As an onsite condition monitoring method, infrared inspection can help to discover and analyze abnormal temperature increases in power equipment. To improve the efficiency of onsite diagnosis of insulators in substations, this paper proposes an automatic diagnosis method using instance segmentation and temperature analysis of infrared insulator images. To develop this method, thousands of infrared images from field inspection databases were collected to establish an annotated data set of insulator images. With the aid of Mask R-CNN it was possible to extract multiple insulators automatically in the infrared images. Transfer learning as well as the dynamic learning rate algorithm were then employed to realize the training process of Mask R-CNN with the annotated image data set. The result of the testing experiment showed that the mAP of the model is 0.77 and the FPS is 5.07, which indicated great identification accuracy and computing speed of the proposed model. Next, function fitting was realized to extract the temperature distribution of each insulator. Finally, to evaluate the condition of each insulator, rules, which are based on the related standards, were established using machine language. This is the first time that the machine could independently realize fault analysis of multiple insulators in the infrared images, which is a great attempt to adapt the development of the Internet of Things and the tendency of predictive maintenance. Moreover, because of the universality of the model algorithm used, automatic infrared fault diagnosis for other power equipment could also be performed in a similar manner, which has significant potential applicability in the area of power equipment diagnosis.

Insulator diagnostics is still a topical issue. No one has yet found out how to accurately determine the condition of all insulators and decide when replacement or maintenance is required. Insulators are one of the main components of a transmission and distribution system and must withstand high voltages in all weather conditions. Moisture and dirt are the main factors influencing the insulating properties of insulators. This article deals with the effect of pollution on a porcelain insulator. An Omicron MI 600 measuring system monitors the changes in the dielectric loss factor and leakage current in a wide frequency range (10 Hz to 1 kHz) to evaluate the contamination level. We applied three high voltage levels (5 kV, 7.5 kV, and 10 kV) to the porcelain insulator to monitor changes in the mentioned quantities with various frequencies. The measurement results confirmed the usability of the dielectric loss factor and leakage current for the diagnosis of insulator pollution. The dielectric loss factor showed more promising results than the leakage current.

Converting an AC circuit of an existing multi circuit overhead line (OHL) to DC is a promising solution to increase the OHL’s transmission capacity. This is called a "hybrid OHL". Because of the small distances, electromagnetic coupling occurs between the AC and DC circuits. This influences conductor surface gradients, which in return affects corona effects such as audible noise (AN). In this contribution, a case study regarding a fictive Indonesian hybrid OHL is used to present AC surface gradient calculations under DC influence. Furthermore, results from laboratory experiments are presented. The aim of the experiments was to explore the AN behavior of AC lines under DC influence. Additionally, the performance of noise reducing surface treatments under hybrid conditions has been investigated. The gathered results show that an AC line’s corona behavior worsens substantially under DC influence. Surface treatments, however, seem to retain their noise reducing effects even under hybrid influences.