Coal slime flotation is crucial to improve the utilization rate of coal resources and reduce environmental pollution. However, the existing flotation foam image processing systems based on wired communication brings insufficient computational resources, poor scalability and high capital expenditure. In this paper, we propose a two-stage coal flotation foam image processing system based on 5G Industrial Internet of Things (IIoT) and edge computing. In the first stage, i.e., task offloading stage, we exploit Lyapunov optimization to decompose the coupling between long-term constrains and short-term decisions. A matching theory-based task offloading algorithm is proposed to maximize the average network throughput. In the second stage, i.e., image processing stage, we employ gray level histogram and gray level co-occurrence matrix (GLCM) to extract the texture feature parameters of the coal slime flotation foam image. On that basis, we present an ash value prediction algorithm based on multiple linear regression. Finally, extensive simulations are carried out to verify the reliability, feasibility and efficiency of the proposed task offloading algorithm and ash value prediction algorithm.
No takes yet. Share an insight, caveat, or question.
Yateng Bai (2020) studied this question.