For the underground cable temperature monitoring problem,this paper proposes a distributed Raman temperature sensing system based on convolutional neural network,because the Raman scattered light is very weak,so the signal-to-noise ratio of this system has a great impact on the system performance,and how to effectively remove the noise is now become a key problem in this field.Some traditional denoising methods need to adjust the hardware of the traditional sensing system,and some consume longer time and are inflexible,all of which cannot achieve the denoising function better and conveniently.In this paper,it proposes to use Convolutional Neural Network to learn a large amount of simulation data,and then validates the trained model with simulation da-ta and real data.Experiments show that the noise removal algorithm based on Convolutional Neural Network can effectively re-move the noise of distributed Raman temperature sensing system.
万方数据
