ÇIÇEK, Adem ;KIVAK, Turgay ;SAMTAŞ, Gürcan ;ÇAY, Yusuf . Modeling of Thrust Forces in Drilling of AISI 316 Stainless Steel Using Artificial Neural Network and Multiple Regression Analysis. Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 58, n.7-8, p. 492-498, october 2018. ISSN 0039-2480. Available at: <https://www.sv-jme.eu/article/modeling-of-thrust-forces-in-drilling-of-aisi-316-stainless-steel-using-artificial-neural-network-and-multiple-regression-analysis/>. Date accessed: 04 oct. 2024. doi:http://dx.doi.org/10.5545/sv-jme.2011.297.
Çiçek, A., Kıvak, T., Samtaş, G., & Çay, Y. (2012). Modeling of Thrust Forces in Drilling of AISI 316 Stainless Steel Using Artificial Neural Network and Multiple Regression Analysis. Strojniški vestnik - Journal of Mechanical Engineering, 58(7-8), 492-498. doi:http://dx.doi.org/10.5545/sv-jme.2011.297
@article{sv-jmesv-jme.2011.297, author = {Adem Çiçek and Turgay Kıvak and Gürcan Samtaş and Yusuf Çay}, title = {Modeling of Thrust Forces in Drilling of AISI 316 Stainless Steel Using Artificial Neural Network and Multiple Regression Analysis}, journal = {Strojniški vestnik - Journal of Mechanical Engineering}, volume = {58}, number = {7-8}, year = {2012}, keywords = {Artificial neural networks, regression analysis, cryogenic treatment, machining, thrust force, predictive modeling}, abstract = {In this study, the effects of cutting parameters (cutting speed, feed rate) and deep cryogenic treatment on thrust force in drilling of AISI 316 stainless steel have been investigated. To observe the effects of deep cryogenic treatment, M35 HSS twist drills were cryogenically treated at -196 °C for 24h and tempered at 200 °C for 2h after conventional heat treatment. Experimental results showed that the lowest thrust forces were measured with cryogenically treated and tempered drills. In addition, artificial neural networks (ANNs) and multiple regression analysis were used to model the thrust force. Scaled conjugate gradient (SCG) learning algorithm with the logistic sigmoid transfer function was used to train and test the ANNs. ANNs results showed that the SCG model with five neurons in the hidden layer produced absolute fraction of variance (R2) of 0,999907 and 0.999871 for training data and test data respectively. Root mean square error (RMSE) was 0.00769 and 0.009066, and mean error percentage (MEP) was 0.725947 and 0.930127 for training and test data, respectively.}, issn = {0039-2480}, pages = {492-498}, doi = {10.5545/sv-jme.2011.297}, url = {https://www.sv-jme.eu/article/modeling-of-thrust-forces-in-drilling-of-aisi-316-stainless-steel-using-artificial-neural-network-and-multiple-regression-analysis/} }
Çiçek, A.,Kıvak, T.,Samtaş, G.,Çay, Y. 2012 October 58. Modeling of Thrust Forces in Drilling of AISI 316 Stainless Steel Using Artificial Neural Network and Multiple Regression Analysis. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 58:7-8
%A Çiçek, Adem %A Kıvak, Turgay %A Samtaş, Gürcan %A Çay, Yusuf %D 2012 %T Modeling of Thrust Forces in Drilling of AISI 316 Stainless Steel Using Artificial Neural Network and Multiple Regression Analysis %B 2012 %9 Artificial neural networks, regression analysis, cryogenic treatment, machining, thrust force, predictive modeling %! Modeling of Thrust Forces in Drilling of AISI 316 Stainless Steel Using Artificial Neural Network and Multiple Regression Analysis %K Artificial neural networks, regression analysis, cryogenic treatment, machining, thrust force, predictive modeling %X In this study, the effects of cutting parameters (cutting speed, feed rate) and deep cryogenic treatment on thrust force in drilling of AISI 316 stainless steel have been investigated. To observe the effects of deep cryogenic treatment, M35 HSS twist drills were cryogenically treated at -196 °C for 24h and tempered at 200 °C for 2h after conventional heat treatment. Experimental results showed that the lowest thrust forces were measured with cryogenically treated and tempered drills. In addition, artificial neural networks (ANNs) and multiple regression analysis were used to model the thrust force. Scaled conjugate gradient (SCG) learning algorithm with the logistic sigmoid transfer function was used to train and test the ANNs. ANNs results showed that the SCG model with five neurons in the hidden layer produced absolute fraction of variance (R2) of 0,999907 and 0.999871 for training data and test data respectively. Root mean square error (RMSE) was 0.00769 and 0.009066, and mean error percentage (MEP) was 0.725947 and 0.930127 for training and test data, respectively. %U https://www.sv-jme.eu/article/modeling-of-thrust-forces-in-drilling-of-aisi-316-stainless-steel-using-artificial-neural-network-and-multiple-regression-analysis/ %0 Journal Article %R 10.5545/sv-jme.2011.297 %& 492 %P 7 %J Strojniški vestnik - Journal of Mechanical Engineering %V 58 %N 7-8 %@ 0039-2480 %8 2018-10-11 %7 2018-10-11
Çiçek, Adem, Turgay Kıvak, Gürcan Samtaş, & Yusuf Çay. "Modeling of Thrust Forces in Drilling of AISI 316 Stainless Steel Using Artificial Neural Network and Multiple Regression Analysis." Strojniški vestnik - Journal of Mechanical Engineering [Online], 58.7-8 (2012): 492-498. Web. 04 Oct. 2024
TY - JOUR AU - Çiçek, Adem AU - Kıvak, Turgay AU - Samtaş, Gürcan AU - Çay, Yusuf PY - 2012 TI - Modeling of Thrust Forces in Drilling of AISI 316 Stainless Steel Using Artificial Neural Network and Multiple Regression Analysis JF - Strojniški vestnik - Journal of Mechanical Engineering DO - 10.5545/sv-jme.2011.297 KW - Artificial neural networks, regression analysis, cryogenic treatment, machining, thrust force, predictive modeling N2 - In this study, the effects of cutting parameters (cutting speed, feed rate) and deep cryogenic treatment on thrust force in drilling of AISI 316 stainless steel have been investigated. To observe the effects of deep cryogenic treatment, M35 HSS twist drills were cryogenically treated at -196 °C for 24h and tempered at 200 °C for 2h after conventional heat treatment. Experimental results showed that the lowest thrust forces were measured with cryogenically treated and tempered drills. In addition, artificial neural networks (ANNs) and multiple regression analysis were used to model the thrust force. Scaled conjugate gradient (SCG) learning algorithm with the logistic sigmoid transfer function was used to train and test the ANNs. ANNs results showed that the SCG model with five neurons in the hidden layer produced absolute fraction of variance (R2) of 0,999907 and 0.999871 for training data and test data respectively. Root mean square error (RMSE) was 0.00769 and 0.009066, and mean error percentage (MEP) was 0.725947 and 0.930127 for training and test data, respectively. UR - https://www.sv-jme.eu/article/modeling-of-thrust-forces-in-drilling-of-aisi-316-stainless-steel-using-artificial-neural-network-and-multiple-regression-analysis/
@article{{sv-jme}{sv-jme.2011.297}, author = {Çiçek, A., Kıvak, T., Samtaş, G., Çay, Y.}, title = {Modeling of Thrust Forces in Drilling of AISI 316 Stainless Steel Using Artificial Neural Network and Multiple Regression Analysis}, journal = {Strojniški vestnik - Journal of Mechanical Engineering}, volume = {58}, number = {7-8}, year = {2012}, doi = {10.5545/sv-jme.2011.297}, url = {https://www.sv-jme.eu/article/modeling-of-thrust-forces-in-drilling-of-aisi-316-stainless-steel-using-artificial-neural-network-and-multiple-regression-analysis/} }
TY - JOUR AU - Çiçek, Adem AU - Kıvak, Turgay AU - Samtaş, Gürcan AU - Çay, Yusuf PY - 2018/10/11 TI - Modeling of Thrust Forces in Drilling of AISI 316 Stainless Steel Using Artificial Neural Network and Multiple Regression Analysis JF - Strojniški vestnik - Journal of Mechanical Engineering; Vol 58, No 7-8 (2012): Strojniški vestnik - Journal of Mechanical Engineering DO - 10.5545/sv-jme.2011.297 KW - Artificial neural networks, regression analysis, cryogenic treatment, machining, thrust force, predictive modeling N2 - In this study, the effects of cutting parameters (cutting speed, feed rate) and deep cryogenic treatment on thrust force in drilling of AISI 316 stainless steel have been investigated. To observe the effects of deep cryogenic treatment, M35 HSS twist drills were cryogenically treated at -196 °C for 24h and tempered at 200 °C for 2h after conventional heat treatment. Experimental results showed that the lowest thrust forces were measured with cryogenically treated and tempered drills. In addition, artificial neural networks (ANNs) and multiple regression analysis were used to model the thrust force. Scaled conjugate gradient (SCG) learning algorithm with the logistic sigmoid transfer function was used to train and test the ANNs. ANNs results showed that the SCG model with five neurons in the hidden layer produced absolute fraction of variance (R2) of 0,999907 and 0.999871 for training data and test data respectively. Root mean square error (RMSE) was 0.00769 and 0.009066, and mean error percentage (MEP) was 0.725947 and 0.930127 for training and test data, respectively. UR - https://www.sv-jme.eu/article/modeling-of-thrust-forces-in-drilling-of-aisi-316-stainless-steel-using-artificial-neural-network-and-multiple-regression-analysis/
Çiçek, Adem, Kıvak, Turgay, Samtaş, Gürcan, AND Çay, Yusuf. "Modeling of Thrust Forces in Drilling of AISI 316 Stainless Steel Using Artificial Neural Network and Multiple Regression Analysis" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 58 Number 7-8 (11 October 2018)
Strojniški vestnik - Journal of Mechanical Engineering 58(2012)7-8, 492-498
© The Authors, CC-BY 4.0 Int. Change in copyright policy from 2022, Jan 1st.
In this study, the effects of cutting parameters (cutting speed, feed rate) and deep cryogenic treatment on thrust force in drilling of AISI 316 stainless steel have been investigated. To observe the effects of deep cryogenic treatment, M35 HSS twist drills were cryogenically treated at -196 °C for 24h and tempered at 200 °C for 2h after conventional heat treatment. Experimental results showed that the lowest thrust forces were measured with cryogenically treated and tempered drills. In addition, artificial neural networks (ANNs) and multiple regression analysis were used to model the thrust force. Scaled conjugate gradient (SCG) learning algorithm with the logistic sigmoid transfer function was used to train and test the ANNs. ANNs results showed that the SCG model with five neurons in the hidden layer produced absolute fraction of variance (R2) of 0,999907 and 0.999871 for training data and test data respectively. Root mean square error (RMSE) was 0.00769 and 0.009066, and mean error percentage (MEP) was 0.725947 and 0.930127 for training and test data, respectively.