Condition Assessment of Power Transformers through DGA Measurements Evaluation Using Adaptive Algorithms and Deep Learning

Condition assessment for critical infrastructure is a key factor the wellbeing of modern human. Especially electricity network, specific components such as oil-immersed power transformers need to be monitored their operating condition. Classic approaches condition have been proposed in past, dissolved gases analysis and respective concentration measurements insulating oils. However, these cannot always correctly (and many cases not at all) classify problems transformers. In last two decades, novel are implemented so address this problem, including artificial intelligence with neural networks being one form algorithm. This paper focuses on implementation an adaptive number layers networks, aiming increase accuracy also compares use various activation functions different transfer other than network implemented. The comparison incorporates total structure size network.