论文信息 - Research on the Application of Neural Network in Diaphragm Icing Sensor Fault Diagnosis

Research on the Application of Neural Network in Diaphragm Icing Sensor Fault Diagnosis

As the core component of the Icing Detection System of aircrafts, the reliability of Diaphragm Icing Sensor is a key factor for the ice detection system to work normally. This paper makes use of Neural Network and Autoregressive Exogeneous Model (ARX) to set up the output prediction model of the diaphragm icing sensor. Compare the predicted output of the model with the actual output to diagnose sensor faults of the sensor. According to the data acquiring from our experiment platform of Diaphragm Icing Sensor, it has been proved that this method is effective for fault diagnosis of the Diaphragm Icing Sensor.

[1] Uwe Kruger,et al. Recursive partial least squares algorithms for monitoring complex industrial processes , 2003 .

[2] Krzysztof Patan,et al. Soft Computing Approaches to Fault Diagnosis for Dynamic Systems , 2001, Eur. J. Control.

[3] Rabi Bhattacharya,et al. Stochastic processes with applications , 1990 .

[4] Y. M. Chen,et al. Neural networks-based scheme for system failure detection and diagnosis , 2002, Math. Comput. Simul..

[5] Frank Lynch,et al. Effects of ice accretions on aircraft aerodynamics , 2001 .

[6] Francis T.K. Au,et al. Acceleration of Levenberg-Marquardt training of neural networks with variable decay rate , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[7] Walter Lang,et al. Application of Computational Intelligence for Sensor Fault Detection and Isolation , 2007 .