Raina, Faricha Ardelia (2025) Penentuan Titik Lokasi Produksi Alat Panen Agroindustri dengan Spatial Regression dan Hybrid Metaheuristic Algorithm: Studi Kasus Egrek Digital Merah Putih. Masters thesis, Institut Teknologi Sepuluh Nopember.
![]() |
Text
6010231046-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (4MB) | Request a copy |
Abstract
Factory location problem sering menjadi permasalahan yang dialami oleh industri-industri dengan produk inovatif. Saat ini, bidang agroindustri mulai banyak melakukan pengembangan produk secara modern. Salah satu produk inovatif yang saat ini sedang dikembangkan adalah Egrek Digital Merah Putih, alat panen kelapa sawit yang berstandar SNI dan dapat mendeteksi kematangan buah. Alat tersebut berpotensi untuk diproduksi massal pada tahun 2025. Sehingga, diperlukan analisis untuk menentukan lokasi produksi Egrek Digital secara optimal. Metode yang akan digunakan dalam penelitian ini adalah spatial regression dan hybrid metaheuristic algorithm. Hasil dari pengujian spatial regression diketahui bahwa Geographically Weighted Regression (GWR) merupakan model yang cocok untuk mengestimasi kebutuhan egrek di wilayah Jawa, Kalimantan, dan Sumatra. Perhitungan demand tersebut menjadi masukan dalam penentuan lokasi fasilitas produksi dengan Hybrid Particle Swarm Optimization-Tabu Search (PSO-TS). Penggabungan kedua metode ini diharapkan dapat mengeksplorasi global optimum dan mencegah terjebak dalam local optimum. Berdasarkan hasil komputasi, didapatkan lokasi terpilih pembangunan fasilitas berada di Kabupaten Bengkayang dengan total cost sebesesar Rp Rp60.270.500.288,96. Pengujian dengan Hybrid PSO-TS ini menghasilkan solusi yang paling baik jika dibandingkan dengan algoritma PSO murni, Tabu Search murni, dan Ant Colonty Optimization.
====================================================================================================================================
factory location problem often becomes an issue faced by industries with innovative products. Currently, the agro-industrial sector is increasingly developing products in a modern way. One of the innovative products currently being developed is the Egrek Digital Merah Putih, a standard SNI palm oil harvesting tool that can detect fruit ripeness. This tool has the potential to be mass-produced in 2025. Therefore, an analysis is needed to determine the optimal production location for the Egrek Digital. The methods to be used in this study are spatial regression and hybrid metaheuristic algorithm. The results of the spatial regression testing indicate that Geographically Weighted Regression (GWR) is a suitable model for estimating the demand for egrek in the regions of Java, Kalimantan, and Sumatra. The demand calculations will be used as input for determining the location of the production facility using Hybrid Particle Swarm Optimization-Tabu Search (PSO-TS). The combination of these two methods is expected to explore the global optimum and prevent getting trapped in a local optimum. Based on the computation results, the selected location for the facility development is in Bengkayang Regency with a total cost of Rp 60,270,500,288.96. Testing with this Hybrid PSO-TS produces the best solution compared to pure PSO, pure Tabu Search, and Ant Colony Optimization algorithms.
Item Type: | Thesis (Masters) |
---|---|
Uncontrolled Keywords: | Egrek Digital Merah Putih, Hybrid Metaheuristic Algorithm, Particle Swarm Optimization, Spatial Regression, Tabu Search, Egrek Digital Merah Putih, Hybrid Metaheuristic Algorithm, Particle Swarm Optimization, Spatial Regression, Tabu Search |
Subjects: | Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression Q Science > QA Mathematics > QA9.58 Algorithms |
Divisions: | Faculty of Industrial Technology and Systems Engineering (INDSYS) > Industrial Engineering > 26101-(S2) Master Thesis |
Depositing User: | Faricha Ardelia Raina |
Date Deposited: | 23 Jul 2025 02:36 |
Last Modified: | 23 Jul 2025 02:36 |
URI: | http://repository.its.ac.id/id/eprint/120684 |
Actions (login required)
![]() |
View Item |