Search

Remarkable mechanical properties make carbon fibres attractive for many industrial applications. However, up to today, carbon fibres come with a significant environmental backpack, undermining their advantages in light of a strong demand for absolute sustainability of new industrial products. Consequently, there is considerable demand for high-quality carbon fibre manufacturing, low waste production, or alternative precursor systems allowing minimization of environmental impacts. Therefore, this paper investigates the capabilities of data analytics with a special emphasis on predictive quality in order to advance the quality management of carbon fibre manufacturing. Although existing research supports the applicability of machine learning in carbon fibre production, there is a notable scarcity of case studies and a lack of a structured repetitive data analytics concept. To address this gap, the study proposes a holistic framework for predictive quality in carbon fibre manufacturing that outlines specific data analytics requirements based on the process properties of carbon fibre production. Additionally, it introduces a systematic method for processing trend data. Finally, a case study of polyacrylonitrile (PAN)-based carbon fibre manufacturing exemplifies the concept, giving indications on feature importance and sensitivity related to the expected fibre properties. Future research can build on the comprehensive overview of predictive quality potentials and its implementation concept by extending the underlying data set and investigating the transfer to alternative precursors.

The design and development of composite structures requires precise and robust manufacturing processes. Composite materials such as fiber reinforced thermoplastics (FRTP) provide a good balance between manufacturing time, mechanical performance and weight. In this contribution, we investigate the process combination of thermoforming FRTP sheets (organo sheets) and injection overmolding of short FRTP for automotive structures. The limiting factor in those structures is the bond strength between the organo sheet and the overmolded thermoplastic. Within this process chain, even small deviations of the process settings (e.g., temperature) can lead to significant defects in the structure. A cyber physical production system based framework for a digital twin combining simulation and machine learning is presented. Based on parametric Finite-Element-Method (FEM) studies, training data for machine learning methods are generated and a FEM surrogate is developed. A comparison of different data-driven methods yields information on the estimation accuracy of task-specific data-driven methods. Finally, in accordance with experimental cross tension tests, the investigated FEM surrogate model is able to predict the interface bond strength quality in dependence of the process settings. The visualization into different quality domains qualifies the presented approach as decision support.