Monitoring of distributed parameter systems based on a sensor network and ANFIS

This paper gives some estimation algorithms and a method for monitoring distributed parameter systems based on sensor networks and the adaptive-network-based fuzzy inference scheme. The modern intelligent sensor networks may be seen as distributed sensors, which may be placed in the field of the distributed parameter systems. ANFIS, as a method for non-linear system identification, is a powerful tool to estimate future behavior in distributed parameter systems, from acquired data obtained using wireless sensor connected in a distributed network placed in the field. The algorithms are based on non-linear auto-regression exogenous models. A case study of temperature flow for a parabolic equation is analysed, based on these approaches.

[1]  Ian F. Akyildiz,et al.  Wireless sensor networks: a survey , 2002, Comput. Networks.

[2]  Nikola K. Kasabov,et al.  DENFIS: dynamic evolving neural-fuzzy inference system and its application for time-series prediction , 2002, IEEE Trans. Fuzzy Syst..

[3]  D. Ucinski.  Optimal measurement methods for distributed parameter system identification , 2004 .

[4]  Hou Zhi-xiang,et al.  Nonlinear System Identification Based on Adaptive Neural Fuzzy Inference System , 2006, 2006 International Conference on Communications, Circuits and Systems.

[5]  Constantin Volosencu,et al.  Identification of distributed parameter systems, based on sensor networks and artificial intelligence , 2008 .

[6]  Jun-Ping Zhang,et al.  Time series prediction based on ensemble ANFIS , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[7]  Guanrong Chen,et al.  Spectral-approximation-based intelligent modeling for distributed thermal processes , 2005, IEEE Transactions on Control Systems Technology.

[8]  Patricia Morreale,et al.  System design and analysis of a web-based application for sensor network data integration and real-time presentation , 2009, 2009 3rd Annual IEEE Systems Conference.

[9]  José de Jesús Rubio,et al.  SOFMLS: Online Self-Organizing Fuzzy Modified Least-Squares Network , 2009, IEEE Transactions on Fuzzy Systems.

[10]  Xiangjie Liu,et al.  Identification of Nonlinear System Based on ANFIS with Subtractive Clustering , 2006, 2006 6th World Congress on Intelligent Control and Automation.

[11]  Rolf Isermann,et al.  Supervision, fault-detection and fault-diagnosis methods — An introduction , 1997 .

[12]  QiDi Wu,et al.  General fuzzy neural network: theory and applications , 1999, FUZZ-IEEE'99. 1999 IEEE International Fuzzy Systems. Conference Proceedings (Cat. No.99CH36315).

[13]  Daniele Marioli,et al.  Application of an ANFIS Algorithm to Sensor Data Processing , 2005, IEEE Transactions on Instrumentation and Measurement.

[14]  E. Cuevas,et al.  Neurofuzzy prediction for gaze control , 2009, Canadian Journal of Electrical and Computer Engineering.

[15]  A. Mellit,et al.  An ANFIS-based Forecasting for Solar Radiation Data from Sunshine Duration and Ambient Temperature , 2007, 2007 IEEE Power Engineering Society General Meeting.

[16]  Alexander S. Poznyak,et al.  Neural numerical modeling for uncertain distributed parameter systems , 2009, 2009 International Joint Conference on Neural Networks.

[17]  Lian Zhao,et al.  The comparison of neural network and hybrid neuro-fuzzy based inferential sensor models for space heating systems , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[18]  T. Poznyak,et al.  Neural network identification of uncertain 2D partial differential equations , 2009, 2009 6th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE).

[19]  Y. F. Zhu,et al.  A blind approach to nonlinear system identification , 2007 .

[20]  Paramasivan Saratchandran,et al.  Sequential Adaptive Fuzzy Inference System (SAFIS) for nonlinear system identification and prediction , 2006, Fuzzy Sets Syst..

[21]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..