Dissolved Gas Analysis Principle Based Intelligent Approaches to Fault Diagnosis and Decision Making of Large Oil-Immersed Power Transformers: A Survey

Abstract

Compared with conventional methods in fault diagnosis of power transformers, which have defects such as imperfect encoding and too absolute encoding boundary, this paper systematically reveals various intelligent approaches applied in fault diagnosing and decision making of large oil-immersed power transformers based on dissolved gas analysis (DGA), including expert system (EPS), artificial neural network (ANN), fuzzy theory, rough sets theory (RST), grey system theory (GST), swarm intelligence (SI) algorithms, data mining technology, machine learning (ML), and other intelligent diagnosis tools, and summarizes existing problems and solutions. From this survey, it is found that a single intelligent approach for fault diagnosis can only reflect operation status of the transformer in one certain aspect, causing some shortcomings in various degrees cannot be revealed effectively. Combined with the current research status in this field, the problems that must be addressed in DGA-based transformer fault diagnosis are identified, and the prospects for future development trends and research directions are outlined. This contribution presents a detailed and systematic survey on various intelligent approaches to faults diagnosing and decisions making of the power transformer, in which their merits and demerits are thoroughly investigated, as well as their improvement schemes and future development trends are proposed. Moreover, this paper concludes that a variety of intelligent algorithms should be combined for mutual complementation to form a hybrid fault diagnosis network, such that avoiding these algorithms falling into a local optimum. Moreover, it is necessary to improve the detection instruments so as to acquire reasonable characteristic gas data samples. The research summary, empirical generalization and analysis of predicament in this paper provide some thoughts and suggestions for the research of complex power grid in the new environment, as well as references and guidance for researchers to choose optimal approach to achieve DGA-based fault diagnosis and decision of the large oil-immersed power transformers in preventive electrical tests.

Interpreting dissolved gases in transformer oil: A new method based on the analysis of labelled fault data

“…Large quantities of carbon dioxide and carbon monoxide are produced when thermal faults attack cellulose. Hydrocarbon gases, such as methane and ethylene, are formed if the fault involves an oil‐impregnated structure [7].…”

A new generation of AI: A review and perspective on machine learning technologies applied to smart energy and electric power systems

“…Among these, some classical DL network models have been widely used, including DBN, SAE, CNN, and RNN. These DL networks are mainly used in scenarios such as power equipment fault diagnosis (eg, generators, transformers, and high‐voltage circuit breakers), power system transient stability assessment, power big data integration and anomaly detection, short‐term power load forecasting, electrical equipment image recognition, and intrusion detection in power information networks . For instance, Kim et al established an RNN long short‐term memory (RNN‐LSTM) model for electricity consumption forecasting.…”

“…For instance, the DL discussed in Section combines supervised and unsupervised learning, whose advantage is that the model is highly expressive and can process data with high‐dimensional sparse features . The ANN structure in DL is based on multiple hidden layers (see Figure ); thus, it can automatically extract and understand hidden abstract concepts from the data to some extent . Again, for instance, the TL discussed in Section breaks through the basic assumption required in statistical learning theory (ie, the training dataset and future dataset must obey the same probability distribution; otherwise, the effect cannot be guaranteed); thus, the data from the original domain and the target domain are not required to obey the same probability distribution; they can even come from different feature spaces.…”

Smart dispatching for energy internet with complex cyber‐physical‐social systems: A parallel dispatch perspective

“…However, we have to confront the fact that multiple energy networks in the field of EI are increasingly interconnected along with massive distributed new energy resources access to the power grid . As a result, the pure power system EMS has been gradually transformed into forms of a comprehensive EMS (CEMS) in which multiple energy networks (eg, electric power, gas, heating, cold, and energy storage) are largely interconnected and coupled in a complementary manner.…”

“…Actually, as elaborated in Section , we have made some attempts to employ the Q‐matrix used in reinforcement learning (RL) algorithms (eg, Q‐learning algorithm) to a Markov decision process (MDP) over the past few years, with the aim of achieving value function storage in an intermediate process of optimization and decision making . In this aspect, we have achieved a satisfactory effect in optimization acceleration.…”