Sensor validation using hardware-based on-line learning neural networks

The objective of this document Is to show the capabilities of parallel hardware-based on-line learning neural networks (NNs). This specific application is related to an on-line estimation problem for sensor validation purposes. Neural-network-based microprocessors are starting to be commercially available. However, most of them feature a learning performed with the classic back-propagation algorithm (BPA). To overcome this lack of flexibility a customized motherboard with transputers was implemented for this investigation, The extended BPA (EBPA), a modified and more effective BPA, was used for the on-line learning, These parallel hardware-based neural architectures were used to implement a sensor failure detection, identification, and accommodation scheme in the model of a night control system assumed to be without physical redundancy in the sensory capabilities. The results of this study demonstrate the potential for these neural schemes for implementation in actual flight control systems of modern high performance aircraft, taking advantage of the characteristics of the extended back-propagation along with the parallel computation capabilities of NN customized hardware.

[1]  C. Ha.  Neural Networks Approach to AIAA Aircraft Control Design Challenge , 1995 .

[2]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[3]  Etienne Barnard,et al.  Optimization for training neural nets , 1992, IEEE Trans. Neural Networks.

[4]  Herbert Rauch,et al.  Fault detection, isolation, and reconfiguration for aircraft using neural networks , 1993 .

[5]  Chien Huang,et al.  Failure-accommodating neural network flight control , 1992 .

[6]  R. S. Nutter,et al.  An extended back-propagation learning algorithm by using heterogeneous processing units , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[7]  Meir Pachter,et al.  A Hopfield neural network for adaptive control , 1993 .

[8]  Jacques de Villiers,et al.  Backpropagation neural nets with one and two hidden layers , 1993, IEEE Trans. Neural Networks.

[9]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[10]  Marcello R. Napolitano,et al.  On-Line Learning Nonlinear Direct Neurocontrollers for Restructurable Control Systems , 1995 .

[11]  Walter Baker,et al.  Learning augmented flight control for high performance aircraft , 1991 .

[12]  Marcello R. Napolitano,et al.  On-line learning non-linear direct neuro controllers for restructurable control systems , 1994 .

[13]  M. Steinberg,et al.  Applying neural network technology to future generation military flight control systems , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[14]  P. A. Jokinen.  Comparison of neural network models for process fault detection and diagnosis problems , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[15]  T.-H. Guo,et al.  Sensor failure detection and recovery by neural networks , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[16]  Walter C. Merrill,et al.  Neural network application to aircraft control system design , 1991 .

[17]  Marcello R. Napolitano,et al.  Aircraft failure detection and identification using neural networks , 1993 .

[18]  Kumpati S. Narendra,et al.  Control of nonlinear dynamical systems using neural networks: controllability and stabilization , 1993, IEEE Trans. Neural Networks.