High-altitude platform fault diagnosis method based on wavelet analysis and multilayer extreme learning machine

The invention relates to a high-altitude platform fault diagnosis method based on wavelet analysis and a multilayer extreme learning machine, and belongs to the field of intelligent fault diagnosis of a high-altitude platform sensor system. The method comprises the following steps: performing feature extraction and denoising on system-based labeled fault sample original data by adopting a wavelet analysis method; constructing a multi-layer extreme learning machine, and carrying out online sequence learning training; and carrying out fault diagnosis aiming at actual system data. According to the method, fault feature extraction and denoising are carried out by adopting a wavelet analysis method, an online multilayer over-limit learning machine is constructed to carry out various fault classification, the fault category is further diagnosed, the limitation that the existing single-layer over-limit learning machine is low in diagnosis precision and cannot diagnose the sensor fault in time at present is broken th