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

Abstract

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%.

Optimizing Ultrasonic Welding Parameters for Multilayer Lap Joints of PEEK and Carbon Fibers by Neural Network Simulation

“…In addition, the finite element method is a popular tool for numerical investigations of deformation processes occurring under mechanical loading of US-welded laminates [ 55 ]. Thus, the variety of process and parameters to be taken into account in the design of USW technology has expectedly attracted a machine learning approach, primarily ANNs [ 56 , 57 , 58 , 59 , 60 ].…”

“…The relevant papers on the application of ANNs to solve USW problems [ 56 , 58 , 61 , 62 , 63 ] focus on their synthesis with low approximation error ( MSE , RMSE , etc.) of the known data, as well as prognosis of a single property of the joint.…”

Controlling Crystallization: A Key Factor during 3D Printing with the Advanced Semicrystalline Polymeric Materials PEEK, PEKK 6002, and PEKK 7002

“…[2] PAEK materials can be processed in the same way as ordinary thermoplastic materials, including via injection molding, extrusion, powder coating, compression molding, computer numerical control machining, or additive manufacturing (AM) to create a range of useful products. [3][4][5] Many industrial sectors are now using the PAEK family of thermoplastics either in their pristine form or as a composite with other materials for advanced engineering applications in areas such as aerospace, automotive, oil and gas, electronic devices, semiconductors, food processing, and medical due to their favorable properties and significant advantages that they provide in comparison to other polymeric materials and metals. [6][7][8][9] Two AM techniques are commonly used to process PAEK materials, selective laser sintering (SLS) and fused filament fabrication (FFF).…”

Repair of Impacted Thermoplastic Composite Laminates Using Induction Welding

“…Toyoda et al [20] investi However, more research is required to develop efficient and reliable composite repair methods, enabling safer, lighter, and more efficient repair solutions for next-generation composite structures. The processing advantages offered by thermoplastics for high throughput and their inherent recyclability make them an increasingly attractive option for aircraft structures [11][12][13][14][15][16][17]. Aerostructures are susceptible to impact damage in-service, leading to catastrophic failures, thus, creating a need for the development of suitable repair techniques.…”