Simulation Line Design Using BP Neural Network

The simulation line is usually used to imitate the frequency characteristic of a real long transmission line. This paper proposes a novel design scheme of simulation line using back propagation neural network (BP NN). A BP NN is trained to correspond with the line’s transfer function and then implemented by field programmable gate array (FPGA) for application in real time. The activation function of NN is approximated with a high-speed symmetric table addition method (STAM), which reduces the amount of memory required. For an underwater coaxial cable that is 10000m long, a simulation line is hardware realized and has been successfully used in the study of digital image transmission.