ANALISIS PREDIKSI TERHADAP KEKASARAN PERMUKAAN PADA PROSES PEMBUBUTAN MENGGUNAKAN METODE ANN (ARTIFICIAL NEURAL NETWORK)

RAMADHAN, I PUTU AHMAD WALMANDA R and Mohruni, Amrifan Saladin (2021) ANALISIS PREDIKSI TERHADAP KEKASARAN PERMUKAAN PADA PROSES PEMBUBUTAN MENGGUNAKAN METODE ANN (ARTIFICIAL NEURAL NETWORK). Undergraduate thesis, Sriwijaya Univesity.

	Text RAMA_21201_03051381621084.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
Preview	Text RAMA_21201_03051381621084_0011096407_01_front_ref .pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (484kB) | Preview
	Text RAMA_21201_03051381621084_0011096407_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (530kB) | Request a copy
	Text RAMA_21201_03051381621084_0011096407_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (334kB) | Request a copy
	Text RAMA_21201_03051381621084_0011096407_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (689kB) | Request a copy
	Text RAMA_21201_03051381621084_0011096407_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (184kB) | Request a copy
	Text RAMA_21201_03051381621084_0011096407_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (125kB) | Request a copy
	Text RAMA_21201_03051381621084_TURNITIN.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy

Abstract

In this study, the cutting parameters include cutting speed, eating movement and eating depth. Chisel used is made from carbide, carbide was chosen because it has high wear resistance. The workpiece used is Inconel 625 which has a carbon steel content of about 0.43 - 0.5. The variables used in this study are cut speed (Vc), feeding motion (fz) and cut depth (a). With parameters: cut speed 50, 125, 250 m/s, feeding motion 0.04, 0.08, 0.12 mm/rev and feeding depth 0.2, 0.3, 0.4 mm.The workpiece is processed using a turning machine, then the results of the turning process are tested with a surface roughness tester by taking the Value of Ra as its roughness value. Then the three Ra values are taken by average as Ra's experimental values. Prediction of surface roughness is done using artificial neural networks methods. the network structure used is; 3 inputs, n hidden layer and 1 output, network feed forward backpropagation algorithm, training and learning functions with Levenberg�Marquardt, performance using MSE and after delivery produces the lowest MSE on network structure 3-7-1 with a predicted error of 6.614% on training data and vaidation data.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Turning, Kekasran Permukaan, ANN
Subjects:	T Technology > TJ Mechanical engineering and machinery > TJ1125-1345 Machine shops and machine shop practice > TJ1205 General works Special tools Planing machines T Technology > TJ Mechanical engineering and machinery > TJ1125-1345 Machine shops and machine shop practice > TJ1210 Slotting and grooving machines Turning machines. Screw machines Cf. TT207 Metal turning
Divisions:	03-Faculty of Engineering > 21201-Mechanical Engineering (S1)
Depositing User:	Users 15529 not found.
Date Deposited:	05 Oct 2021 04:13
Last Modified:	05 Oct 2021 04:13
URI:	http://repository.unsri.ac.id/id/eprint/55489

Actions (login required)

View Item