Pollution flashover is a serious accident with a wide range of impacts in power grid. Accurate and timely classification of pollution severity is both a key to preventing pollution flashovers and a crucial challenge. This paper proposes an innovative method based on PTR and MCS3VM for classification of insulator pollution severity. The introduction of time-dimension information makes it possible to achieve pixel-level image identification instead of image or region-level image identification. The PTR physical model for pollution severity measurement is established. The relevant features are extracted by using PCA. A semi-supervised classifier is proposed to solve the problem of poor generalization due to insufficient labeled samples in industrial applications. Experimental results verify the satisfactory efficiency and accuracy of the proposed method and an estimation framework for fast, accurate and nondestructive industrial application without tedious work of labeling large amounts of data is concluded.

The defect classification task is of great benefit to evaluating the safety performance of equipment and providing useful feedback information for discovering production process problems. In this article, we present a semisupervised learning (SSL) framework for transient thermography detection to employ the temporal and spatial information encoded into the three-dimensional transient thermal tensor data and provide pixel-level classification results for defect types. The time- and frequency-domain physical models for the transient thermal evolution of different kinds of defects are established to illustrate the theoretical foundation of defects classification based on transient thermography. The semisupervised multiclass Laplacian support vector machine is proposed to enable involving the abundant unlabeled data for enhancing learning performance in practical industrial applications where labeled samples are insufficient and labeling work is costly and laborious. A case study on silicone insulating materials with various types of artificial simulated internal defects validates the stronger generalized ability of the proposed method. This work, for the first time, proposes an SSL framework in transient thermography-based defect detection studies. It is believed that our proposed method is quite inspired for introducing SSL techniques to transient thermography for preferable performance in practical industrial applications.

This work introduces differential evolution fitting-based optical step phase thermography for fast, contactless, and high-accurate measurement of micron thickness, which is widely needed in industrial applications. In this process, frequency-domain characteristics of thermal wave propagation are extracted to estimate micron thickness. The relationships between several frequency-domain features and thickness to be measured under different sampling frequency are discussed. The effect of sampling frequency is emphasized for measuring micron thickness and improving the sensitivity of the frequency-domain features as measurement tools of thickness. In particular, differential evolution is introduced to implement adaptive global optimization of transient thermal responses fitting and eliminate the frequency aliasing in micron thickness measurement when the sampling frequency is not satisfactory. Finally, experimental studies have been conducted to compare the effectiveness of principle component analysis, independent component analysis, and the proposed method for quantitative evaluation of atmospheric corrosion.

Nondestructive testing and evaluation of composite insulating components of electrical equipment is extremely necessary for assuring the safety of a power system. However, most existing nondestructive testing methods are not applicable for fast and effective live detection due to their time-consuming operation, high cost, and contact or near-field measurement. In this work, the effectiveness of active infrared thermography was investigated for detecting defects in silicone rubber (SIR)–fiber-reinforced plastic (FRP) bonding structures, which have been commonly used in insulating components of power equipment. The effectiveness of differential thermal image for enhancing the contrast of defective and sound areas and eliminating additive noise was demonstrated. Particularly, frame difference thermal image obtained by subtracting two differential thermal images extracting from respectively before and after the contrast inversion was proposed to enhance defect identification. The results revealed that defects of various sizes and depths such as voids, cracks, and interface disbonding of the SIR–FRP bonding structure were accurately detected by thermographic data. With the advantages of a quick and simple process, safety, universal applicability, visual results, far-field measurement, and quantitative defect estimation capabilities, active infrared thermography would be quite promising for live detection of electrical equipment.