Abstract: The present invention provides a method for generating a decision tree for determining the type of an internal abnormality of an oil-filled electric apparatus using a computer. In the decision tree generation method, the computer generates a standardized data group by converting concentrations of a plurality of gas species dissolved in an insulating oil in an oil-filled electric apparatus into ratios for each abnormality case, generates a discretized data group by converting the ratios of the concentrations of the gas species, the ratios constituting the standardized data group, into a plurality of discretized attributes using predetermined thresholds which are set for the respective gas species, and generates a decision tree for determining the type of an internal abnormality of the oil-filled electric apparatus by analysis using specific formulae on the basis of the discretized data group.

Abstract: An in-oil gas concentration measuring system comprises: gas extracting which extracts an in-oil gas from an insulating oil sample; component detecting which detects gas components of the in-oil gas extracted by the gas extracting; extracted-gas concentration calculating which calculates, on the basis of data detected by the component detecting, extracted-gas concentrations of the gas components being detected; extracted-gas concentration storing which stores information on the extracted-gas concentrations calculated by the extracted-gas concentration calculating as a result of two or more extractions performed by the gas extracting, the information being stored in each of the extractions; and in-oil gas concentration calculating which calculates in-oil gas concentrations of the gas components on the basis of the extracted-gas concentrations thus stored in the extracted-gas concentration storing.

Abstract: An object is to provide an internal abnormality diagnosis method, an internal abnormality diagnosis system and a decision tree generation method for internal abnormality diagnosis of an oil-filled electric apparatus utilizing gas concentration in oil and having a diagnostic accuracy equal to or higher than that of a diagnostic specialist having reached a certain level. The present invention provides a method for generating a decision tree for determining the type of an internal abnormality of an oil-filled electric apparatus using a computer.