Repair of Impacted Thermoplastic Composite Laminates Using Induction Welding.

The lack of well-developed repair techniques limits the use of thermoplastic composites in commercial aircraft, although trends show increased adoption of composite materials. In this study, high-performance thermoplastic composites, viz., carbon fibre (CF) reinforced Polyetherketoneketone (PEKK) and Polyether ether ketone (PEEK), were subjected to low-velocity impact tests at 20 J. Post-impact, the damaged panels were repaired using an induction welder by applying two different methods: induction welding of a circular patch to the impacted area of the laminate (RT-1); and induction welding of the impacted laminates under the application of heat and pressure (RT-2). The panels were subjected to compression-after-impact and repair (CAI-R), and the results are compared with those from the compression-after-impact (CAI) tests. For CF/PEKK, the RT-1 and RT-2 resulted in a 13% and 7% higher strength, respectively, than the value for CAI. For CF/PEEK, the corresponding values for RT-1 and RT-2 were higher by 13% and 17%, respectively. Further analysis of the damage and repair techniques using ultrasonic C-scans and CAI-R tests indicated that induction welding can be used as a repair technique for industrial applications. The findings of this study are promising for use in aerospace and automotive applications.

Multi-objective optimisation of ultrasonically welded dissimilar joints through machine learning.

The use of composite materials is increasing in industry sectors such as renewable energy generation and storage, transport (including automotive, aerospace and agri-machinery) and construction. This is a result of the various advantages of composite materials over their monolithic counterparts, such as high strength-to-weight ratio, corrosion resistance, and superior fatigue performance. However, there is a lack of detailed knowledge in relation to fusion joining techniques for composite materials. In this work, ultrasonic welding is carried out on a carbon fibre/PEKK composite material bonded to carbon fibre/epoxy composite to investigate the influence of weld process parameters on the joint's lap shear strength (LSS), the process repeatability, and the process induced defects. A 33 parametric study is carried out and a robust machine learning model is developed using a hybrid genetic algorithm-artificial neural network (GA-ANN) trained on the experimental data. Bayesian optimisation is employed to determine the most suitable GA-ANN hyperparameters and the resulting GA-ANN surrogate model is exploited to optimise the welding process, where the process performance metrics are LSS, repeatability and joint visual quality. The prediction for the optimal LSS was subsequently validated through a further set of experiments, which resulted in a prediction error of just 3%.