Analytical redundancy technique is of great importance to guarantee the reliability and safety of aircraft engine system. In this\npaper, a machine learning based aeroengine sensor analytical redundancy technique is developed and verified through hardwarein-\nthe-loop (HIL) simulation. The modified online sequential extreme learning machine, selective updating regularized online\nsequential extreme learning machine (SROS-ELM), is employed to train the model online and estimate sensor measurements. It\nselectively updates the output weights of neural networks according to the prediction accuracy and the norm of output weight\nvector, tackles the problems of singularity and ill-posedness by regularization, and adopts a dual activation function in the hidden\nnodes combing neural and wavelet theory to enhance prediction capability.The experimental results verify the good generalization\nperformance of SROS-ELM and show that the developed analytical redundancy technique for aeroengine sensor fault diagnosis\nbased on SROS-ELM is effective and feasible.
Loading....