Penerapan analisis cluster untuk segmentasi masalah produksi ban berdasarkan hasil pengukuran dynamic balance dan uniformity dengan machine learning = Application of clustering analysis for segmentation production tire problems base on result of measurement dynamic balance and uniformity with machine learning

Rahmadana, Ilqham (2021) Penerapan analisis cluster untuk segmentasi masalah produksi ban berdasarkan hasil pengukuran dynamic balance dan uniformity dengan machine learning = Application of clustering analysis for segmentation production tire problems base on result of measurement dynamic balance and uniformity with machine learning. Bachelor thesis, Universitas Pelita Harapan.

	Text (Title) Title.pdf.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (2MB)
Preview	Text (Abstract) Abstract.pdf.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (138kB) | Preview
Preview	Text (ToC) ToC.pdf.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (344kB) | Preview
Preview	Text (Chapter1) Chapter1.pdf.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (111kB) | Preview
	Text (Chapter2) Chapter2.pdf.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (235kB)
	Text (Chapter3) Chapter3.pdf.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (399kB)
	Text (Chapter4) Chapter4.pdf.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (261kB)
	Text (Chapter5) Chapter5.pdf.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (322kB)
	Text (Chapter6) Chapter6.pdf.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (74kB)
Preview	Text (Bibliography) Bibliography.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (193kB) | Preview
	Text (Appendices) Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)

Abstract

Aktivitas produksi sebuah produsen ban berkembang pesat beriringan dengan perkembangan teknologi pada era globalisasai saat ini. Hal ini menyebabkan eksistensi sebuah perusahaan dipertaruhkan agar tetap meningkatkan kualitas ban yang diproduksi. Hal tersebut menjadi salah satu alasan mengapa machine learning dibutuhkan pada pemrosesan data dalam skala besar dan dengan waktu yang cepat akurat untuk terus meningkatkan eksistensi perusahaan di skala nasional maupun internasional. Analisis clustering merupakan salah satu metode machine learning yang digunakan dalam penelitian ini. Tujuan dari penelitian ini adalah mencari tahu apakah metode clustering ini dapat dijadikan sebuah alat praktis bagi perusahaan manufaktur sektor ban untuk mempermudah menentukan tindakan perbaikan yang dilakukan secara akurat tepat sasaran, cepat, dan efektif berdasarkan aktual permasalahan yang terjadi. Hal ini bertujuan pula untuk mengurangi Scrap atau Reject Rate sebuah produsen pembuatan ban di tengah-tengah persaingan industri 4.0 yang sangat kompetitif. Hasil penelitian ini menunjukkan hasil visualiasai segmentasi permasalahan yang terjadi berdasarkan hasil mesin pengetesan nilai Dynamic Balance dan Uniformity yang berada dalam 3 besar penyumbang Scrap atau Reject Rate tahun 2020 dan menjadi perhatian pasar guna memberikan jaminan ban yang nyaman dan aman digunakan saat berkendara. Dari hasil klasterisasi empat variabel dataset didapatkan tiga buah cluster ban, cluster 2 menjadi cluster yang mendapatkan prioritas lebih karena memiliki nilai karakteristik centroid paling tinggi pada tiga dari empat variabel dataset yang digunakan. Yaitu pada variabel RFV (4,126), Conicity (1,970), dan Bumpy (1,028) merupakan yang tertinggi dari semua cluster / The production activities of a tire manufacturer develop’s rapidly in line with technological developments in the current globalization era. This causes the existence of a company to be at stake in order to keep improving the quality of the tires it produces. This is one of the reasons why machine learning is needed for data processing on a large scale and at a fast and accurate time to continue to improve the existence of companies on a national and international scale. Clustering analysis is one of the machine learning methods used in this study. The purpose of this study is to find out whether this clustering method can be used as a practical tool for tire manufacturing companies to make it easier to determine corrective actions that are carried out accurately, quickly, and effectively based on the actual problems that occur. It also aims to reduce the Scrap or Reject Rate of a tire manufacturer in the midst of very competitive industry 4.0. The results of this study show segmentation problems that occur based on the results of the Dynamic Balance and Uniformity value testing machines which are in the top 3 contributors to the 2020 Scrap or Reject Rate and become the market's attention to guarantee tires that are comfortable and safe to use when driving. Results of the clustering from four variable dataset, it was obtained three tire clusters, cluster 2 became the cluster that got more priority because it had the highest centroid characteristic value in three of the four dataset variables used. Namely, the variable RFV (4.126), Conicity (1.970), and Bumpy (1.028) is the highest of all clusters

Actions (login required)

View Item