Defect Detection of Adhesive Layer of Thermal Insulation Materials Based on Improved Particle Swarm Optimization of ECT

Abstract

This paper studies the defect detection problem of adhesive layer of thermal insulation materials. A novel detection method based on an improved particle swarm optimization (PSO) algorithm of Electrical Capacitance Tomography (ECT) is presented. Firstly, a least squares support vector machine is applied for data processing of measured capacitance values. Then, the improved PSO algorithm is proposed and applied for image reconstruction. Finally, some experiments are provided to verify the effectiveness of the proposed method in defect detection for adhesive layer of thermal insulation materials. The performance comparisons demonstrate that the proposed method has higher precision by comparing with traditional ECT algorithms.

A Novel Computational Imaging Algorithm for Electrical Capacitance Tomography

“…The image reconstruction process of the ECT is ( ) The training sample set between the capacitance correlation coefficient and the imag ing target is obtained through numerical simulation or experiment. (2) The mapping model between the capacitance correlation coefficient and the imaging target is obtained by the RELM method. (3) The capacitance correlation coefficient corresponding to the measured capacitance value is calculated.…”

“…ECT is a growing research topic, with advantages such as its wide range of applications, non-invasiveness, fast response time, high security performance, low cost, etc. It is widely used in the multiphase flow process detection of insulating media [1][2][3][4], such as monitoring flames and combustion conditions in engine combustion chambers, defect detection of thermal protection materials, measuring solid concentration in cyclone separator, pneumatic measurement of high pressure pulverized coal, etc.…”

“…(1) The implementation of the algorithm mainly consists of two stages: at the learning stage, according to the training sample set, the RELM model between capacitance correlation coefficient and imaging target is extracted; at the prediction stage, by taking the calculated capacitance correlation coefficient as the input of the RELM model, the corresponding reconstructed image can be predicted. (2) The solution method of the capacitance correlation coefficient is analyzed in detail.…”