Speaker
Description
The increasing complexity of modern manufacturing systems requires companies to design and develop a contemporary framework with high degree of accuracy and speed. The demand for precise and fast equipment in wood processing and other industries is topical within modern progress of Machine Learning, more powerful computing systems and approaches. To meet this challenge and to be in pace with Industry 5.0 advancements they rely heavily on real-time systems, which are essential tools for assessing dynamics of manufacturing data. In the paper, the research project focuses on developing an advanced 3D and line-scanning camera system concept for real-time wood defect detection and labelling. High-performance computing (HPC) technologies and FPGA-based (Field-Programmable Gate Array) for real-time processing will be employed to ensure high scanning speed and precision. Additionally, the research will focus on creating the necessary computing algorithms and a set of diagnostic, calibration, and maintenance technologies to optimize the performance and reliability of the scanning system. As the critical step for framework elaboration, the development of a conceptual model for the camera system and evaluation of technological options that would ensure effective recognition of wood defects, as well as creation of a basis for further technological development are performed.