Sandwich panels—thin face sheets bonded to lightweight cores—are critical structural components in aerospace, automotive, mining, marine, and industrial applications. The integration of 3D-printed lattice cores enables unprecedented control over acoustic and vibration performance. However, optimizing sandwich panel designs across multiple competing objectives (acoustic radiation reduction, vibration damping, weight minimization, manufacturing feasibility, cost) remains a significant challenge.
Research Gap: No systematic machine learning framework exists for multi-objective optimization of 3D-printed lattice sandwich panels accounting for **coupled vibration-acoustic behavior.
Innovation: This PhD project develops a machine learning-guided multi-objective optimization framework that:
- Uses FEA-based surrogate models to rapidly explore 10,000+ design combinations
- Simultaneously optimizes five competing objectives: minimize sound radiation, maximize damping, minimize weight, maximize printability, minimize cost
- Applies Pareto optimization to reveal design trade-offs
- Validates designs experimentally with coupled vibration-acoustic testing
- Demonstrates real-world application on WA industrial equipment
Aim
To develop a machine learning-guided, multi-objective optimization framework for 3D-printed sandwich panel designs that systematically balances acoustic performance, structural damping enhancement, weight minimization, and manufacturing feasibility—enabling rapid, informed design of high-performance structures.
Objectives
- Map the complete lattice core design parameter space via 200-300 FEA simulations
- Train ML models predicting vibro-acoustic performance with ≥90% accuracy on test datasets
- Use Shapley values and sensitivity analysis to identify critical design parameters
- Apply Pareto-based optimization to identify optimal design trade-offs
- 3D-print and test 5-10 sandwich panel designs; validate ML predictions with <10% error
Significance
WA Strategic Alignment:
- Mining & METS: $70B+ green mining investment; BHP/Rio Tinto electric haul trucks require advanced isolation
- Energy: $104B clean energy; hydrogen facilities need vibration/noise control for Pilbara extremes
- Space Industries: Compact, high-performance components with controlled vibration/acoustic radiation
Research Contribution: Fills critical gap by combining vibrations/acoustics, structural mechanics, and ML into integrated framework for multi-objective design.
Ideal Candidate
Essential:
- Bachelor’s/Master’s in Mechanical/Aerospace Engineering
- Strong background in vibrations, acoustics, or structural mechanics
- FEA software experience (ANSYS or equivalent)
- Basic Python/MATLAB programming
- Strong experimental design skills
Preferred: Relevant undergrad FYP or master’s thesis in sandwich panels or vibro-acoustic optimization. Additionally, the applicants should meet the eligibility criteria for entry into a PhD program at Curtin University.
This project is open to International and Domestic applicants.
Internship
This PhD project includes structured research internship across WA industry end-users in mining, energy, and advanced manufacturing sectors (140–160 FTE days across Year 3), significantly exceeding 60-day priority threshold. Three embedded case studies: (1) validating optimized sandwich panels on mining equipment in Pilbara, (2) designing vibration/acoustic isolation for hydrogen facility equipment, (3) prototyping lightweight vibration-damped aerospace/defence structures. Student undertakes field testing, performance monitoring, technology transfer, and co-authors 2–3 publications with industry collaborators.
Scholarship
If you are identified as the preferred candidate for this project, you may be considered for an RTP scholarship.
Enquires and How to Apply
For enquires about this opportunity contact Dr Azma Putra Azis at Azmaputra.Azis@curtin.edu.au
To formally apply submit an Expression of Interest to Dr Azma Putra Azis during the Central Scholarship round (July 1st – July 31st 2026)