Cloud-CT
The increasing complexity in the automotive industry demands new quality assurance methods. Key drivers include CO₂ reduction, functional integration, lightweight construction, new manufacturing processes (e.g., gigacasting, hybrid methods, additive manufacturing), and the avoidance of costly recalls. In all these cases, requirements for non-destructive testing (NDT) are rising. Computed tomography (CT) is particularly well-suited due to its high material and structural resolution. However, current limitations remain in scan time, image quality, automation level, and IT integration.
The goal of the project is to unlock new possibilities for industrial CT through the use of AI-powered reconstruction methods. Focus areas include shortened measurement times via data-reduced scans, improved image quality (e.g., using GANs and Energy-Based Priors), modular software architecture for flexible applications, and cloud-based post-processing enabled by AI-driven data compression. The overall system aims to enable automated, robust quality assessment of large and complex structural components such as transmission housings or battery cells while simultaneously reducing costs and increasing throughput.
Collaborations
Supported by
