Melola Discovery

← Melola Discovery

Jurnal SINTA 1

Multi-objective optimization of SS 410 CNC plasma cutting using RSM, ANN, MOGA, and MOALO

Mechanical Engineering for Society and Industry · Vol. 5 No. 2 (2026) · hlm. 560–575

DOI
10.31603/mesi.11646
ISSN
2798-5245
Terbit
2026-01-06
Penerbit
Universitas Muhammadiyah Magelang
Bahasa
en

Abstrak

This study focuses on optimizing the CNC plasma cutting process for Stainless Steel 410 alloy, a type of martensitic stainless steel known for its high strength, hardness, and good corrosion resistance, using Response Surface Methodology (RSM) combined with advanced optimization methods. Key input variables, including cutting current, speed, and torch height, were systematically analyzed to enhance cutting efficiency by minimizing machining time and surface roughness while maximizing material removal rate. The experimental approach utilized a Central Composite Design (CCD) with 18 trials and Analysis of Variance (ANOVA) to validate linear models as optimal predictors for response variables. Results indicate that cutting speed significantly influences machining time and material removal rate, while cutting current and torch height also influence surface roughness. To improve prediction accuracy and explore the parameter space beyond experimental trials, Artificial Neural Networks (ANN) were implemented, demonstrating superior predictive capabilities compared to RSM alone. Moreover, Multi-Objective Genetic Algorithm (MOGA) and Multi-Objective Ant Lion Optimizer (MOALO) were employed to refine optimization outcomes, addressing trade-offs between conflicting objectives. The optimal configuration, identified as a cutting current of 85.31 A, a speed of 1500 mm/min, and a torch height of 5 mm, achieved a machining time of 0.665 minutes, a surface roughness of 1.77 μm, and a material removal rate of 77.08 g/min. These findings underscore the effectiveness of integrating statistical methods with machine learning and advanced optimization algorithms for precision manufacturing. The study offers a comprehensive framework for improving process efficiency and quality in CNC plasma cutting, catering to the growing demand for high-performance cutting techniques in the steel industry.

Kata kunci

Jaringan kolaborasi para penulis

12 penulis · 30 tautan kepenulisan bersama · 13 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • University of Indonesia
  • Hiroshima University
  • Universitas Muhammadiyah Magelang
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Adi SurjosatyoUniversity of Indonesia2
Hafif DafiqurrohmanUniversity of Indonesia2
Izzuddin Al QossamUniversity of Indonesia2
Puspa LestariUniversity of Indonesia2
Teddy TumenggungAfiliasi tidak diketahui1
Achmad RiadiUniversity of Indonesia1
Muhammad Arif BudiyantoUniversity of Indonesia1
Muhammad Agung SantosoUniversity of Indonesia1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://journal.unimma.ac.id/index.php/mesi/oai, pertama di-harvest 9 Nov 2026, terakhir terlihat 9 Nov 2026.
Metadata asli (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Multi-objective optimization of SS 410 CNC plasma cutting using RSM, ANN, MOGA, and MOALO</dc:title>
	<dc:creator xml:lang="en">Sari, Wanda Rulita</dc:creator>
	<dc:creator xml:lang="en">Saputro, Bayu Aji</dc:creator>
	<dc:creator xml:lang="en">Gunawan, Gunawan</dc:creator>
	<dc:creator xml:lang="en">Muzhoffar, Dimas Angga Fakhri</dc:creator>
	<dc:subject xml:lang="en">Plasma arc cutting</dc:subject>
	<dc:subject xml:lang="en">SS 410 alloy</dc:subject>
	<dc:subject xml:lang="en">Response surface methodology</dc:subject>
	<dc:subject xml:lang="en">Artificial neural networks</dc:subject>
	<dc:subject xml:lang="en">Multi-objective genetic algorithm</dc:subject>
	<dc:subject xml:lang="en">Multi-objective ant lion optimizer</dc:subject>
	<dc:subject xml:lang="en">Process optimization</dc:subject>
	<dc:description xml:lang="en">This study focuses on optimizing the CNC plasma cutting process for Stainless Steel 410 alloy, a type of martensitic stainless steel known for its high strength, hardness, and good corrosion resistance, using Response Surface Methodology (RSM) combined with advanced optimization methods. Key input variables, including cutting current, speed, and torch height, were systematically analyzed to enhance cutting efficiency by minimizing machining time and surface roughness while maximizing material removal rate. The experimental approach utilized a Central Composite Design (CCD) with 18 trials and Analysis of Variance (ANOVA) to validate linear models as optimal predictors for response variables. Results indicate that cutting speed significantly influences machining time and material removal rate, while cutting current and torch height also influence surface roughness. To improve prediction accuracy and explore the parameter space beyond experimental trials, Artificial Neural Networks (ANN) were implemented, demonstrating superior predictive capabilities compared to RSM alone. Moreover, Multi-Objective Genetic Algorithm (MOGA) and Multi-Objective Ant Lion Optimizer (MOALO) were employed to refine optimization outcomes, addressing trade-offs between conflicting objectives. The optimal configuration, identified as a cutting current of 85.31 A, a speed of 1500 mm/min, and a torch height of 5 mm, achieved a machining time of 0.665 minutes, a surface roughness of 1.77 μm, and a material removal rate of 77.08 g/min. These findings underscore the effectiveness of integrating statistical methods with machine learning and advanced optimization algorithms for precision manufacturing. The study offers a comprehensive framework for improving process efficiency and quality in CNC plasma cutting, catering to the growing demand for high-performance cutting techniques in the steel industry.</dc:description>
	<dc:publisher xml:lang="en">Universitas Muhammadiyah Magelang</dc:publisher>
	<dc:date>2026-01-06</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.unimma.ac.id/mesi/article/view/11646</dc:identifier>
	<dc:identifier>10.31603/mesi.11646</dc:identifier>
	<dc:source xml:lang="en">Mechanical Engineering for Society and Industry; Vol. 5 No. 2 (2025); 560-575</dc:source>
	<dc:source>2798-5245</dc:source>
	<dc:language>en</dc:language>
	<dc:relation>https://journal.unimma.ac.id/mesi/article/view/11646/6435</dc:relation>
	<dc:rights xml:lang="en">Copyright (c) 2026 Wanda Rulita Sari, Bayu Aji Saputro, Gunawan Gunawan, Dimas Angga Fakhri Muzhoffar</dc:rights>
</oai_dc:dc>