The high voltage insulator requires continuous monitoring and inspection to prevent failures and emergencies. Manual inspections are costly as it requires covering a large geographical area where insulators are often subjected to harsh weather conditions. Automatic detection of insulators from aerial images is the first step towards performing real-time classification of insulator conditions using Unmanned Aerial Vehicle (UAV). In this paper, we provide a cost-effective solution for detecting insulators under the conditions of an uncluttered background, varied object resolution and illumination conditions using You Only Look Once (YOLO) deep learning neural network model from aerial images. We apply data augmentation to avoid overfitting with a training set size of 56000 image samples. It is demonstrated experimentally that this method can accurately locate insulator on UAV based real-time image data. The detected insulator images are then successfully subjected to insulator surface condition assessment for the presence of ice, snow and water using different classifiers.

An important application in the growing field of unmanned aerial vehicles (UAVs) is in monitoring and inspection of high voltage power lines and electrical networks. The UAV-based monitoring method will save energy, simplify access to impassable or remote areas, reduce inspection cost, and automate the inspection process. However, the battery capacity of a medium scale drone limits their travel distance and mission duration. It is crucial to improve the energy feeding system of drones and overcome the battery capacity problem to foster the use of drones for routine monitoring operations. In this study, we focus on presenting wireless techniques available for drone mission duration improvement as well as discuss and practically examine the most feasible and reliable technique to charge UAV using power lines.

As a response to rapidly increasing penetration of wind power generation in modern electric power grids, accurate prediction models are crucial to deal with the associated uncertainties. Due to the highly volatile and chaotic nature of wind power, employing complex intelligent prediction tools is necessary. Accordingly, this paper proposes a novel improved version of empirical mode decomposition (IEMD) to decompose wind measurements. The decomposed signal is provided as input to a hybrid forecasting model built on a bagging neural network (BaNN) combined with K-means clustering. Moreover, a new intelligent optimization method named ChB-SSO is applied to automatically tune the BaNN parameters. The performance of the proposed forecasting framework is tested using different seasonal subsets of real-world wind farm case studies (Alberta and Sotavento) through a comprehensive comparative analysis against other well-known prediction strategies. Furthermore, to analyze the effectiveness of the proposed framework, different forecast horizons have been considered in different test cases. Different error assessment criteria were used and the obtained results demonstrate the superiority of the proposed method for wind forecasting compared to other methods for all test cases.

On-line monitoring and diagnosis of transformers have been investigated and discussed significantly in last decade. This study has concentrated on issues arising while on-line transformer winding deformation diagnosis is going to be applied on transformers with various kinds of techniques. From technical perspective, before replacing off-line methods by on-line methods and eventually by intelligent approaches, practical challenges must be addressed and overcome. Hence, available off-line transformer winding deformation diagnosis methods are discussed precisely. Mathematical calculation in on-line short circuit impedance measurement is investigated. On-line transformer transfer function measurement setup is presented. A profound insight to the problems pertaining on-line transformer winding deformation recognition methods, characterizes existing online methods, explains the concepts behind online measurements and striving to open the discussion doors towards challenges are discussed. In the end a 400 MVA step up transformer has been taken as a case in order to clarify the capability of Frequency Response Analysis (FRA) method in fault detection while short circuit impedance could only demonstrate some rough understanding about transformer condition.

Power transformers are in service under different environmental, electrical, and mechanical conditions [1] and may be subject to enormous hazards during the course of operation [2], [3]. They are commonly considered to be the heart of the transmission and distribution sectors of electric power systems; monitoring their condition and diagnosing faults are important parts of the maintenance function [4]. Utility engineers strive to keep power transformers in service and to prevent even shortterm outages. Failure of a transformer can cause extensive damage to equipment owned by consumers or the utility [5].

On-line monitoring and diagnosis of transformers have been investigated and discussed significantly in the last few decades. Vibration method is considered as one of the non-destructive and economical methods to explore transformer operating condition and evaluate transformer mechanical integrity and performance. However, transformer vibration and its evaluation criteria in transformer faulty condition are quite challenging and are not yet agreed upon. At the same time, with the advent of IoT facilities and services, it is expected that classical diagnosis techniques will be replaced with more powerful data-driven prognosis methods that can be used efficiently and effectively in smart monitoring. In this paper, we first discuss in detail an analytical approach to the transformer vibration modeling. Nevertheless, precise interpretation of transformer vibration signal through analytical models becomes unrealistic as higher harmonics are mixed with fundamental harmonics in vibration spectra. Therefore, as the next step, we aim to support the Industry 4.0 concept by utilizing the state-of-the-art machine learning and signal processing techniques to develop prognosis models of transformer operating condition based on vibration signals. Transformer turn-to-turn insulation deterioration and short circuit analysis as one the most important concerns in transformer operation is practically emulated and examined. Along with transformer short-circuit study, transformer over and under excitations are also studied and evaluated. Our constructed predictive models are able to detect transformer short-circuit fault in early stages using vibration signals before transformer catastrophic failure. Real-time information is transferred to the cloud system and results become accessible over any portable device.