High-accuracy gearbox health state recognition based on graph sparse random vector functional link network

hA GSRVFLN model is invented for gearbox health state recognition.hGSRVFLN can fully leverage exploit the sparsity of the output labels.hGSRVFLN employs a manifold graph to capture the structure information of input data.hWe devise an effective solver for GSRVFLN model with ADMM scheme.hTwo gearbox datasets are used to verify the superiority of GSRVFLN.