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

Abstract

The aim of this study is to substantiate the use machine learning methods to optimize a combination of ultrasonic welding (USW) parameters for manufacturing of multilayer lap joints consisting of two outer PEEK layers, a middle prepreg of unidirectional carbon fibers (CFs), and two energy directors (EDs) between them. As a result, a mathematical problem associated with determining the optimal combination of technological parameters was formulated for the formation of USW joints possessing improved functional properties. In addition, a methodology was proposed to analyze the mechanical properties of USW joints based on neural network simulation (NNS). Experiments were performed, and threshold values of the optimality conditions for the USW parameters were chosen. Accordingly, NNS was carried out to determine the parameter ranges, showing that the developed optimality condition was insufficient and required correction, taking into account other significant structural characteristics of the formed USW joints. The NNS study enabled specification of an extra area of USW parameters that were not previously considered optimal when designing the experiment. The NNS-predicted USW mode (P = 1.5 atm, t = 800 ms, and τ = 1500 ms) ensured formation of a lap joint with the required mechanical and structural properties (σUTS = 80.5 MPa, ε = 4.2 mm, A = 273 N·m, and Δh = 0.30 mm).

Ultrasonic welding of lap joints of PEI plates with PEI/CF-fabric prepregs

“…However, failure is to be guaranteed to occur adhesively along the fusion zone (between the adherends) in the studied cases. Since the neat PEI plates were welded, the USW joints could be fractured through the base material [26]. Respectively, the applied strength criterion was the  f parameter.…”

Effect of the Energy Director Material on the Structure and Properties of Ultrasonic Welded Lap Joints of PEI Plates with CF Fabric/PEI Prepreg

“…The main cracks initiated at their junctions with the PEI adherends (which were stress raisers) and propagated along the interlayer interface. This phenomenon caused additional bending of the PEI plates [37], so the high adhesion level slowed down the process, according to the authors. The final fracture stage was of a cohesive type.…”

“…The DIC method [39,40] was applied to experimentally confirm the macroscopic bending of the USW lap joints during the tensile tests (previously investigated by computer simulation based on the finite-element method [37]), as well as to assess strain distributions in both the PEI plates and the fusion zone. The TecaPEI lap joint fabricated using mode #5 was tested under static tension at a cross-head speed of 1 mm/min.…”

“…Taking into account the above-mentioned fact of the influence of macrobending of the TecaPEI lap joints in the tensile tests [37], the improvement of the mechanical properties could not be the only criterion for optimizing USW parameters. For this reason, an analysis of the structural (geometric) characteristics of the one obtained using mode #5 (Table 3) was also carried out.…”

Application of Neural Network Models with Ultra-Small Samples to Optimize the Ultrasonic Consolidation Parameters for ‘PEI Adherend/Prepreg (CF-PEI Fabric)/PEI Adherend’ Lap Joints

“…A brief overview of the application of machine learning methods using small experimental data samples. As the authors have shown previously [ 42 ], the issue of finding an optimal combination of USC parameters cannot be considered as an optimization problem, since the conditions for ensuring the optimality of the functional characteristics of such lap joints are represented by a system of inequalities. This formulation is determined not only by the inconsistency of the requirements (formulation of criteria) for their individual properties, but also by the specifics of the problem.…”