In light of climate change, fiber-reinforced plastics (FRP) are becoming increasingly important due to their lightweight construction potential. This benefit is additionally expanded on with the low cycle times, scrap rates and material costs of Sheet Moulding Compounds (SMC), making it the most often used material on the FRP market. While extensive studies regarding the recycling of SMC with unsaturated polyester-based matrices (UP-SMC) have been conducted in the past, this is not the case for vinylester-based SMC (VE-SMC). In this research, VE-SMC components were subject to a particle-recycling approach. Recyclate in the form of VE-SMC regrind was used to substitute SMC matrices during the compounding process. The dependence of the mechanical properties and failure behavior of VE-SMC containing regrind was investigated by means of microscopic and mechanical test methods for varying mass proportions of SMC regrind. Due to the addition of SMC regrind, a decreased fiber/matrix adhesion was observed. Furthermore, an increase in pore formation was observed with an increasing proportion of SMC regrind. The flexural modulus increased by 20% with a low percentage of regrind (ω_rSMC = 10 wt.%) in comparison to virgin SMC. In contrast, the tensile properties decrease (up to 30%) with the addition of SMC regrind independent of the investigated proportions of SMC regrind.

In the design of parts consisting of long-fibre-reinforced Sheet Moulding Compounds (SMC), the potential for the optimisation of processing parameters and geometrical design is limited due to the high number of interdependent variables. One of the influences on fibre orientations and therefore mechanical part performance is the initial filling state of the compression moulding tool, which is defined by the geometry and positioning of the SMC preform. In the past, response surface methodology and linear regression analysis were successfully used for a simulation-based optimisation of rectangular preform size and position in regard to a part performance parameter. However, the computational demand of these increase exponentially with an increase in the number of design variables, such as in the case of more complex preform geometries. In this paper, these restrictions are addressed with a novel approach for metamodelling the correlation of preform and the resulting mechanical part performance. The approach is applied to predicting the maximum absolute deflection of a plate geometry under bending load. For metamodelling, multiple neural networks (NN) are trained on a dataset obtained by process and structural simulation. Based on the discretisation of the plate geometry used in these simulation procedures, the binary initial filling states (completely filled/empty) of each element are used as inputs of the NNs. Outputs of the NNs are combined by ensemble modelling to form the metamodel. The metamodel allows an accurate prediction of maximum deflection; subsequent validation of the metamodel shows differences in predicted and simulated maximum deflection ranging from 0.26% to 2.67%. Subsequently, the metamodel is evaluated using a mutation algorithm for finding a preform that reduces the maximum deflection.