Muhammad Izzulhaq
Research Subjects
Muhammad Izzulhaq has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Arif Wahjudi
Institut Teknologi Sepuluh Nopember
1 shared publication - Bobby Oedy Pramoedyo Soepangkat
Institut Teknologi Sepuluh Nopember
1 shared publication Faisal Ibrahim
1 shared publicationMaulana Yusuf Izzuddin
1 shared publicationMuhammad Thaliban Habib Hudzaifah
1 shared publication
Latest Publications
- Open Access
- 7 May 2026
- Published by Elsevier in SSRN Electronic Journal
A Multi-Criteria Framework for Optimizing Drilling Conditions in AFRP Composites based on a BPNN-GA Intelligent Framework
Aramid Fiber Reinforced Polymer (AFRP) composites are increasingly adopted in automotive lightweight structures for their excellent mechanical performance. Precision drilling remains indispensable in component assembly, where maintaining superior hole integrity is a critical requirement. This study introduces an AI-driven multi-objective optimization framework to minimize thrust force, torque, peel-up and push-out delamination damage during AFRP drilling. A two-replication full factorial design was employed, varying drill type, spindle speed, and feed rate to generate a comprehensive dataset for analysis. A Backpropagation Neural Network (BPNN) was constructed to evaluate and predict the complex connection between process parameters and multiple responses. The integration of a Backpropagation Neural Network (BPNN) with a Genetic Algorithm (GA) enabled efficient identification of the optimal drilling parameter set. Verification experiments confirmed that drilling with a twist drill at 1455 rpm and 10 mm/min achieved the lowest thrust (29.03 N), torque (90.33 Nmm), and delamination factors (peel-up: 1.157, push-out: 1.081). This hybrid BPNN–GA framework demonstrates an effective AI-driven strategy for achieving sustainable and high-precision machining of AFRP composites.
- 7 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Multi-Criteria Framework for Optimizing Drilling Conditions in AFRP Composites based on a BPNN-GA Intelligent Framework
Aramid Fiber Reinforced Polymer (AFRP) composites are increasingly adopted in automotive lightweight structures for their excellent mechanical performance. Precision drilling remains indispensable in component assembly, where maintaining superior hole integrity is a critical requirement. This study introduces an AI-driven multi-objective optimization framework to minimize thrust force, torque, peel-up and push-out delamination damage during AFRP drilling. A two-replication full factorial design was employed, varying drill type, spindle speed, and feed rate to generate a comprehensive dataset for analysis. A Backpropagation Neural Network (BPNN) was constructed to evaluate and predict the complex connection between process parameters and multiple responses. The integration of a Backpropagation Neural Network (BPNN) with a Genetic Algorithm (GA) enabled efficient identification of the optimal drilling parameter set. Verification experiments confirmed that drilling with a twist drill at 1455 rpm and 10 mm/min achieved the lowest thrust (29.03 N), torque (90.33 Nmm), and delamination factors (peel-up: 1.157, push-out: 1.081). This hybrid BPNN–GA framework demonstrates an effective AI-driven strategy for achieving sustainable and high-precision machining of AFRP composites.