Sistem Prediksi Penjadwalan Perbaikan Ball Mill Pada Lini Produksi Pasta Timah Menggunakan Metode Fuzzy Time Series

Putra, Mohammad Osama (2023) Sistem Prediksi Penjadwalan Perbaikan Ball Mill Pada Lini Produksi Pasta Timah Menggunakan Metode Fuzzy Time Series. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 10311910000034-_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (2MB) | Request a copy

Abstract

Baterai Timbal Asam (Suyanto et al., 2021) terdiri dari dua komponen utama, yakni bahan aktif, Lead Paste, dan bahan pasif, Grid. Produksi Lead Paste melibatkan beberapa proses berkesinambungan, dimulai dari mesin pembuat Lead Lump, Ball Mill, dan Pencampuran Pasta. Lead Powder dihasilkan melalui proses pengolahan Lead Lump dalam Ball Mill, yang menghasilkan material yang lebih halus melalui tumbukan akibat aliran udara panas dan rotasi Ball Mill. Data penggunaan Lead Lump penting untuk menganalisis performa dan mengidentifikasi masalah pada Ball Mill ketika terjadi penurunan performa akibat kelainan pada mesin. Namun, saat ini, data tren performa didapatkan dengan menghitung stok awal lead ingot dengan lead oxide yang tersimpan di silo. Metode tersebut kurang akurat dan menyebabkan kekurangan data antara proses pembuatan Lead Lump hingga pasting.
Proyek akhir "Sistem Prediksi Penjadwalan Perbaikan Ball Mill Pada Lini Produksi Pasta Timah Menggunakan Metode Fuzzy Time Series" diusulkan untuk menyediakan data pendukung melakukan penjadwalan maintenance yang diperlukan oleh tim maintenance dan engineering di PT GS Battery Karawang. Penggunaan fuzzy time series dipilih karena data yang diakuisisi adalah data runtun waktu, dan metode ini memungkinkan penggunaan data yang diakuisisi secara real-time. Tujuan proyek ini adalah mendapatkan prediksi dengan seakurat mungkin dengan membandingkan beberapa metode fuzzy time series dan metode prediksi lainnya menggunakan evaluasi RMSE dan MAPE, dengan penekanan pada penggunaan metode fuzzy time series model Singh yang telah terbukti memiliki keakuratan prediksi tertinggi dari penelitian sebelumnya.
Hasilnya menunjukkan bahwa metode Fuzzy Time Series Model Singh memberikan prediksi paling akurat dibandingkan dengan metode lainnya, dengan nilai RMSE dan MAE masing-masing 6% dan 5%. Oleh karena itu, metode ini dianggap layak sebagai decision support system untuk melakukan penjadwalan maintenance dan improvement pada performa ball mill.
======================================================================================================================================
Lead Acid Battery (Suyanto et al., 2021) consists of two main components: the active material, Lead Paste, and the passive material, Grid. The production of Lead Paste involves several continuous processes, starting from the Lead Lump-making machine, Ball Mill, and Paste Mixing. Lead Powder is produced through the processing of Lead Lump in the Ball Mill, resulting in finer material due to collisions caused by hot airflow and Ball Mill rotation. Data on Lead Lump usage is crucial for analyzing performance and identifying issues with the Ball Mill when there is a decrease in performance due to abnormalities in the machine. However, currently, performance trend data is obtained by calculating the initial stock of lead ingots with lead oxide stored in a silo. This method is less accurate and leads to data gaps between the Lead Lump-making and pasting processes.
The final project "Predictive Scheduling System for Ball Mill Maintenance in Tin Paste Production Line Using Fuzzy Time Series Method" is proposed to provide supporting data for the necessary maintenance scheduling by the maintenance and engineering team at PT GS Battery Karawang. Fuzzy time series method is chosen as the acquired data is time series data, and this method allows the use of real-time data. The goal of this project is to achieve the most accurate prediction by comparing several fuzzy time series methods and other prediction methods using RMSE and MAPE evaluation, with an emphasis on using the fuzzy time series method known as the Singh model, which has shown the highest prediction accuracy in previous research.
The results show that the Fuzzy Time Series Model Singh provides the most accurate predictions compared to other methods, with RMSE and MAE values of 6% and 5% respectively. Therefore, this method is considered suitable as a decision support system for maintenance scheduling and performance improvement on ball mill.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Ballmill,Performa,Prediksi,Fuzzy time series
Subjects:	Q Science > QA Mathematics > QA9.64 Fuzzy logic
Divisions:	Faculty of Vocational > 36304-Automation Electronic Engineering
Depositing User:	Mohammad Osama Putra
Date Deposited:	08 Aug 2023 01:26
Last Modified:	02 Oct 2023 01:07
URI:	http://repository.its.ac.id/id/eprint/103795

Actions (login required)

View Item