Estimasi Bahan Bakar pada Kapal KRI Bima Suci menggunakkan Machine Learning

Firdaus, Mahendra Alfath (2022) Estimasi Bahan Bakar pada Kapal KRI Bima Suci menggunakkan Machine Learning. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 04211841000028-Undergraduate_Thesis.pdf] Text
04211841000028-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 April 2024.

Download (3MB) | Request a copy

Abstract

Adanya permasalahan dalam bahan bakar pada KRI Bima Suci, seperti kekurangan bahan bakar saat sedang berlayar disebabkan karena perhtiungan estimasi yang masi terbilang manual. Belum adanya penggunaan komputerisasi juga salah satu penyebab timbulnya permasalahan. Oleh karena itu, studi ini dilakukan untuk membuat penyelesaian dalam permasalahan tersebut, estimasi konsumsi bahan bakar akan dilakukan menggunakan machine learning. Machine learning ialah suatu bagian dari Artificial Intelligence dimana bisa melakukan suatu prediksi dengan metode regresi. Dengan menggunakkan 4 variabel diantaranya kecepatan kapal, kekuatan angin, kondisi laut, dan engine rpm diharapkan bisa mengestimasi konsumsi bahan bakar dengan baik. Penelitian dalam studi ini menghasilkan suatu klasifikasi dan estimasi yang tergolong baik. Untuk akurasi yang diperoleh dalam metode klasifikasi, K Nearest Neighbor merupakan yang tertinggi diantara metode klasifikasi yang lainnya, dengan tingkat akurasi terbesar mencapai 84.95%. untuk akurasi yang diperoleh dalam metode regresi, Polinomial Regresi merupakan yang terbaik diantara metode regresi yang lainnya, dengan tingkat akurasi sebesar 98.99% dan rata rata error hanya 13.66. Dalam memudahkan pihak KRI Bima Suci dalam menggunakkan metode machine learning, dibuatkan suatu prototipe website yang berfungsi untuk pengolahan data baru yang bisa dimasukkan sebagai data tambahan agar metode klasifikasi dan regresi bertambah baik
====================================================================================================
There were problems in fuel on the KRI Bima Suci, such as a lack of fuel when sailing due to the estimation calculations, which were still reasonably manual. The absence of computers is also one of the causes of problems. Therefore, this study was conducted to make a solution to this problem, the estimation of fuel consumption will be carried out using machine learning. Machine learning is a part of Artificial Intelligence that can make predictions using the regression method. By using four variables, including ship speed, wind strength, sea conditions, and engine rpm, it is expected to be able to estimate fuel consumption correctly. The research in this study resulted in classification and estimation that were classified as good. For the accuracy obtained in the classification method, K Nearest Neighbor is the highest among other classification methods, with the highest accuracy rate reaching 84.95%. For the accuracy obtained in the regression method, Regression Polynomial is the best among other regression methods, with an accuracy rate of 98.99% and an average error of only 13.66. To make it easier for KRI Bima Suci to use machine learning methods, a website prototype was created to process new data that can be entered as additional data so that the classification and regression methods are better

Item Type: Thesis (Other)
Uncontrolled Keywords: Konsumsi Bahan Bakar, Machine Learning, KRI Bima Suci Fuel Consumption, Machine learning, KRI Bima Suci
Subjects: Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Q Science > QA Mathematics > QA246.8 Gaussian
Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression
Q Science > QA Mathematics > QA336 Artificial Intelligence
Q Science > QA Mathematics > QA9.58 Algorithms
T Technology > T Technology (General) > T57.5 Data Processing
T Technology > T Technology (General) > T57.74 Linear programming
T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
T Technology > T Technology (General) > T58.62 Decision support systems
V Naval Science > VM Naval architecture. Shipbuilding. Marine engineering > VM751 Resistance and propulsion of ships
Divisions: Faculty of Marine Technology (MARTECH) > Marine Engineering > 36202-(S1) Undergraduate Thesis
Depositing User: Mahendra Alfath Firdaus
Date Deposited: 07 Feb 2022 08:33
Last Modified: 31 Oct 2022 03:11
URI: http://repository.its.ac.id/id/eprint/92962

Actions (login required)

View Item View Item