Modeling of cutting performances in turning process using artificial neural networks

Dahbi, Samya; Ezzine, Latifa; Moussami, Haj El

doi:10.1177/1847979017718988

Cited by 23 publications

(15 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the literature is examined, there are examples where cutting forces and cutting parameters are modelled with an artificial neural network [21][22][23][24]. However, none of these examples mention the development of the graphical user interface included in this study.…”

Section: Artificial Neural Network Modelling and Developing An Interactive Interfacementioning

confidence: 99%

Modelling of cutting parameters for Nilo 36 superalloy with machine learning methods and developing an interactive interface

Basmacı

Kırbaş

2021

International Advanced Researches and Engineering Journal

View full text Add to dashboard Cite

Superalloys have become increasingly used in the machining sector due to their high strength, temperature and machinability. One of these alloys, Nilo (Invar) 36, has a low thermal expansion and its use is rapidly increasing in areas where high temperature and expansion are not required, especially in composite mould applications, such as aerospace, electronics, measuring instruments and aerospace. In this study, a mathematical model based on artificial intelligence and an interactive visual interface in MATLAB software were developed according to the test results obtained from surface roughness Ra, cutting methods, rotational speeds, cooling method and cutting speed of Nilo 36 alloy. For the mathematical analysis of the measurements, the number of experiments to be performed by using Minitab program and Taguchi method was reduced to 32. The measurement results were modelled by Response Surface Design method and the factors affecting the surface roughness were determined in order of importance. A high-performance feedforward artificial neural network has been developed using experimental data and an interactive interface has been prepared based on the developed model. Thus, the user can easily observe the cutting forces and surface roughness values for different cutting parameters with high accuracy.

show abstract

Section: Artificial Neural Network Modelling and Developing An Interactive Interfacementioning

confidence: 99%

Modelling of cutting parameters for Nilo 36 superalloy with machine learning methods and developing an interactive interface

Basmacı

Kırbaş

2021

International Advanced Researches and Engineering Journal

View full text Add to dashboard Cite

show abstract

“…The paper uses three performance measures: correlation coefficient (R 2 > 99%), mean squared error (MSE < 0.3%), and average percentage error (APE < 6%). 13…”

Section: Literature Surveymentioning

confidence: 99%

Optimization of input machining parameters in SBCNC-60 for turning and drilling on P8 (H-13,HSS) material

Saxena

Dubey²,

Kumar³

et al. 2021

International Journal of Electrical Engineering & Education

View full text Add to dashboard Cite

Today’s technology of automobile manufacturing industries depends mainly on a metal cutting operation like turning and drilling. This paper aims to improve turning and drilling operations in industries where necessity is to increase productivity by improving the metal removal rate. This paper-work uses the Taguchi method to analyze the input control parameter and optimize the significant ones to obtain the desired output. Taguchi method is a broadly used technique for experimental design and analysis of experimental data to improve the performance of machining operations like face turning, drilling, etc. in a CNC machine by taking input control factor cutting speed (CS), feed rate (FR), depth of cut (DOC) and then find out the significant ones to optimize machining operation. In this paper, CNMG190616-M5-TM2501 and SD205A-1050–056-12R1-P cutting tool are used for turning and drilling operation respectively for H-13 (P8) material, and then by applying Taguchi L9 array and further analysis using ANOVA and validation test through regression model is done on input control parameters to obtain better optimum performance of SBCNC 60 lathe machine.

show abstract

“…The training data set of desired outputs generated utilizing experimental data set, as reflected in Table 3. In order to get a closed-form solution, MATLAB function feed-forward back-propagation neural network (TRAINGD) was used for training the data of the network, which has been widely used for prediction and optimization of various machining processes (Dhar et al 2008;Dhupal et al 2009;Somashekhar et al 2010;Kuo et al 2012;Dahbi et al 2017;Behera et al 2016). TRAINGD is a network training function which works in accordance with the gradient descent method that measures the output error, calculates the gradient of the error by adjusting as well as updating the weight variable repetitively in the direction of the negative gradient of the performance function and also reduces the mean square error (MSE) between expected data and training data set.…”

Section: Model Prediction Using Artificial Neural Networkmentioning

confidence: 99%

Parametric optimization of Nd:YAG laser microgrooving on aluminum oxide using integrated RSM-ANN-GA approach

2018

View full text Add to dashboard Cite

Nowadays in highly competitive precision industries, the micromachining of advanced engineering materials is extremely demand as it has extensive application in the fields of automobile, electronic, biomedical and aerospace engineering. The present work addresses the modeling and optimization study on dimensional deviations of square-shaped microgroove in laser micromachining of aluminum oxide (Al 2 O 3) ceramic material with pulsed Nd:YAG laser by considering the air pressure, lamp current, pulse frequency, pulse width and cutting speed as process parameters. Thirty-two sets of laser microgrooving trials based on central composite design (CCD) design of experiments (DOEs) are performed, and response surface method (RSM), artificial neural network (ANN) and genetic algorithm (GA) are subsequently applied for mathematical modeling and multi-response optimization. The performance of the predictive ANN model based on 5-8-8-3 architecture gave the minimum error (MSE = 0.000099) and presented highly promising to confidence with percentage error less than 3% in comparison with experimental result data set. The ANN model combined with GA leads to minimum deviation of upper width, lower width and depth value of − 0.0278 mm, 0.0102 mm and − 0.0308 mm, respectively, corresponding to optimum laser microgrooving process parameters such as 1.2 kgf/cm 2 of air pressure, 19.5 Amp of lamp current, 4 kHz of pulse frequency, 6% of pulse width and 24 mm/s of cutting speed. Finally, the results have been verified by performing a confirmatory test.

show abstract

Modeling of cutting performances in turning process using artificial neural networks

Cited by 23 publications

References 43 publications

Modelling of cutting parameters for Nilo 36 superalloy with machine learning methods and developing an interactive interface

Modelling of cutting parameters for Nilo 36 superalloy with machine learning methods and developing an interactive interface

Optimization of input machining parameters in SBCNC-60 for turning and drilling on P8 (H-13,HSS) material

Parametric optimization of Nd:YAG laser microgrooving on aluminum oxide using integrated RSM-ANN-GA approach

Contact Info

Product

Resources

About