Research and Application of NSSN Neural Network in Electrical Capacitance Tomography Image Reconstruction

Electrical capacitance tomography (ETC) is a kind of imaging technology which is based on the difference in the sensitivity distribution of capacitance in each medium. In under the background of the ETC system of 12 electrode capacitance sensor arrays an improved NSSN neural network algorithm will be applied to the reconstruction of the image of ECT system in this thesis, and making the ECT image reconstruction algorithm more stable and efficient. In training of the neural network algorithm with large scale, we adopt the method of dividing the sub network to improve it. Through the closed pipeline of gas and solid two-phase flow monitoring data and using the improved neural network image algorithm for image reconstruction. The experimental results show that the improved method makes up for the deficiency of the slow speed of the large scale neural network operation.,simplify the neural network structure, for electrical capacitance tomography provides a new way of thinking.