Integration of Hybrid Machine Learning and Multi-Objective Optimization for Enhanced Turning Parameters of EN-GJL-250 Cast Iron
This study aims to optimize the turning parameters for EN-GJL-250 grey cast iron using hybrid machine learning techniques integrated with multi-objective optimization algorithms. The experimental design focused on evaluating the impact of cutting tool type, testing three tools: uncoated and coated s...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Crystals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4352/15/3/264 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850205771482005504 |
|---|---|
| author | Yacine Karmi Haithem Boumediri Omar Reffas Yazid Chetbani Sabbah Ataya Rashid Khan Mohamed Athmane Yallese Aissa Laouissi |
| author_facet | Yacine Karmi Haithem Boumediri Omar Reffas Yazid Chetbani Sabbah Ataya Rashid Khan Mohamed Athmane Yallese Aissa Laouissi |
| author_sort | Yacine Karmi |
| collection | DOAJ |
| description | This study aims to optimize the turning parameters for EN-GJL-250 grey cast iron using hybrid machine learning techniques integrated with multi-objective optimization algorithms. The experimental design focused on evaluating the impact of cutting tool type, testing three tools: uncoated and coated silicon nitride (Si<sub>3</sub>N<sub>4</sub>) ceramic inserts and coated cubic boron nitride (CBN). Key cutting parameters such as depth of cut (<i>ap</i>), feed rate (<i>f</i>), and cutting speed (<i>Vc</i>) were varied to examine their effects on surface roughness (<i>Ra</i>), cutting force (<i>Fr</i>), and power consumption (<i>Pc</i>). The results showed that the coated Si<sub>3</sub>N<sub>4</sub> tool achieved the best surface finish, with minimal cutting force and power consumption, while the uncoated Si<sub>3</sub>N<sub>4</sub> and CBN tools performed slightly worse. Advanced optimization models including improved grey wolf optimizer–deep neural networks (DNN-IGWOs), genetic algorithm–deep neural networks (DNN-GAs), and deep neural network–extended Kalman filters (DNN-EKF) were compared with traditional methods like Support Vector Machines (SVMs), Decision Trees (DTs), and Levenberg–Marquardt (LM). The DNN-EKF model demonstrated exceptional predictive accuracy with an R<sup>2</sup> value of 0.99. The desirability function (DF) method identified the optimal machining parameters for the coated Si<sub>3</sub>N<sub>4</sub> tool: <i>ap</i> = 0.25 mm, <i>f</i> = 0.08 mm/rev, and <i>Vc</i> = 437.76 m/min. At these settings, <i>Fr</i> ranged between 46.424 and 47.405 N, <i>Ra</i> remained around 0.520 µm, and <i>Pc</i> varied between 386.518 W and 392.412 W. The multi-objective grey wolf optimization (MOGWO) further refined these parameters to minimize <i>Fr</i>, <i>Ra</i>, and <i>Pc</i>. This study demonstrates the potential of integrating machine learning and optimization techniques to significantly enhance manufacturing efficiency. |
| format | Article |
| id | doaj-art-aa17e69d92b0423c9c501f8a5d49489b |
| institution | OA Journals |
| issn | 2073-4352 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Crystals |
| spelling | doaj-art-aa17e69d92b0423c9c501f8a5d49489b2025-08-20T02:11:01ZengMDPI AGCrystals2073-43522025-03-0115326410.3390/cryst15030264Integration of Hybrid Machine Learning and Multi-Objective Optimization for Enhanced Turning Parameters of EN-GJL-250 Cast IronYacine Karmi0Haithem Boumediri1Omar Reffas2Yazid Chetbani3Sabbah Ataya4Rashid Khan5Mohamed Athmane Yallese6Aissa Laouissi7Electromechanical Department, Institute of Applied Sciences and Techniques, University of Constantine 1, Constantine 25017, AlgeriaMechanical Department, Institute of Applied Sciences and Techniques, University of Constantine 1, Constantine 25017, AlgeriaElectromechanical Department, Institute of Applied Sciences and Techniques, University of Constantine 1, Constantine 25017, AlgeriaLaboratory of Mechanics and Materials Development, Department of Civil Engineering, University of Djelfa, Djelfa 17000, AlgeriaDepartment of Mechanical Engineering, College of Engineering, Imam Mohammad Ibn Saud Islamic University, Riyadh 11432, Saudi ArabiaDepartment of Mechanical Engineering, College of Engineering, Imam Mohammad Ibn Saud Islamic University, Riyadh 11432, Saudi ArabiaLMS Laboratory, 8 Mai 1945 University, Guelma 24000, AlgeriaDepartment of Mechanical Engineering, Faculty of Sciences and Technology, University of Bordj Bou Arreridj, Bordj Bou Arreridj 34033, AlgeriaThis study aims to optimize the turning parameters for EN-GJL-250 grey cast iron using hybrid machine learning techniques integrated with multi-objective optimization algorithms. The experimental design focused on evaluating the impact of cutting tool type, testing three tools: uncoated and coated silicon nitride (Si<sub>3</sub>N<sub>4</sub>) ceramic inserts and coated cubic boron nitride (CBN). Key cutting parameters such as depth of cut (<i>ap</i>), feed rate (<i>f</i>), and cutting speed (<i>Vc</i>) were varied to examine their effects on surface roughness (<i>Ra</i>), cutting force (<i>Fr</i>), and power consumption (<i>Pc</i>). The results showed that the coated Si<sub>3</sub>N<sub>4</sub> tool achieved the best surface finish, with minimal cutting force and power consumption, while the uncoated Si<sub>3</sub>N<sub>4</sub> and CBN tools performed slightly worse. Advanced optimization models including improved grey wolf optimizer–deep neural networks (DNN-IGWOs), genetic algorithm–deep neural networks (DNN-GAs), and deep neural network–extended Kalman filters (DNN-EKF) were compared with traditional methods like Support Vector Machines (SVMs), Decision Trees (DTs), and Levenberg–Marquardt (LM). The DNN-EKF model demonstrated exceptional predictive accuracy with an R<sup>2</sup> value of 0.99. The desirability function (DF) method identified the optimal machining parameters for the coated Si<sub>3</sub>N<sub>4</sub> tool: <i>ap</i> = 0.25 mm, <i>f</i> = 0.08 mm/rev, and <i>Vc</i> = 437.76 m/min. At these settings, <i>Fr</i> ranged between 46.424 and 47.405 N, <i>Ra</i> remained around 0.520 µm, and <i>Pc</i> varied between 386.518 W and 392.412 W. The multi-objective grey wolf optimization (MOGWO) further refined these parameters to minimize <i>Fr</i>, <i>Ra</i>, and <i>Pc</i>. This study demonstrates the potential of integrating machine learning and optimization techniques to significantly enhance manufacturing efficiency.https://www.mdpi.com/2073-4352/15/3/264cutting parameterssurface roughnesshybrid machine learningpredictive modelingmulti-objective optimization |
| spellingShingle | Yacine Karmi Haithem Boumediri Omar Reffas Yazid Chetbani Sabbah Ataya Rashid Khan Mohamed Athmane Yallese Aissa Laouissi Integration of Hybrid Machine Learning and Multi-Objective Optimization for Enhanced Turning Parameters of EN-GJL-250 Cast Iron Crystals cutting parameters surface roughness hybrid machine learning predictive modeling multi-objective optimization |
| title | Integration of Hybrid Machine Learning and Multi-Objective Optimization for Enhanced Turning Parameters of EN-GJL-250 Cast Iron |
| title_full | Integration of Hybrid Machine Learning and Multi-Objective Optimization for Enhanced Turning Parameters of EN-GJL-250 Cast Iron |
| title_fullStr | Integration of Hybrid Machine Learning and Multi-Objective Optimization for Enhanced Turning Parameters of EN-GJL-250 Cast Iron |
| title_full_unstemmed | Integration of Hybrid Machine Learning and Multi-Objective Optimization for Enhanced Turning Parameters of EN-GJL-250 Cast Iron |
| title_short | Integration of Hybrid Machine Learning and Multi-Objective Optimization for Enhanced Turning Parameters of EN-GJL-250 Cast Iron |
| title_sort | integration of hybrid machine learning and multi objective optimization for enhanced turning parameters of en gjl 250 cast iron |
| topic | cutting parameters surface roughness hybrid machine learning predictive modeling multi-objective optimization |
| url | https://www.mdpi.com/2073-4352/15/3/264 |
| work_keys_str_mv | AT yacinekarmi integrationofhybridmachinelearningandmultiobjectiveoptimizationforenhancedturningparametersofengjl250castiron AT haithemboumediri integrationofhybridmachinelearningandmultiobjectiveoptimizationforenhancedturningparametersofengjl250castiron AT omarreffas integrationofhybridmachinelearningandmultiobjectiveoptimizationforenhancedturningparametersofengjl250castiron AT yazidchetbani integrationofhybridmachinelearningandmultiobjectiveoptimizationforenhancedturningparametersofengjl250castiron AT sabbahataya integrationofhybridmachinelearningandmultiobjectiveoptimizationforenhancedturningparametersofengjl250castiron AT rashidkhan integrationofhybridmachinelearningandmultiobjectiveoptimizationforenhancedturningparametersofengjl250castiron AT mohamedathmaneyallese integrationofhybridmachinelearningandmultiobjectiveoptimizationforenhancedturningparametersofengjl250castiron AT aissalaouissi integrationofhybridmachinelearningandmultiobjectiveoptimizationforenhancedturningparametersofengjl250castiron |