Skip to Main Content
Article navigation
Purpose

This research introduces a comprehensive framework for optimising fibre laser butt welding of NiTi shape memory alloy (SMA) wires, integrating experimental studies, predictive modelling and sustainability evaluation, with particular focus on the tensile strength–corrosion trade-off.

Design/methodology/approach

A 43-run central composite design (CCD) experiment was conducted to assess how laser power, pulse duration, frequency, wire diameter and filler powder types (Fe/Cu/Ni) influence tensile strength and corrosion rate. The resulting response patterns were examined using ANOVA and Pareto charts, and three modelling methods – adaptive neuro-fuzzy inference system (ANFIS), particle swarm optimised ANFIS (PSO-ANFIS) and Gaussian process regression (GPR) – were compared. A hybrid AHP–entropy approach was used to benchmark the sustainability of different welding techniques.

Findings

ANOVA and Pareto analysis confirmed pulse time, frequency and power as dominant factors for both responses. Fe filler produced tensile strengths over 400 MPa, while Ni filler had the lowest corrosion rate (∼0.001298 mm/year) and more uniform weld microstructures, showing a strength–corrosion trade-off. GPR model outperformed others with high accuracy for tensile strength (R2 = 0.8752; RMSE = 23.9706 MPa) and corrosion rate (R2 = 0.9565; RMSE = 0.0001 mm/year). Confirmatory tests supported predictions, and fibre laser welding was ranked most sustainable.

Practical implications

The integration of predictive modelling with sustainability evaluation offers a strong tool for optimising technical performance and environmental impact in NiTi SMA welding. This study's insights are vital for industrial engineering, where high-performance materials and sustainable manufacturing improve reliability, cut costs and ensure environmental compliance.

Originality/value

The proposed methodology offers a novel comparative perspective on modelling strategies, supporting informed decision-making in advanced manufacturing using a relatively small dataset.

Licensed re-use rights only
You do not currently have access to this content.
Don't already have an account? Register

Purchased this content as a guest? Enter your email address to restore access.

Please enter valid email address.
Email address must be 94 characters or fewer.
Pay-Per-View Access
$41.00
Rental

or Create an Account

Close Modal
Close Modal

Gift article access

As a benefit of your subscription, you can share temporary access to restricted articles.

Each link will stop working after 30 days or 10 uses. You may create up to 10 links in a 30 day period.

Please sign in to your personal account to gift article access.

Register

Gift article access

As a benefit of your subscription, you can share temporary access to restricted articles.

Each link will stop working after 30 days or 10 uses. You may create up to 10 links in a 30 day period.

Gift articles remaining: --

Gift article access

Each link will stop working after 30 days or 10 uses. You may create up to 10 links in a 30 day period.

Gift articles remaining: --

Gift article access

As a benefit of your subscription, you can share temporary access to restricted articles.

Each link will stop working after 30 days or 10 uses.

You have reached the limit of 10 links within a 30 day period.