Design and development of automated systems for the biomedical industry

This thesis is within the Industry 4.0 paradigm, exploring automation solutions in two distinct but complementary manufacturing areas i.e medical diagnostics and advanced therapeutic applications, with the aim of improving the quality and efficiency of processes and reducing human intervention in repetitive tasks. The first project, APROMISE co-funded by the European Regional Development Fund POR CreO FESR 2014-2020 – Tuscany Region, explores the feasibility of implementing an automated machine vision system for the inspection of ultrasound probes produced by Esaote S.p.A. This system exploits convolutional neural networks (CNNs) to automatically analyse probe images, detecting surface defects with high accuracy and reliability, reducing quality control time and ensuring greater uniformity of the finished product. The second project, REPAIR funded by the European Union's Horizon 2020 Research and Innovation Program under Grant Agreement No. 952166, focuses on automating the manufacturing process of liquid crystal elastomers (LCEs), thermo- and photo-sensitive materials that can be used for biomedical applications, particularly as contracting devices for cardiac function support. An automated infiltration cell construction system is proposed to ensure the uniformity and quality of the LCE films produced. Both projects show how the technologies developed can improve traditional production processes, making them more competitive by optimising time, reducing errors and increasing quality standards.