Automatic Sorting System for Wood Diameter Grades

Abstract

Wood is one of the energy sources for sustainable development, which is closely related to our life. In the wood production process, it will be sorted according to different diameter grade is an essential link, at present the wood sorting work mainly rely on manual completion, not only low efficiency, high cost, and can not meet the automated era of production needs. In this paper, a wood diameter level automatic sorting system is designed, first of all, using computer vision technology to measure the diameter of the wood section in real time, then the diameter data is transmitted to the PLC control system, and finally the PLC control system pushes out the wood in the specified position, realizing the automated on-line sorting of wood. In addition, a wood diameter measurement method based on deep learning combined with binocular vision is proposed, which can quickly and accurately recognize the diameter of each piece of wood, and provides a solid foundation for the efficient performance of the automatic wood diameter grade sorting system. The experimental results show that the measurement method proposed in this paper has high robustness and the maximum error is within 5mm, which meets the accuracy requirements needed for sorting, and the sorting system can sort 10 pieces of wood per minute on average, which greatly improves the efficiency of wood sorting and reduces the labor workload and cost, and the research design is of great significance to the wood production and manufacturing industry.