MULTI-INFORMATION FUSION-BASED FAULT EARLY WARNING METHOD AND DEVICE FOR CONVERTER

The present invention relates to a fault early warning method and device for a converter based on multi-information fusion, and a computer-readable medium. The fault early warning method comprises: establishing a performance parameter database of the converter (101), wherein the performance parameter database comprises a performance parameter set of a plurality of functional components of the converter collected when at least one fault occurs to the converter; performing feature extraction on the performance parameter set of the performance parameter database to obtain a fault feature parameter database (102), wherein the fault feature parameter database comprises at least one fault and at least one fault feature parameter group corresponding to each of the fault, and each of the fault feature parameter group comprises a plurality of fault feature parameters, related to a plurality of functional components of the converter; and performing neural network modeling, based on at least one fault and at least one fault feature parameter group corresponding to each of the fault in the fault feature parameter database, to obtain a fault early warning model representing a mapping relationship between the fault and the fault feature parameters (103).