Recognition ofMPS OutputSignal Described byDifferent Mathematical Models

Thepossibility ofartificial neural network usage for recognition ofasignal ofa multi-parameter sensor (MPS), described bydifferent mathematical models, isdescribed inthis paper. These mathematical models aredeveloped forthecases, whenMPSconversion characteristics havepositive derivatives, negative derivatives andderivatives ofdifferent signatsimilar andopposite increasing ofMPS output signal. Themodelof neural network, usedforrecognition, aswellasachieved results ofsimulation modeling ofa multi-parameter sensor signal recognition using MAITLAB software arepresented inthe endofthis paper.

[1]  Desire L. Massart,et al.  Supervised pattern recognition: the ideal method? , 1986 .

[2]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[3]  I.V. Turchenko,et al.  Simulation modeling of multi-parameter sensor signal identification using neural networks , 2004, 2004 2nd International IEEE Conference on 'Intelligent Systems'. Proceedings (IEEE Cat. No.04EX791).