Neural Modeling of Non-Linear Processes: Relevance of the Takens-Mane Theorem

In this paper, we test a constructive methodology for shaping neural networks models of non-linear dynamic systems. The method is supported by results and prescriptions related to the Takens-Mañé theorem, and is based on the measurement of the first minimum of the mutual information of the output signal, and in the application of the method of global false nearest neighbors to determine the embedding dimension. We present a numerical experiment to assess this constructive approach to the identification of a non-linear dynamic system and the application to the design of a neural network to forecasting a time series generated by an accelerometer coupled to a 150 MW steam turbine.

[1]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[2]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[3]  Henry D. I. Abarbanel,et al.  Analysis of Observed Chaotic Data , 1995 .

[4]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[5]  Francesco Masulli,et al.  Building a neuro-fuzzy system to efficiently forecast chaotic time series , 1997 .

[6]  R. Mañé,et al.  On the dimension of the compact invariant sets of certain non-linear maps , 1981 .

[7]  M. E. Davies,et al.  Reconstructing attractors from filtered time series , 1997 .

[8]  Bruce W. Suter,et al.  The multilayer perceptron as an approximation to a Bayes optimal discriminant function , 1990, IEEE Trans. Neural Networks.

[9]  Mark Girolami.  Temporal Anti-Hebbian Learning , 1999 .

[10]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[11]  Francesco Masulli,et al.  Neuro-fuzzy system for chaotic time series forecasting , 1997, Optics & Photonics.

[12]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

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

[14]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[15]  L. Glass,et al.  Oscillation and chaos in physiological control systems. , 1977, Science.

[16]  Fraser,et al.  Independent coordinates for strange attractors from mutual information. , 1986, Physical review. A, General physics.

[17]  Riccardo Parenti,et al.  Steam turbine vibration diagnostic system based on neural hologram , 1998 .