Open AccessANALISA AKAR MASALAH RADIAL RUN OUT BAN MENGGUNAKAN DECISION TREE
Author(s) -
Bambang Biantoro,
Hernadewita Hernadewita
Publication year - 2021
Publication title -
jurnal muara sains, teknologi, kedokteran, dan ilmu kesehatan
Language(s) - English
Resource type - Journals
eISSN - 2579-6410
pISSN - 2579-6402
DOI - 10.24912/jmstkik.v5i2.9417
Subject(s) - tread , decision tree , radial tire , tree (set theory) , computer science , process (computing) , root cause , quality (philosophy) , industrial engineering , engineering , artificial intelligence , mathematics , operations management , materials science , mathematical analysis , natural rubber , composite material , operating system , philosophy , epistemology
Problem solving in the multistage production process is a challenge for the industry. The use of modern techniques such as machine learning in solving quality problems continues to be developed. One of the machine learning is decision tree. The tire industry entered the era of industrial revolution 4.0 with the use of information technology. Utilizing data using machine learning in finding the root cause of the problem can support the tire industry in industrial competition. This study aims to explore the process data in the tire industry to solve one of the tire quality problems, namely radial run-out tires. The technique of finding the root of the problem in this research is done using Classification and Regression Tree (CART) technique. Input variables involve 60 factors in the production process. From the research, it was found that the factors that influence the radial run out value are the lot of the Tread, Bead and Sidewall components. The factors causing the high radial run-out of the tires are the variations in the lot of the tire components Tread and Bead. The decision tree model that was formed has a precision level of 74.7% in detecting high radial run-out events. The effects of improvement on the lot tread and bead components resulting from the decision tree can reduce the defect of radial run out rate by 99.9%. Keywords: Decision tree; Root cause analysis; Radial run-out Tire; Data mining AbstrakPemecahan masalah pada proses produksi multistage merupakan tantangan untuk indusri. Pemanfaatan teknik modern seperti machine learning dalam pemecahan masalah kualitas terus dikembangkan. Salah satu machine learning adalah decision tree. Industri ban memasuki era industri revolusi 4.0 dengan adanya pemakaian teknologi informasi seperti barcode atau radio frequency identification. Pemanfaataan data dengan menggunakan machine learning dalam pencarian akar masalah bisa mendukung industri ban dalam kompetisi industri. Penelitian ini bertujuan untuk mengekplorasi data proses pada industri ban untuk memecahkan permasalahan kualitas ban yaitu radial run-out ban. Teknik pencarian akar masalah dilakukan menggunakan Clasification and Regression Tree (CART). Variabel input melibatkan 60 faktor dalam proses produksi. Dari penelitian didapatkan faktor yang mempengaruhi nilai radial run out adalah lot komponen Tread, Bead dan Sidewall. Untuk faktor penyebab tingginya radial run-out ban adalah variasi lot komponen Tread dan Bead. Model decision tree yang terbentuk memiliki tingkat presisi 74,7% dalam mendeteksi kejadian radial run-out berkategori tinggi. Efek perbaikan pada komponen lot Tread dan Bead yang dihasilkan dari decision tree dapat menurunkan tingkat defect radial run- out ban sebesar 99,9%.