Chapter 5: Machine learning-guided mechanical characterisation of 3D-printed plastic materials towards future optimisation of additive manufactured infrastructure components

Machine learning (ML)-guided materials design is a powerful tool in advancing additive manufacturing (AM) processes. ML-guided materials design involves using ML methods to analyse/model the relationships between the composition, structure and properties of materials, which will lead to predicting and optimising the properties of materials. This chapter introduces an ML-based framework aimed at accurately predicting and optimising the mechanical properties of three dimensional (3D)-printed plastic, using a comprehensive dataset derived from varied AM processes. By systematically analysing the interaction between processing parameters and the resulting material characteristics, the study presented in this chapter not only predicts the tensile strength of 3D-printed plastic but also identifies critical factors affecting its performance. Addressing the challenges of data scarcity and complex parameter interactions, this chapter expands the predictive capabilities of ML in AM, optimising print conditions for enhanced material properties. The findings provide a basis for optimising AM-based structural components, such as modular bridge segments and lightweight formworks, where plastic-based composites play a critical role. While this chapter primarily characterises mechanical properties, its findings lay the groundwork for future applications in structural optimisation, facilitating the development of smart and sustainable infrastructure.