Neural network based sensor array signal processing

An autoassociative memory using neural networks is proposed for sensor failure detection and correction. A classical approach to sensor failure detection and correction relies upon complex models of physical systems, however, a neural network approach can be used to represent systems through training for which mathematical models can not be formulated. In such cases, a neural network autoassociative memory can be used to predict sensor outputs. Differences between measured sensor outputs and sensor outputs estimated by the autoassociative memory, can be used to identify faulty sensors. Median filtering or other signal processing schemes may then be used to correct faulty sensor outputs. This technique can be used to process data from MEMS (micro electromechanical systems) or other sensor arrays.

[1]  J. Andel.  Sequential Analysis , 2022, The SAGE Encyclopedia of Research Design.

[2]  Kurt Hornik,et al.  Neural networks and principal component analysis: Learning from examples without local minima , 1989, Neural Networks.

[3]  M. Arozullah,et al.  Higher order data compression with neural networks , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[4]  Dejan J. Sobajic,et al.  Learning and generalization characteristics of the random vector Functional-link net , 1994, Neurocomputing.

[5]  M. Kramer.  Nonlinear principal component analysis using autoassociative neural networks , 1991 .

[6]  Mark A. Kramer,et al.  Autoassociative neural networks , 1992 .

[7]  David C. Zimmerman,et al.  Sensor failure detection and isolation in flexible structures using system realization redundancy , 1993 .

[8]  Yoh-Han Pao,et al.  Stochastic choice of basis functions in adaptive function approximation and the functional-link net , 1995, IEEE Trans. Neural Networks.

[9]  W. Merrill,et al.  Turbofan Engine Demonstration of Sensor Failure Detection , 1991 .

[10]  E. Beale,et al.  Missing Values in Multivariate Analysis , 1975 .

[11]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[12]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[13]  N. P. Piercy.  Sensor failure estimators for detection filters , 1992 .

[14]  A. Willsky,et al.  Analytical redundancy and the design of robust failure detection systems , 1984 .