Experimental investigation and machine learning-based optimization of abrasive water jet drilling in GFRP laminates
Year: 2026
Type: article
Abstract: Abrasive water jet drilling (AWJD) has emerged as a promising technique for producing fastener holes in glass fiber reinforced polymer (GFRP) laminates, where conventional drilling often suffers from tool wear, delamination, and dimensional inaccuracy. This study systematically investigates the influence of nozzle diameter (d), stand-off distance (SOD), water jet pressure (WJP), and abrasive flow rate (AFR) on five critical responses: material removal rate (MRR), circularity error (CE), overcut (OC), taper angle (θ), and delamination factor (Fd). Controlled experiments were conducted using Taguchi’s L18 orthogonal array for two practical hole diameters (2 mm and 4 mm). The experimental data were analyzed through ANOVA, correlation mapping, and entropy-based weighting to quantify factor significance. To address the challenge of multi-response optimization, an unsupervised machine learning framework (k-means clustering) was developed. Unlike regression or RSM-based models, clustering effectively captured nonlinear dependencies and revealed stable process clusters, enabling robust parameter selection. The results identified nozzle diameter and WJP as dominant factors influencing productivity, while AFR and SOD significantly affected surface integrity and geometry. The probability-density surfaces highlighted clear trade-offs between productivity and quality, confirming the need for multi-objective optimization. The proposed framework provides practical guidelines for tailoring AWJD parameters to balance accuracy, integrity, and throughput in composite machining applications.
Institutions: Osmania University, Jamia Millia Islamia
Language: English
Subfield: Ecological Modeling
Field: Environmental Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7128922158