Electrical capacitance tomography and parameter prediction based on particle swarm optimization and intelligent algorithms

Electrical capacitance tomography is an industrial process tomography technology, mainly used to measure and plot two-phase flow and multi-phase flow. The technology is based on the properties of various dielectric constants between the phases of the measured substance. This work focuses on the improvement of particle swarm optimization and intelligent algorithms, especially for the parameter control of particle swarm optimization and intelligent algorithms. The efficiency of group optimization algorithms and intelligent algorithms that solve optimization problems. This paper mainly aims at the image reconstruction process in electrical capacitance tomography system, and proposes an image reconstruction algorithm based on intelligent algorithm and particle swarm algorithm. Combined with the experimental environment of the self-made electrical capacitance tomography system, the actual imaging effect of the algorithm was compared and analyzed with the traditional imaging algorithm, and the verification of the algorithm improvement effect was theoretically completed. According to the finite element analysis method, the internal area of the sensor is subdivided on the entire network, and three flow modes are modeled, which provides conditions for the construction of the following experimental environment. Based on the theory, the principle of the classic Landweber imaging algorithm is discussed in detail. Using the experimental environment with built-in electrical capacitance tomography system, experiments were conducted to visualize the gas–liquid two-phase flow. The traditional Landweber algorithm and imaging algorithm proposed in this paper are used to reconstruct the image using the obtained volume data. Through comparative analysis of the resulting images, the results show that the imaging algorithm proposed in this paper improves the accuracy of flow pattern recognition and image accuracy, which proves the improvement. The feasibility of algorithm and particle swarm algorithm.