Fault Detection and Identification for Fire and Explosion Detection

A real – time fire and explosion detection system is presented in this paper. The data being used was acquired by a Wireless Sensor Network, residing in a room. Noise is first rejected from the acquired samples, using an appropriate filter. Next, a model of the stochastic process is computed in real time using a robust – adaptive method. It will be used to predict the temperature's future evolution. The outputs of the model are used to detect sensor faults and to ensure the reliability and consistency of the data. Fires are detected using a probabilistic change detection method. Three different change detection algorithms were tested and compared, with one being chosen for recommendation. Explosions are identified using the predicted data. Finally, a software application was developed, to prove the efficiency of the proposed system.

[1]  Gregory J. Pottie,et al.  Sensor network data fault types , 2007, TOSN.

[2]  João Gama,et al.  A Study on Change Detection Methods , 2009 .

[3]  Abdel Aitouche,et al.  Contribution to state and sensor fault estimation applied to PEM Fuel Cell Systems , 2016, 2016 5th International Conference on Systems and Control (ICSC).

[4]  Ciprian Lupu,et al.  Adaptive - Robust control a computational efficient real time simulation , 2015, 2015 13th International Conference on Engineering of Modern Electric Systems (EMES).

[5]  S. Rogers,et al.  Sensor noise fault detection , 2003, Proceedings of the 2003 American Control Conference, 2003..

[6]  R. Sorrentino,et al.  Electronic Filter Simulation & Design , 2007 .

[7]  Jianwen Luo,et al.  Properties of Savitzky-Golay digital differentiators , 2005, Digit. Signal Process..

[8]  Jens Marklof.  Encyclopedia of Mathematical Physics, Vol 1 , 2004 .

[9]  Cosmin Mihai,et al.  Real Time & Power Efficient Adaptive - Robust Control , 2017 .

[10]  Sen M. Kuo,et al.  Real-time digital signal processing , 2001 .

[11]  Jarred Barber,et al.  A Generalized Likelihood Ratio Test for Coherent Change Detection in Polarimetric SAR , 2015, IEEE Geoscience and Remote Sensing Letters.

[12]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[13]  Steven Lake Waslander,et al.  Outlier rejection for visual odometry using parity space methods , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[14]  Hong Chen,et al.  Data-Driven Design of Parity Space-Based FDI System for AMT Vehicles , 2015, IEEE/ASME Transactions on Mechatronics.

[15]  Mark S. Nixon,et al.  Feature Extraction and Image Processing , 2002 .

[16]  Deborah Estrin,et al.  A Collaborative Approach to In-Place Sensor Calibration , 2003, IPSN.

[17]  Miroslav D. Lutovac,et al.  Filter Design for Signal Processing Using MATLAB and Mathematica , 2000 .

[18]  Georges Barakat,et al.  FAULT DETECTION AND ISOLATION APPROACH FOR PERMANENT MAGNET SYNCHRONOUS MACHINES , 2015 .

[19]  R. Baierlein.  Probability Theory: The Logic of Science , 2004 .