The Performance Prediction of Electrical Discharge Machining of AISI D6 Tool Steel Using ANN and ANFIS Techniques: A Comparative Study

Pourasl, Hamed H.; Javidani, Mousa; Khojastehnezhad, Vahid M.; Barenji, Reza Vatankhah

doi:10.3390/cryst12030343

Cited by 15 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 77 ] A number of researchers have adopted the neural network technique to achieve the estimated machining responses. [ 78–80 ] The neural network method is superior and accurate technique as compared to RSM. Thus, in the present investigation neural network‐based prediction model is developed for FDM process to obtain the responses namely tensile strength, build time, material consumption and surface roughness.…”

Section: Overview To Artificial Neural Network Approachmentioning

confidence: 99%

Development of artificial intelligence‐based neural network prediction model for responses of additive manufactured polylactic acid parts

et al. 2022

View full text Add to dashboard Cite

Fused deposition modeling (FDM) is one of the most economical and popular technology amongst numerous additive manufacturing techniques. The quality of FDM fabricated parts is highly sensitive to the production parameters. Thus, in the present work, an investigation on the FDM printed polylactic acid parts has been performed considering six printing process parameters, that is, nozzle diameter, build orientation, raster pattern, layer height and print speed to develop the feedforward backpropagation (FFBP) artificial neural network prediction model for the prediction of responses, namely, tensile strength, material consumption, build time and surface quality. Tensile specimens as per L 27 orthogonal array are printed considering the various combination of parameters. The printed samples have been subjected to tensile strength testing, surface roughness measurement, build time recording, and material consumption evaluation. The highest tensile strength of 57.633 MPa, lowest surface roughness of 1.71 μm, lowest build time of 0.35 h and lowest material consumption of 7.8 g are observed. The experimental results have been used to develop the artificial intelligence-based prediction model through FFBP algorithm and sigmoid transfer function to predict the responses. The best performance of the developed neural network with R 2 for testing (0.99343), training (0.99366), and validation (0.99372) of data is recorded for prediction of responses with minimum percentage error. The study concluded that developed model is capable of predicting the responses of FDM process according to the input process parameters.

show abstract

Section: Overview To Artificial Neural Network Approachmentioning

confidence: 99%

Development of artificial intelligence‐based neural network prediction model for responses of additive manufactured polylactic acid parts

et al. 2022

View full text Add to dashboard Cite

show abstract

“…However, one critical aspect that has been overlooked in most of the research conducted in this field is the thermal behavior of the process. A deeper understanding of the thermal behavior of EDM machining can lead to better optimization techniques and further advancements in the field [15].…”

Section: Introductionmentioning

confidence: 99%

Thermal modeling, simulation, and experimental validation of micro electric discharge machining of tungsten carbide (WC)

Ali,

Ali Khan,

Ali

2024

Eng. Res. Express

View full text Add to dashboard Cite

Tungsten carbide is a material that is widely used in tools and dies applications due to its high hardness, excellent toughness, and wear resistance. However, machining this material using conventional methods can be very challenging due to its exceptional properties. In such cases, electrical discharge machining can be used as an alternative method for machining this material. The aim of this study is to examine the thermal properties of EDM of tungsten carbide, both through finite element modeling and experimental conditions. The study aims to evaluate the temperature distribution in tungsten carbide during EDM die sinking. This is accomplished by drilling 0.5mm diameter and 1mm deep micro holes using micro-drilling processes. Seven experiments were performed using an EDM die-sinking machine, and a 3D axis symmetrical model was created and simulated using the COMSOL Multiphysics heat transfer module. The temperature profile of tungsten carbide material during a single spark machining was obtained by considering only 30% of energy in the form of Gaussian distribution that gets transferred to the workpiece. The temperature profile of this model was then used to estimate the material removal rate. By comparing the numerical and experimental results, it was found that there was only a 4.8% average percentage error, indicating very close agreement between the numerical and experimental results. The findings suggest that the finite element method of the COMSOL Multiphysics heat transfer module can accurately predict and simulate the real-time results of EDM machining. These results could be useful for EDM machine operators for pre-estimating MRR and maximum temperatures before proceeding with the actual machining.

show abstract

“…Gholizadeh et al 12 developed fuzzy possibility regression integrated and ANFIS models to explore the crucial factors of the EDM machine, such as volumetric flow rate, surface roughness, and electrode corrosion percentage. To improve the cutting performance of AISI D6 steel by obtaining the best surface roughness, material removal rate, and tool wear ratio, Pourasl et al 13 designed ANN and ANFIS techniques for estimating the ideal values of pulse on, pulse current, and voltage. Sharma et al 14 experimented with an electro-discharge machine on Inconel 625 super alloy and determined the optimal parameters for machining by employing ANFIS and the response surface method.…”

Section: Introductionmentioning

confidence: 99%

Modeling and optimization of WEDM of monel 400 alloy using ANFIS and snake optimizer: A comparative study

Jithendra,

Sharief Basha,

Das

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

The exploration of the prediction of wired electro-discharge machining parameters is becoming progressively more crucial in order to choose the ideal parameters for making products with impeccable designs. The objective of this work is to develop an augmented adaptive neuro-fuzzy inference system (ANFIS) model by encrypting the snake optimizer for estimating the surface roughness, material removal rate, and residual stress of Monel 400 alloy in wire electric discharge machining (WEDM). The performance of the indicated augmented model called ANFIS-SO was evaluated using 64 trials of WEDM experimental data. As a means of emphasizing the performance of the presented model, estimation results were compared to those from existing models, which included integration of ANFIS and beetle antennae search capabilities, reptile search algorithms, and COOT algorithms. The ANFIS-SO model showed excellent performance based on the statistical benchmarks tested for the developed models. The model achieved RMSE of 0.0793, 0.2781, and 16.3286 with performance errors of 0.3203, 1.9687, and 1112.529 along with an accuracy of 99%, 98%, and 95% for surface roughness, MRR, and residual stress, respectively, which are extremely more accurate than the ANFIS, ANFIS-BAS, ANFIS-RSA, and ANFIS-COOT. As a result of these findings, it is evident that the developed ANFIS-SO model might be used with reliability when designing future model forecasting approaches for optimizing machining parameters. Therefore, it is discovered that using ANFIS-SO is an innovative method for determining WEDM machining parameters which are very promising.

show abstract

The Performance Prediction of Electrical Discharge Machining of AISI D6 Tool Steel Using ANN and ANFIS Techniques: A Comparative Study

Cited by 15 publications

References 35 publications

Development of artificial intelligence‐based neural network prediction model for responses of additive manufactured polylactic acid parts

Development of artificial intelligence‐based neural network prediction model for responses of additive manufactured polylactic acid parts

Thermal modeling, simulation, and experimental validation of micro electric discharge machining of tungsten carbide (WC)

Modeling and optimization of WEDM of monel 400 alloy using ANFIS and snake optimizer: A comparative study

Contact Info

Product

Resources

About