![[ Visit Client Website ]](images/banner.gif)
In order to design a safe and practical Friction Stir Welding (FSW) process, it is crucial to identify the correlations between the controllable process conditions, such as tool rotation speed and traverse speed, and some internal process variables, which include tool temperature, shaft temperature, torque, traverse force, compression force, and tool bending forces ('tool force footprint' by displaying them onto a polar plot) [1] in this work. They would be very helpful in the weld design to avoid the overheating and tool wear problems. However, due to the high complexities involved in the welding process, such as non-linearities, uncertainties and in certain cases the lack of fundamental knowledge, it is often 'tricky' to derive practical physical models [2]. In such a situation, a systematic data-driven fuzzy modelling strategy was developed in this work to elicit adequate prediction models for the internal process features of FSW (see Figure 1), relating to the AA5083 aluminium alloy.
The proposed modelling methodology allows constructing transparent fuzzy models considering both accuracy and interpretability attributes of fuzzy systems by using the multi-objective optimisation technique. Compared with analytically based methods, fuzzy systems are capable of learning from data without needing much prior knowledge about the materials and processes. On the other hand, compared with black-box modelling approaches, fuzzy systems have transparent characteristics and the relationships between inputs and outputs are more interpretable, because of their use of descriptive language, such as linguistic 'If-Then' rules. The elicited models would be effective to enhance the welding productivity and process reliability (see Figure 2). They can be further exploited to serve as the core module for 'reverse-engineering' designs that are able to suggest optimal process conditions (process routes) by taking into account a set of desired objectives relating to achieving structurally sound, defect free, and reliable welds.
