In order to diagnose sensor fault of aeroengine more quickly and accurately, a double redundancy diagnosis approach based on\nWeighted Online Sequential Extreme LearningMachine (WOS-ELM) is proposed in this paper.WOS-ELM, which assigns different\nweights to old and new data, implements weighted dealing with the input data to get more precise training models. The proposed\napproach contains two series of diagnosismodels, that is, spatialmodel and timemodel.The application of double redundancy based\non spatial and time redundancy can in real time detect the hard fault and soft fault much earlier.The trouble-free or reconstructed\ntime redundancy model can be utilized to update the training model and make it be consistent with the practical operation mode\nof the aeroengine. Simulation results illustrate the effectiveness and feasibility of the proposed method.
Loading....