Sains Malaysiana 42(12)(2013): 1735–1741

 

Prediction of Tool Life in End Milling of Ti-6Al-4V Alloy Using

Artificial Neural Network and Multiple Regression Models

(Ramalan Hayat Mata Alat dalam Kisar Hujung AloiTi-6Al-4V  Menggunakan Rangkaian Neural Tiruan dan Model Regresi Pelbagai)

 

 

SALAH AL-ZUBAIDI*, JAHARAH A. GHANI & CHE HASSAN CHE HARON

Department of Mechanical and Material Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia

 

Diserahkan: 22 Mac 2012/Diterima: 19 Mei 2012

 

ABSTRACT

Tool life of the cutting tools is considered as one of the factors which has effects on machining costs and the quality of machined parts. The topic of tool life prediction has been an interesting and important research topic attracting the attention of a wide number of researchers in this particular area. In terms of the suitable methods used in this research topic, it is stated that both statistical and artificial intelligence (AI) approaches can be employed to model tool life. For further justifying the capability of the ANN model in predicting tool life, the current study was based on conducting experimental work for collecting the experimental data. After carrying out the experiment, 17 data sets were collected and they were divided into two subsets; the first one for training and the second for testing. Since the data sets seemed to be lower than the number of data sets used in previous studies, we attempted to make verification of the ability of the ANN model in learning and adapting with low training and testing data. Diverse topologies accompanied with single and two hidden layers were created for modeling the tool life. For choosing the best and most effective network, the study adopted the mean square error function as criteria for the evaluation of the network selection. Thus, based on the data generated from the same experiment, a regression model (RM) was constructed employing the SPSS software. A comparison between the ANN model and RMs in terms of their accuracy was carried out and the findings revealed that the accuracy of the ANN was higher than that of the RM.

 

Keywords: Artificial neural network; prediction; tool life; uncoated carbide

 

ABSTRAK

Salah satu faktor yang memberi kesan terhadap kos pemesinan dan kualiti produk yang dimesin. Topik mengenai ramalan hayat mata alat sangat menarik dan merupakan kajian yang penting dan menarik perhatian sebahagian jumlah penyelidik dalam bidang ini. Kaedah yang sesuai digunakan dalam kajian ini ialah statistik dan pintar buatan bagi memodelkan hayat mata alat. Bagi justifikasi keupayaan model ANN dalam ramalan hayat mata alat, kajian ini berdasarkan kepada membuat kerja eksperimen untuk pengumpulan data. Selepas menjalankan eksperimen, 17 set data telah dikumpulkan dan dibahagikan kepada dua subset data; pertama untuk latihan dan kedua untuk ujian. Disebabkan set data agak rendah berbanding kajian sebelum ini, keupayaan model ANN dikaji dalam pembelajaran dan adaptasi dengan data latihan dan ujian yang rendah. Topologi yang besar beserta satu dan dua lapis tersorok telah direka bagi memodelkan hayat mata alat. Bagi memilih rangkaian terbaik dan paling berkesan, kajian ini menggunakan fungsi min ralat kuasa dua sebagai kriteria untuk penilaian rangkaian yang dipilih. Oleh itu, berdasarkan data yang dijana daripada eksperimen, model regresi (RM) telah dibangunkan menggunakan perisian SPSS. Perbandingan kejituan antara model ANN dan RMS telah dibuat, dan hasil kajian menunjukkan kejituan model ANN lebih tinggi berbanding dengan RM.

 

Kata kunci: Hayat mata alat; karbida tak bersalut; ramalan; rangkaian neural tiruan

RUJUKAN

 

Al-Zubaidi, S., A. Ghani, J. & Che Haron, C.H. 2011. Application of ANN in milling process: A review. Modelling and Simulation in Engineering 2011: 1-7.

Beale, M.H., Hagan, M.T. & Demuth, H.B. 2010. Neural Network Toolboxtm 7 User’s Guide. Math Work Inc.

Bruni, C., d’Apolito, L., Forcellese, A., Gabrielli, F. & Simoncini, M. 2008. Surface roughness modelling in finish face milling under MQL and dry cutting conditions. International Journal of Material Forming 1: 503-506.

Chen, J.C. & Chen, J.C. 2004. An artificial-neural-networks-based in-process tool wear prediction system in milling operations. The International Journal of Advanced Manufacturing Technology 25(5-6): 427-434.

Dutta, R.K., Paul, S. & Chattopadhyay, A.B. 2000. Applicability of the modified back-propagation algorithm in tool condition monitoring for faster convergence. Journal of Materials Processing Technology 98(3): 299-309.

Elmagrabi, N.H.E. 2009. End milling of titanium alloy Ti-6Al-4V with carbide tools using response surface methodology.Tesis PhD. Universiti Kebangsaan Malaysia, Bangi (unpublished).

Graupe, D. 2007. Principles of Artificial Neural Networks. Chicago: World Scientific Publishing Co. Pte. Ltd.

Hagan, M.T., B. Demuth, H. & Beale, M. 1996. Neural Network Design. Boston: PWS Publishing Company.

Magrab, E.B., Azarm, S., Balachandran, B., Duncan, J., Herold, K. & Walsh, G. 2000. An Engineers Guide to Matlab. New Jersey: Prentic Hall.

Palanisamy, P., Rajendran, I. & Shanmugasundaram, S. 2007. Prediction of tool wear using regression and ANN models in end-milling operation. The International Journal of Advanced Manufacturing Technology 37: 29-41.

Zain, A.M., Haron, H. & Sharif, S. 2010. Prediction of surface roughness in the end milling machining using artificial neural network. Expert Systems with Applications 37(2): 1755-1768.

 

*Pengarang untuk surat-menyurat; email: salah@eng.ukm.my

 

 

 

sebelumnya