Recurrent neural network for faulty data identification in smart grid

The accuracy of the control data from different sensors in a system is evaluated by embedding a recurrent neural network with layer feedback for each sensor. The accuracy of the sensor output is calculated by comparing the values from neighboring sensor output. Here non-linear sensor model using Hammerstein-Wiener was used and the amount of sensor data fault is estimated by using kalman filter. This value will be considered as an actual output in case of sensor failure. The performance is analyzed with and without extended kalman filter learning algorithm by introducing a step size fault.

[1]  Marcello R. Napolitano,et al.  A learning approach to the SFDIA problem using radial basis function networks , 2000, Proceedings of the 2000 IEEE International Symposium on Intelligent Control. Held jointly with the 8th IEEE Mediterranean Conference on Control and Automation (Cat. No.00CH37147).

[2]  R. S. Ahmed.  Identification of nonlinear dynamic systems using a rapid neural network , 2001, IECON'01. 27th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.37243).

[3]  D. Schroder,et al.  Identification of nonlinear dynamic systems with recurrent neural networks and Kalman filter methods , 1996, 1996 IEEE International Symposium on Circuits and Systems. Circuits and Systems Connecting the World. ISCAS 96.

[4]  Mario G. Perhinschi,et al.  An adaptive threshold approach for the design of an actuator failure detection and identification scheme , 2006, IEEE Transactions on Control Systems Technology.

[5]  Rastko R. Selmic,et al.  Wireless Sensor Network Modeling Using Modified Recurrent Neural Networks: Application to Fault Detection , 2008, IEEE Transactions on Instrumentation and Measurement.

[6]  Younghwan An,et al.  A design of fault tolerant flight control systems for sensor and actuator failures using on-line learning neural networks , 1998 .

[7]  Reza Langari,et al.  Performance Study of Enhanced Auto-Associative Neural Networks For Sensor Fault Detection , 2004 .

[8]  Jürgen Schmidhuber,et al.  Kalman filters improve LSTM network performance in problems unsolvable by traditional recurrent nets , 2003, Neural Networks.

[9]  B. Azimi-Sadjadi,et al.  Stability of networked control systems in the presence of packet losses , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[10]  Mario Innocenti,et al.  Fault detection using neural networks , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[11]  Dennis S. Bernstein,et al.  Sensor performance specifications , 2001 .