The invention relates to an insulation health state evaluation method of a dry type
transformer for a
coal mine underground power supply
system. According to the method, evaluation is carried out based on monitoring quantity determining, feature quantity extraction, feature quantity
processing, fault diagnosis, health state evaluation,
database establishment and state early warning-based multi-information source fusion; the development degree of an insulation local defect is monitored through using the change laws of related feature quantities in a
discharge evolution process of the insulation defect; and diagnosis of the risk of the insulation local defect is realized based on a
particle swarm optimization algorithm-based
support vector machine, so that a comprehensive
evaluation result of the overall health state and insulation local deterioration degree of the dry type
transformer can be obtained. According to the method of the invention, corresponding
variable weight values are assigned for the feature quantities, and therefore, high applicability and high judgment accuracy can be realized, early, accurate and quick prediction of potential faults and identification of fault types can be benefitted, the operating state and possible defect development trend of the
transformer can be comprehensively evaluated, and the reliability and continuity of the operation of the transformer can be improved.