article · Procedia Manufacturing
Friction stir welding is a solid-state joining method used across the aerospace, marine, and automotive sectors to join various alloys, including aluminium, copper, and titanium. In this process, operational parameters including welding speed, rotational tool speed, pin profile, and axial force heavily influence the overall quality of the welded joint. A study evaluated two predictive modelling approaches, the response surface method and the adaptive neuro-fuzzy inference system, to enhance the ultimate tensile strength of dissimilar joints formed between AA2024 and AA5083 aluminium alloys. A four-factor, three-level model was implemented using the neuro-fuzzy framework to examine how the key welding parameters impact joint strength. When compared statistically with the response surface method, the adaptive neuro-fuzzy inference system proved to be the more effective modelling tool for predicting the mechanical properties of these welded joints.
Joining dissimilar aluminium alloys is essential for building strong, lightweight components in transport industries. Accurately predicting the ultimate tensile strength of these joints helps engineers select optimal welding settings without relying solely on trial and error. Demonstrating that neuro-fuzzy models outperform traditional response surface methods provides a more reliable computational pathway for controlling process parameters and achieving higher-quality welds.
This predictive modelling approach is relevant to manufacturing and design engineers within the aerospace, marine, and automotive industries seeking to join dissimilar aluminium alloys. By improving the prediction of joint tensile strength from operational variables, it can help refine manufacturing settings. The research is applied and tested at a computational and experimental level, meaning further software integration and factory testing would be needed before near-market deployment.
AI-generated from the published abstract. Always read the original work before citing.
Friction stir welding (FSW) is a solid-state joining technique which has been employed in aerospace, marine, and automotive industries for joining aluminum, copper, titanium and other alloys. The FSW process parameters such as welding speed, tool rotational speed, pin profile, and axial force have a main role in determining the joint quality. A comparative study was achieved between the response surface method (RSM) and the adaptive neuro-fuzzy inference system (ANFIS) to improve the mechanical properties of dissimilar friction stir welded AA2024-AA5083 aluminium alloys in terms of the ultimate tensile strength (UTS). The effects of the welding parameters on the UTS were investigated using four-factor, three-level ANFIS model. The statistical results of the ANFIS model were compared with those of RSM. The results reveal that the developed ANFIS model is more powerful than the RSM model.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.promfg.2019.12.088
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
