TY - JOUR A2 - Li, Lianhui AU - Li, Bin AU - Zhang, Xuejun AU - Ban, Yanjiao AU - Xu, Xianfu AU - Su, Wenjun AU - Chen, Jingxian AU - Zhang, Shan AU - Li, Feng AU - Liang, Zuopeng AU - Zhou, Shengkai PY - 2022 DA - 2022/10/07 TI - Construction of a Smart Supply Chain for Sand Factory Using the Edge-Computing-Based Deep Learning Algorithm SP - 9607755 VL - 2022 AB - The diminishing natural sand has facilitated the booming of the sand manufacturing industry, and intelligent management of sand factories, in a time- and cost-efficient way, has become a growing tendency for the future. A role has been played in achieving intelligent management by constructing a smart supply chain. However, the smart sand factories are hardly involved in previously reported studies, which is inconsistent with related studies on smart factories and the Industrial Internet of Things (IIoT). In this paper, a smart supply chain management system (SSCMS) is constructed to realize the intelligence and automatization of the management of sand factories, using edge-computing and deep learning techniques. Along the supply chain, the deep learning model is used to realize the automatic identification of sand, avoiding the disadvantages of human identification, while improving the quality of sand factory operations. In order to relieve the pressure of network bandwidth, reduce system delay, and improve system operation efficiency, we use edge-computing technology to process data at the edge. To verify the performance of the constructed system, a sand factory simulation platform is established. Experiments show that the most critical indicator in the system, the accuracy rate of sand type identification, is above 98%, and the sand type identification time is only 0.022 s. In general, compared with traditional supply chain management, the constructed smart supply chain improves the quality and efficiency of sand factory operations, and all indicators of the designed system have achieved satisfactory results. SN - 1058-9244 UR - https://doi.org/10.1155/2022/9607755 DO - 10.1155/2022/9607755 JF - Scientific Programming PB - Hindawi KW - ER -