Effect of chemical treatment on the mechanical and thermal performance of flax fiber reinforced aluminium 6082 laminate: a machine learning-enhanced investigation.

This work examined the role of alkaline and epoxy-based surface chemical treatments on the mechanical and thermal properties of flax fiber reinforced Aluminum Alloy 6082 hybrid Fiber Metal Laminates (FMLs), integrated with machine learning (ML) predictive frameworks. Flax fiber mats underwent surface modification via a 1% NaOH alkaline soak followed by an epoxy sizing treatment to promote stronger bonding with the aluminum matrix. Concurrently, aluminum sheets were treated with an NaOH-Na₂CO₃ alkaline bath to enhance metal-polymer interfacial compatibility. Composite laminates were manufactured through hand layup combined with compression molding at 30 bar and 70 °C curing for four hours. Tensile characterization followed ASTM D638 protocols, thermal conductivity measurements employed a guarded hot plate (GHP) system per ASTM C177, and corrosion evaluation relied on gravimetric immersion in 3.5 wt.% NaCl over 30 days. Predictive models using Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Random Forest (RF) were developed on a structured 180-observation experimental dataset. Steady-state thermal conductivity values of 0.1039 W/m·K and 0.065 W/m·K were recorded for untreated and chemically treated FFAL laminates, respectively. Surface treatment yielded a 31% gain in tensile strength (168.5 MPa to 220.7 MPa) and a 34% rise in tensile modulus (12.3 GPa to 16.34 GPa), while thermal conductivity declined by 37.4%. Among all models, the Random Forest algorithm demonstrated superior predictive capability with R