Aiming at the lack of fault samples of power equipment

this paper proposes a dry-type air-core reactor condition assessment method based on belief rule base. By building a test platform for the electrical and temperature rise characteristics of dry-type air-core reactors under multiple working conditions

a data sample set of reactor active power and the temperature rise rate of the hottest point is obtained under different operating conditions. A reactor condition assessment model based on belief rule base and evidential reasoning is established.In order to reduce the influence of expert subjectivity on the prediction results of the state assessment model

a belief rule base optimization method is proposed

and the evidential reasoning algorithm is used to convert the input feature information of the reactor into the output state level. The evaluation model was tested by test data

and the results verified the validity and accuracy of the dry-type air-core reactor condition assessment method based on small training samples.