Fault detection method and system for blade root bolt of wind power blade

Abstract

The invention provides a fault detection method and system for a blade root bolt of a wind power blade, and relates to the technical field of fault detection, and the method comprises the steps: collecting multi-dimensional operation data of the blade root bolt of the wind power blade, executing multi-layer wavelet transform to decompose the multi-dimensional operation data, carrying out noise reduction processing, and dividing the multi-dimensional operation data into a plurality of time windows, constructing a time-frequency characteristic matrix; constructing a mixed deep learning model, extracting forward time sequence features and backward time sequence features of the time-frequency feature matrix, combining the forward time sequence features and the backward time sequence features to generate a time sequence feature graph, extracting to obtain a fault feature probability vector, generating a preliminary fault diagnosis result, executing fuzzy rule reasoning, and correcting according to a Markov chain to obtain a fault diagnosis result; and obtaining a fault development trend prediction result, determining a fault level, and generating early warning information.

Images