Optimization of Ship-borne Anti-collision Sounding System Based on Internet of Things and Full Convolution Neural Network

Abstract

Shu, J.; Deng, M., and He, J., 2020. Optimization of ship-borne anti-collision sounding system based on Internet of Things and full convolution neural network. In: Yang, Y.; Mi, C.; Zhao, L., and Lam, S. (eds.), Global Topics and New Trends in Coastal Research: Port, Coastal and Ocean Engineering. Journal of Coastal Research, Special Issue No. 103, pp. 757–761. Coconut Creek (Florida), ISSN 0749-0208.The traditional ship-borne anti-collision sounding system has low resolution of detection image and collision of detection signals, which affects the accuracy of detection results. For this reason, this paper combines the Internet of Things and full convolution neural network method to optimize the ship-borne anti-collision sounding system. The resolution of detection image is improved by full convolution neural network method. On the basis of the above, the modular reconstruction of anti-collision sounding system is carried out. The system takes STM32F103 VET6 embedded chip as the control core of the system, uses CC2530 to implement ZigBee wireless network communication, and integrates ZigBee wireless communication technology and embedded technology. Now anti-collision and bathymetry function, aiming at the problem of signal collision of each node in wireless network, anti-collision algorithm is introduced to optimize the system, to prevent signal collision when receiving, and to ensure the synchronization and accuracy of the whole system. Experiments show that the system has the advantages of low energy consumption, fast response and high accuracy.