Application of Subtractive Clustering for Power Transformer Fault Diagnostics

The issue of developing methods and implementation of hardware and software for power transformer state control is relevant due to the need for enhancing stability and durability of essential expensive equipment. A promising diagnostic condition control technique for the high-voltage oil-filled electrical facilities is the method of positioning partial discharges (PDs) and their intense measuring. The paper provides outcome of experiments enabling acoustic PD positioning at the transformers of the power plant units. It considers the methods and algorithm of processing results of the periodical acoustic PD positioning based on the subtractive clustering technique. These methods provides a fault tracing and identification as well as assessment of their trend.