Optimasi Multi Respons Proses Drilling Aramid Fiber Reinforced Polymer (AFRP) Dengan Metode Backpropagation Neural Network-Genetic Algorithm

Izzulhaq, Muhammad Fiky (2024) Optimasi Multi Respons Proses Drilling Aramid Fiber Reinforced Polymer (AFRP) Dengan Metode Backpropagation Neural Network-Genetic Algorithm. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6007221018-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2026. Download (4MB) | Request a copy

Abstract

Aramid fiber reinforcement polymer (AFRP) adalah salah satu bahan yang digunakan dalam komponen struktur pesawat terbang. Dalam perakitannya, proses drilling adalah proses pemesinan yang paling umum dilakukan. Proses drilling harus menghasilkan kualitas lubang yang memenuhi spesifikasi. Kualitas lubang yang diamati sebagai respons pada penelitian ini adalah delaminasi masuk dan keluar. Selain kualitas lubang, respons lain yang juga diamati adalah gaya tekan dan torsi. Untuk mendapatkan nilai respon yang optimal secara bersamaan, parameter proses antara lain jenis pahat drill, kecepatan spindel, dan kecepatan makan digunakan untuk memprediksi keempat respons. Dalam memprediksi eksperimen menggunakan desain eksperimen full faktorial dengan replikasi sebanyak 2 kali. Hubungan parameter proses dan respons diprediksi menggunakan metode backpropagation neural network (BPNN) berdasarkan hasil eksperimen. Kemudian, optimasi dilakukan menggunakan metode genetic algorithm (GA). Hasil optimasi dengan GA selanjutnya, dikonfirmasi dengan eksperimen konfirmasi. Berdasarkan eksperimen konfirmasi, nilai optimal respons gaya tekan 29,03 N, torsi 90,33 Nmm, delaminasi masuk 1,157, dan delaminasi keluar 1,081 yang dicapai pada kombinasi parameter proses jenis pahat twist drill, kecepatan spindel 1455 rpm, dan kecepatan makan 10 mm/menit.
=================================================================================================================================
Aramid fiber reinforcement polymer (AFRP) is one of the materials used in aircraft structural components. In its assembly, drilling is the most common machining process. The drilling process must produce hole quality that meets specifications. The hole quality observed as a response in this study is peel-up and push-out delamination. Other responses that are also observed are thrust force and torque. To obtain the optimal response values simultaneously, process parameters including drill tool type, spindle speed, and feeding speed are used to predict the four responses. In predicting the experiment, a full factorial experimental design with 2 replications was used. The relationship between process parameters and responses was predicted using the backpropagation neural network (BPNN) method based on the experimental results. Then, optimization is carried out using the genetic algorithm (GA) method. The results of optimization with GA were then confirmed by experiment confirmations. Based on the experiment confirmation, the optimal response values of thurst force 29.03 N, torque 90.33 Nmm, peel-up delamination 1.157, and push-out delamination 1.081 were achieved at the combination of process parameters of twist drill tool type, spindle speed 1455 rpm, and feed rate 10 mm/min.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	AFRP, drilling process, multi response optimization, BPNN-GA, Optimasi Multi-respon, Proses drilling, Backpropagation Neural Network, Genetic Algorithm.
Subjects:	T Technology > T Technology (General) > T57.5 Data Processing T Technology > TJ Mechanical engineering and machinery > TJ1225 Milling machines numerically controlled T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL240.5 Composite materials
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Mechanical Engineering > 21101-(S2) Master Thesis
Depositing User:	Muhammad Fiky Izzulhaq
Date Deposited:	09 Feb 2024 17:00
Last Modified:	09 Feb 2024 17:00
URI:	http://repository.its.ac.id/id/eprint/106601

Actions (login required)

View Item