Neural-network-based Generalized Filter for Inter-channel Nonlinear Compensation in Long-haul Optical Transmission

2021 ◽  
Author(s):  
Zhiyuan Yang ◽  
Yiwen Wu ◽  
Hexun Jiang ◽  
Mengfan Fu ◽  
Lilin Yi ◽  
...  
Keyword(s):  
Neural Network ◽  
Optical Transmission ◽  
Nonlinear Compensation

Nonlinear Compensation Method for Transducer Based on Neural Network with Fourier Functions

2012 ◽  
Vol 220-223 ◽  
pp. 1843-1847
Author(s):  
Nan Lan Wang ◽  
Ming Shan Cai
Keyword(s):  
Neural Network ◽  
Fourier Series ◽  
Compensation Method ◽  
Measured Temperature ◽  
Temperature Transducer ◽  
Model Based ◽  
Basic Functions ◽  
Thermistor Temperature ◽  
Nonlinear Compensation

Aiming to solve the problems in the non-linearity of thermistor temperature transducer, a compensate model based on neural network (NN) is proposed. The basic idea is using Fourier series as the basic functions of NN，the output of transducer as input samples of NN and the temperature as the expectation output of NN. The output of NN is used to approximate to the measured temperature by adjusting the weights. The results show the proposed method is effective in raising accuracy.

Application of General Regression Neural Network in Characteristic Curve Fitting of Optical Fiber Micro-Bend Sensor

2013 ◽  
Vol 441 ◽  
pp. 116-119 ◽  
Author(s):  
Shuo Ding ◽  
Xiao Heng Chang ◽  
Qing Hui Wu
Keyword(s):  
Neural Network ◽  
Optical Fiber ◽  
Characteristic Curve ◽  
New Method ◽  
General Regression Neural Network ◽  
Small Scale ◽  
Training Samples ◽  
Nonlinear Compensation ◽  
General Regression ◽  
Bend Sensor

In order to reflect the input and output features of an optical fiber micro-bend sensor, a new method using general regression neural network (GRNN) to fit the characteristic curve is proposed in this paper. First, the measuring principle of optical fiber micro-bend sensor and the principle of GRNN are introduced. Then, to verify the feasibility and effectiveness of this new method, a comparison between two kinds of fitting methods is done. One is based on GRNN, the other is based on Levenberg-Marquart improved BPNN. The results of the simulation experiment show that with the same number of training samples and for small scale to medium scale networks, compared with BPNN, GRNN has smaller error, faster convergence speed and higher fitting accuracy. So the method discussed in this paper provides a reliable basis for the nonlinear compensation problem of optical fiber micro-bend sensor.

Neural Network Assisted Geometric Shaping for 800Gbit/s and 1Tbit/s Optical Transmission

2020 ◽  
Author(s):  
Maximilian Schaedler ◽  
Stefano Calabrò ◽  
Fabio Pittalà ◽  
Georg Böcherer ◽  
Maxim Kuschnerov ◽  
...  
Keyword(s):  
Neural Network ◽  
Optical Transmission
Sign in / Sign up

Export Citation Format

Share Document