coefficient (R) are obtained 0.021, 0.020 and 0.871, respectively. Also, the Froude number (Fr) is detected as the most effective input parameter. Moreover, the discharge coefficient of the circular side orifices and the flow field within main channels along the side orifices are simulated through the adoption of a computational fluid dynamics (CFD) model. Additionally, the flow field at three different cross sections (beginning, middle and end of orifice) along the side weir is evaluated. For instance, by advancing the flow toward the side orifice, the Froude number is reduced. Besides, at each cross section, the maximum shear stress is estimated to occur in the vicinity of the crest of the circular side orifice. According to the CFD results, the maximum lateral velocity is estimated near the circular side orifice. In addition, the results yielded by the ANFIS, ANFIS–PSO, ANFIS–PSOGA and CFD models are compared and an uncertainty analysis is carried out for the models. Based on the comparison, ANFIS–PSOGA has the best performance in simulating the discharge coefficient. Ultimately, a simple and practical computer code for the best model (ANFIS–PSOGA) is proposed which can be easily used by scholars and engineers in practical usages.

The chapter presents the critical review on the machining parameters of fibre-reinforced polymer (FRP) composites, such as glass fibre composites, carbon fibre composites and jute/epoxy composites etc. Over the past few years, the use of FRPs has increased because of its good strength-to-weight ratio; however, it requires further machining during the joining of two components with the help of fasteners. To date, conventional drilling is used to drill the holes. Drilling of holes may induce damage to the part. Operating parameters, such as thrust force and torque induced during the drilling operation need to be studied and knowledge database needs to be developed. This chapter deals with the drilling aspects of polymer composites in detail. A comparative study has been made for three different drill point geometries with different spindle speeds and feed rates. Different predictive models, such as artificial neural network (ANN), fuzzy logic and adaptive neuro fuzzy inference system (ANFIS) are used to predict drilling induced damage, thrust force and torque induced while drilling of the fibre-reinforced polymer composites.

This study examined the modelling and optimisation of the electrocoagulation-flocculation (ECF) recovery of aquaculture effluent (AQE) using aluminium electrodes. The response surface methodology (RSM), artificial neural network (ANN), and adaptive neuro-fuzzy inference system (ANFIS) were used for the modelling, while the optimisation tools were the numerical RSM and genetic algorithm (GA). Furthermore, the kinetics of the ECF process was studied to provide insight into the mechanism governing the ECF of AQE. The experimental design was performed using the central composite design (CCD) of the RSM. The ANFIS modelling was accomplished via the Grid Partition (GP) of the data set, while the ANN used the multi-layer perceptron (MLP) based feed-forward system. Statistically, the prediction accuracy of the models followed the order: ANFIS (R2: 0.9990), ANN (R2: 0.9807), and RSM (R2: 0.9790). The process optimisation gave optimal turbidity (TD) removal efficiencies of 98.98, 97.81, and 96.01% for ANFIS-GA, ANN-GA, and RSM optimisation techniques, respectively. The ANFIS-GA gave the best optimization result at optimum conditions of pH 4, current intensity (3 A), electrolysis time (7.2min), settling time (23min), and temperature (43.8°C). In the kinetics study, the experimental data was analysed using pseudo-first-order (0.8787), pseudo-second-order (0.9395), and Elovich (R2: 0.9979) kinetic models; the Elovich model gave the best correlation with the experimental data showing that the process is governed by electrostatic interaction mechanism. This study effectively demonstrated that ECF recovery of AQE can effectively be modelled using RSM, ANN, and ANFIS and be optimised using RSM, ANN-GA, and ANFIS-GA techniques, and the order of performance is ANFIS > ANN > RSM and ANFIS-GA > ANN-GA > RSM, respectively.

Digital images of the soybean and three species of weeds with different backgrounds were acquired for image processing. An adaptive neuro-fuzzy inference system (ANFIS) from MATLAB® 6.1 was used to obtain a preliminary separation of plant and background. To train the fuzzy inference system (FIS), red-green-blue (RGB) values were first converted to HSV color space (hue, saturation, value), and samples from plant and background were visually selected from the images to be used as inputs. These were then mapped to a binary output that indicated the presence or absence of plant. Subtractive clustering was used to generate the FIS with a total of 100 epochs. Three clusters, and therefore three rules, were found by the ANFIS. This resulted in a total of 9 membership functions. Source code for a genetic algorithm was written using the toolbox of MATLAB® 6.1 to adjust the membership functions to reduce misclassification and improve segmentation. The membership function parameters were used to generate chromosome genes. The initial population of 50 chromosomes was generated using 30% noise perturbation of the membership functions originally given by ANFIS. A final segmentation of background and plant was achieved after 10 generations. Between evaluations crossover and mutations were applied. The results showed that the adaptive neuro-fuzzy inference system and genetic algorithm segmentation system was capable of eliminating areas that were misclassified as plant and also generally the final segmentation.

Brushless DC (BLDC) motors are the most popular motors used by the industry because they are easy to control. BLDC motors are generally controlled by artificial controls such as Fuzzy Logic Controller (FLC), Artificial Neural Network (ANN), and Adaptive Neuro-Fuzzy Inference System (ANFIS). However, the performance of the BLDC control system in previous studies was compared separately with their respective parameters, making it difficult to evaluate comprehensively. Therefore, in order to investigate the characteristic performance of Fuzzy, ANN, and ANFIS, this article provides a comparison of these artificial controls. Two scenarios of the dynamic tests are conducted to investigate control performance under constant torque-various speed and constant speed-various torque. By dynamic testing, characteristics of Fuzzy, ANN, and ANFIS can be observed as real applications. The testing parameters are: Settling Time, Overshoot and Overdamp (in the graph and average value), and then statistic performance are: Integral Square Error (ISE), Integral Absolute Error (IAE), Integral Time Absolute Error (ITAE), and Mean Absolute Error (MAE). The test result in scenario 1 showed that the ANN has a better performance compared to other controllers with the MAE, IAE, ITAE, and ISE value of 31.3003; 105.6280; 208.0630; and 5,7289 e4, respectively. However, in scenario 2, ANN only has a better performance compared to other controllers on just a few parameters. In scenario 2, ANN is indeed able to maintain speed but it has a more ripple value than ANFIS. Even so, the ripple that occurs in ANN does not have too much value compared to the setpoint. Therefore, the MAE value of the ANN is smaller than the ANFIS (18.8937 of ANN and 28.4685 of ANFIS).

In the present study, the predictive model is developed to observe the effect of radial rake angle on the end milling cutting tool by considering the following machining parameters: spindle speed, feed rate, axial depth of cut, and radial depth of cut. By referring to the real machining case study, the second-order mathematical models have been developed using response surface methodology (RSM). A number of machining experiments based on statistical five-level full factorial design of experiments are carried out in order to collect surface roughness values. The direct and interaction effects of the machining parameter with surface roughness are analyzed using Design Expert software. The optimal surface roughness value can be attained within the specified limits by using RSM. The genetic algorithm (GA) model is trained and tested in MATLAB to find the optimum cutting parameters leading to minimum surface roughness. The GA recommends 0.25 μm as the best minimum predicted surface roughness value. The confirmatory test shows the predicted values which were found to be in good agreement with observed values.

Prediction of surface roughness and tool wear in milling process on brass (C26130) alloy by Taguchi technique

Regional modeling of the ionosphere using adaptive neuro-fuzzy inference system in Iran

Due to the increasing need for intelligent systems, the adaptive neuro-fuzzy inference system (ANFIS) has recently attracted the attention of researchers in various scientific and engineering areas. The purpose of this work is to present the modeling of a photovoltaic power supply (PVPS) system using an ANFIS. For the modeling of the PVPS system, it is required to find suitable models for its different components (ANFIS PV-generator, ANFIS battery and ANFIS regulator) under variable climatic conditions. A database of measured weather data (global radiation, temperature and humidity) and electrical signals (photovoltaic, battery and regulator voltage and current) of a PVPS system installed in Tahifet (south of Algeria) has been recorded for the period from 1992 to 1997 using a data acquisition system. These data have been used for the modeling and simulation of the PVPS system. The ANFIS for the PV-generator, battery and regulator have been trained by using 10 signals recorded from the different components of the PVPS system. Each signal is represented by 365*5 values (complete 5-years). A set of data for 4-years have been used for the training of the ANFIS and data for 1-year has been used for the testing of the ANFIS. In this way, the ANFIS was trained to accept and handle a number of unusual cases. The comparison between actual and estimated values obtained from the ANFIS gave satisfactory results. The correlation coefficient between measured values and those estimated by the ANFIS gave good prediction accuracy of 98%. In addition, test results show that the ANFIS performed better than the artificial neural networks (ANN). Predicted electrical signals by the ANFIS can be used for several applications in PV systems.

Review of <i>Environmental and Hydrological Systems Modeling</i> by A. W. JayawardenaCRC Press Taylor &amp; Francis Group, Boca Raton, FL 33487; 2014; ISBN 978-0-415-46532-8; 516 pp.; $99.95.

This study aims to optimize the machining parameters in the manufacture of Yamaha motorcycle brake piston master cylinder and determine the effect on surface roughness. The method used is the Taguchi method. Machining parameters were varied based on the Taguchi method, each of which was experimented with using a finishing CNC lathe machine. From these experiments, the results obtained in the form of surface roughness values ​​which were then analyzed, in order to obtain the best parameters with the smallest surface roughness values ​​and the effect of each factor on surface roughness. This research produces the best parameters are spindle speed 1.755 RPM, feed rate 0.09 mm/rev, and depth of cut 0.30 mm. This parameter has a small surface roughness value. Based on surface roughness measurements, the factors that have the greatest influence on the level of surface roughness are feed rate of 67.9%, spindle speed of 15.4% and depth of cut of 3.3%. This proves that the smaller the value of feed rate, spindle speed and depth of cut, the smaller the value of surface roughness will be.