A power transformer is one of the most critical and expensive assets in electric power systems. Failure of a power transformer would not only result in a downtime to the entire transmission and distribution networks but may also cause personnel and environmental hazards due to oil leak and fire. Hence, to enhance a transformer’s reliability and extend its lifespan, a cost-effective and reliable condition monitoring technique should be adopted from day one of its installation. This will help detect incipient faults, extend a transformer’s operational life, and avoid potential consequences. With the global trend to establish digital substation automation systems, transformer online condition monitoring has been given much attention by utilities and researchers alike. Several online and offline condition monitoring techniques have been recently proposed for oil-immersed power transformers. This paper is aimed at providing a state-of-the-art review for the various condition monitoring technologies used for oil-immersed power transformers. Concept of measurements and analysis of the results along with the future trend of condition monitoring techniques are presented.

Frequency response analysis (FRA) has become a widely accepted technique by worldwide utilities to detect winding and core deformations within power transformers. The main drawback of this technique is its reliance on the personnel level of expertise more than standard or automated codes. To establish reliable FRA interpretation codes, accurate high frequency transformer model that can emulate the frequency characteristics of real transformers in a wide frequency range is essential. The model can be used to investigate the impact of various winding and core deformations on the transformer FRA signature. The transformer equivalent high frequency electric circuit parameters can be calculated based on design data, which are rarely available, especially for old transformers. As such, this paper presents an artificial intelligence technique to estimate these parameters from the transformer FRA signature. The robustness of the proposed technique is assessed through its application on three, 3-phase power transformers of different ratings, sizes, and winding structures to estimate their high frequency electric circuit parameters during normal and fault conditions. Results show that the proposed technique can estimate equivalent circuit parameters with high accuracy and helps interpret the FRA signature based on the numerical changes of these parameters. The main advantage of this approach is the physical meaning of the model parameters facilitates reliable identification of various faults and hence aids in establishing reliable interpretation codes for transformer FRA signatures.

Reliable operation of oil-immersed power transformers is crucial for electrical transmission and distribution networks. However, the aging of high voltage assets including power transformers along with the increasing of load demand have heightened the importance of adopting cost-effective asset management strategies. Dissolved gas analysis (DGA) has been recognized as a valuable diagnostic tool for detecting potential faults and monitoring the condition of oil-immersed power transformers. Traditional offline DGA method involves periodic sampling and laboratory analysis, which often results in delayed detection and response to emerging faults. To address these limitations, online DGA approach has been emerged to provide real-time monitoring and continuous data acquisition. This paper presents a new asset management approach for mineral oil-immersed power transformers by analysing the online DGA data using convolutional neural networks. The proposed approach provides real time solutions to classify emerging fault type and predict transformer health deterioration level with high accuracy. Results show that the accuracy of fault diagnostics of the proposed approach is approximately 87%.

Accurate short-term load forecasting (STLF) is essential for power grid systems to ensure reliability, security and cost efficiency. Thanks to advanced smart sensor technologies, time-series data related to power load can be captured for STLF. Recent research shows that deep neural networks (DNNs) are capable of achieving accurate STLP since they are effective in predicting nonlinear and complicated time-series data. To perform STLP, existing DNNs use time-varying dynamics of either past load consumption or past power correlated features such as weather, meteorology or date. However, the existing DNN approaches do not use the time-invariant features of users, such as building spaces, ages, isolation material, number of building floors or building purposes, to enhance STLF. In fact, those time-invariant features are correlated to user load consumption. Integrating time-invariant features enhances STLF. In this paper, a fuzzy clustering-based DNN is proposed by using both time-varying and time-invariant features to perform STLF. The fuzzy clustering first groups users with similar time-invariant behaviours. DNN models are then developed using past time-varying features. Since the time-invariant features have already been learned by the fuzzy clustering, the DNN model does not need to learn the time-invariant features; therefore, a simpler DNN model can be generated. In addition, the DNN model only learns the time-varying features of users in the same cluster; a more effective learning can be performed by the DNN and more accurate predictions can be achieved. The performance of the proposed fuzzy clustering-based DNN is evaluated by performing STLF, where both time-varying features and time-invariant features are included. Experimental results show that the proposed fuzzy clustering-based DNN outperforms the commonly used long short-term memory networks and convolution neural networks.

Frequency response analysis (FRA) plays an important role in the assessment of the mechanical integrity and hence, reliability of high-voltage power transformers. Wireless power transfer (WPT) system introduced by Tesla a 100 years ago based on Faraday's law of electromagnetic induction is similar to a conventional power transformer. Therefore, the reliability of a large WPT system can also be evaluated using FRA measurement. When the WPT system is constructed, the electrical components and the desired transfer distance need to be ascertained accurately. Furthermore, the structure of the winding and the electrical characteristic of the components in WPT systems may vary due to aging or fault events. FRA measurement can examine the discrepancy between the WPT system parameters and the reference fingerprint data to provide cost-effective condition monitoring-based maintenance scheme for the WPT systems. This paper presents a detailed circuit analysis of a two-coil inductively coupled WPT model in different compensating topologies to accomplish efficient energy transfer. Then, FRA measurement is used to detect the variation in the amplitude and the phase angle of the developed circuit input impedance in a wide frequency range. In addition, displacements due to the placement of ferrite material and the variation of the transfer distance between the transmitter and receiver units are investigated through practical measurements.

Solving combined economic emission dispatch (CEED) problem optimizes power generation by balancing cost minimization with emission reduction, addressing economic and environmental goals simultaneously. This trade-off results in a Pareto front, where each non-dominated solution represents an optimal balance between costs and emissions. Decision-makers can select solutions based on their preferences. This paper proposes an Epsilon-based multi-objective genetic algorithm (MOGA) to solve the CEED problem. By integrating evolutionary techniques and Epsilon constraint methods, the proposed method actively explores diverse solutions, avoiding local optima and enhancing the Pareto front. The two-objective CEED problem is reformulated into two single-objective problems, alternately minimizing cost or emissions. The Epsilon constraint algorithm accelerates the search for optimal solutions. Two quality indicators are proposed to evaluate the Pareto fronts. The first indicator measures solution spread; it assesses the diversity of generator settings and the dominated volume. The second indicator evaluates the uniformity of solution distribution, where smaller distances indicate better uniformity. High spread and uniform distribution signify superior Pareto fronts. If diversity is insufficient, the proposed Epsilon-based MOGA continues to refine the front. The performance of the proposed method was tested on IEEE 30-bus and 118-bus systems, showing improved results compared to RNSGA-II, the Epsilon constraint algorithm, and NSGA-II. The proposed method produced more diverse and uniformly distributed non-dominated solutions; it offers grid operators a broader range of options to balance costs and emissions. Additionally, it achieved lower costs and emissions. The computational time for the larger IEEE 118 system is manageable and does not increase exponentially compared to the smaller IEEE 30 system.