Search

Non-technical losses (NTL) have been a growing problem over the years, causing significant financial losses for electric utilities. Among the methods for detecting this type of loss, those based on Artificial Intelligence (AI) have been the most popular. Many works use the electricity consumption profile as an input for AI models, which may not be sufficient to develop a model that achieves a high detection rate for various types of energy fraud that may occur. In this paper, using actual electricity consumption data, additional statistical and temporal features based on these data are used to improve the detection rate of various types of NTL. Furthermore, a model that combines both the electricity consumption data and these features is developed, achieving a better detection rate for all types of fraud considered. [ABSTRACT FROM AUTHOR]

Dissolved gas analysis of insulating oil in refrigerated power transformer oil is a widespread technique for detecting incipient faults. However, this technique involves safety procedures for the collection of oil samples, laboratory response times and, in some cases, removing the transformer from operation. Removing a transformer from operation in certain situations can become very costly as there are production environments that must run uninterrupted so that stoppages such as this represent financial loss. Infrared thermography is a non-destructive temperature measurement technique commonly used to detect anomalies and predict possible faults without disrupting system operation. This paper presents studies based on the use of infrared temperature measurement to detect incipient faults in transformers through dissolved gas analysis of the insulating oil. This study’s methodology uses intelligent systems to analyse transformer face temperatures and detect incipient faults. The results obtained in this work present 86 and 83% of classification correctness using artificial neural networks and fuzzy logic, respectively. [ABSTRACT FROM AUTHOR]