SISTEM KONTROL JARINGAN SYARAF TIRUAN BERBASIS SIMULASI PADA PENGELASAN PIPA ALUMINUM
DOI:
https://doi.org/10.21609/jiki.v4i1.155Keywords:
deteksi kolam las, jaringan syaraf tiruan, pengelasan tungsten inert gas (TIG), sensor vision, simulasi pengelasan, molten pool detection, neural network, tungsten inert gas (TIG) welding, welding simulationAbstract
Dalam penelitian ini telah dikembangkan sistem pengelasan otomatis Tungsten Inert Gas (TIG) dengan menggunakan sensor vision pada pengelasan pipa aluminum. Penelitian ini mempelajari proses pengelasan cerdas pipa paduan aluminum 6063S-T5 dalam posisi tetap dengan obor las (welding torch) bergerak dan menggunakan mesin las AC. Model Jaringan Syaraf Tiruan (neural network) untuk pengendalian kecepatan pengelasan telah dikembangkan agar dapat bekerja secara otomatis. Untuk melatih Jaringan Syaraf Tiruan ini diperlukan cukup banyak data dari penelitian sehingga memerlukan waktu dan dana yang cukup besar. Penelitian ini menawarkan proses baru untuk memperkirakan dan mengendalikan penetrasi pengelasan dalam pengelasan pipa paduan aluminum. Penetrasi las diperkirakan dengan menggunakan metode perkiraan secara hibrida yaitu dengan mengombinasikan simulasi pengelasan dan pengamatan visual menggunakan sensor vision. Dari hasil eksperimen didapatkan bahwa sistem pengendalian cukup efektif untuk mendeteksi kolam las (molten pool) dan menghasilkan pengelasan yang baik. This research has developed an automatic welding system Tungsten Inert Gas (TIG) using sensor vision on aluminum pipe welding. This research studied the process of intelligent welding of alloy pipe aluminum 6063S-T5 in a fixed position with a welding torch to move and use the AC welding machines. The neural network model to control the speed of the welding has been developed in order to work automatically. The neural network train need quite a lot of data from studies that require time and substansial funds. This research offers a new process for estimating and controlling welding penetration in welding of aluminum alloy pipe. Weld penetration was estimated by using the approximate hybrid method that combines the simulations of welding and visual inspection using sensor vision. The experiment results that the control system is effective enough to detect the molten pool and produce a good weld.Downloads
Published
2012-05-29
How to Cite
Baskoro, A. S., Kabutomori, M., & Suga, Y. (2012). SISTEM KONTROL JARINGAN SYARAF TIRUAN BERBASIS SIMULASI PADA PENGELASAN PIPA ALUMINUM. Jurnal Ilmu Komputer Dan Informasi, 4(1), 30–35. https://doi.org/10.21609/jiki.v4i1.155
Issue
Section
Articles
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).