Application Of Sensor Position Reconstruction And Multi-objective Algorithm In EMT Image Reconstruction

Electromagnetic Tomography (EMT) appeared in the 1990s, based on the principle of electromagnetic induction and electromagnetic theory. EMT is mainly used to study the distribution of matter with electromagnetic properties in space. EMT technology has the advantages of non-intrusive, no contact, simple structure and no harm, no artificial in the field measurement and get remote image. Therefore, it has the very strong technical advantages in future production of industrial process. After more than 20 years of efforts to study the research team. While this technology is not very mature, there are still some problems need to be solved.After consulting a large number of literatures at home and abroad, due to the effect of sensor projection data is too little and image reconstruction algorithm on EMT image reconstruction, a multi position sensor data fusion technique and an improved multi-objective optimization algorithm are presented in this paper, and applied to the EMT system for image reconstruction simulation design. This paper mainly completed the following work:1?It describes the basic theory of EMT system is described in detail. EMT system is simulation modeling and analysis problems by applying the finite element method (fem) in software COMSOL.2?For the image reconstruction of electromagnetic tomography, due to the effect of sensor projection data is too little, a data fusion method for the location of the sensor is proposed in this paper. Image distortion can be achieved when the measured object field is not completely detected. In order to avoid this effect, then the sensor detecting coil position is measured again after rotate 22.5°to obtain more information about the field. Thus the system error of EMT system is compensated, and the precision of image reconstruction is improved.3?In order to improve the precision of the reconstruction image, an improved multi-objective optimization algorithm for image reconstruction of EMT. Firstly, the basic principle of multi-objective optimization algorithm is described in detail, and an improved multi-objective optimization algorithm combined with the neural network algorithm is obtained. According to the theory of EMT technology, the mathematical model of image reconstruction is established. After the sensor is reconstructed, the image is reconstructed by using the improved multi-objective optimization algorithm, then, image fusion. The image error caused by the too little sensor projection data is compensated, the precision of image reconstruction is improved.Finally, the simulation experiment is carried out, the simulation results show that, The sensor location and the improved multi-objective optimization algorithm used in EMT image reconstruction algorithm, the quality of reconstructed image is improved obviously. Compared with the traditional method, the relative error and the correlation coefficient are improved. This shows that the proposed method is feasible and effective, it also provides a new way and means for the research of EMT image reconstruction technology.