Fault-Tolerant Event Region Detection on Trajectory Pattern Extraction for Industrial Wireless Sensor Networks

Poisonous pollutants produced in chemical, plastics, or nuclear power industry are easy to leak and result in a large-scale hazardous event region. Recently, industrial wireless sensor networks (IWSNs) are intended to provide situational awareness in industry site and thus hold the promise of profiling the event region. However, low-cost nodes in IWSNs are prone to fail due to prolonged exposure to harsh environment. This article targets the detection of hazardous event region for IWSNs with faulty nodes. A fault-tolerant event region detection algorithm named TPE-FTED is proposed to formulate faulty nodes identification as a trajectory pattern extraction problem. Through online learning of probabilistic model, each node characterizes the distribution of sensing values under different sensing states. A specific set of probabilistic models can be formed as a trajectory which indicates something special happens. Based on the implicit knowledge from generated trajectories, TPE-FTED conducts pattern matching and checks spatiotemporal constraint to identify the declaration of faulty nodes. Simulation results demonstrate that TPE-FTED achieves low false alarm rate as well as high detection accuracy.

[1]  Insoo Koo,et al.  Sensor Fault Classification Based on Support Vector Machine and Statistical Time-Domain Features , 2017, IEEE Access.

[2]  Riaz Ahmed Shaikh,et al.  An analysis of fault detection strategies in wireless sensor networks , 2017, J. Netw. Comput. Appl..

[3]  Lei Shu,et al.  Toxic gas boundary area detection in large-scale petrochemical plants with industrial wireless sensor networks , 2016, IEEE Communications Magazine.

[4]  Corentin Briat,et al.  Convergence and Equivalence Results for the Jensen's Inequality—Application to Time-Delay and Sampled-Data Systems , 2011, IEEE Transactions on Automatic Control.

[5]  Young-Bae Ko,et al.  A Continuous Object Boundary Detection and Tracking Scheme for Failure-Prone Sensor Networks , 2017, Sensors.

[6]  Song Han,et al.  Industrial Internet of Things: Challenges, Opportunities, and Directions , 2018, IEEE Transactions on Industrial Informatics.

[7]  Boubaker Daachi,et al.  Application of fuzzy inference systems to detection of faults in wireless sensor networks , 2012, Neurocomputing.

[8]  Bonnie S. Heck-Ferri,et al.  Distributed Fault-Tolerance for Event Detection Using Heterogeneous Wireless Sensor Networks , 2012, IEEE Transactions on Mobile Computing.

[9]  Lei Shu,et al.  Internet of Things for Disaster Management: State-of-the-Art and Prospects , 2017, IEEE Access.

[10]  Guangjie Han,et al.  Analysis of Energy-Efficient Connected Target Coverage Algorithms for Industrial Wireless Sensor Networks , 2017, IEEE Transactions on Industrial Informatics.

[11]  Cesare Alippi,et al.  A Cognitive Fault Diagnosis System for Distributed Sensor Networks , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[12]  Shaojie Tang,et al.  Fault tolerant complex event detection in WSNs: A case study in structural health monitoring , 2013, 2013 Proceedings IEEE INFOCOM.

[13]  Pabitra Mohan Khilar,et al.  Distributed self fault diagnosis algorithm for large scale wireless sensor networks using modified three sigma edit test , 2015, Ad Hoc Networks.

[14]  Jiming Chen,et al.  Detecting Faulty Nodes with Data Errors for Wireless Sensor Networks , 2014, ACM Trans. Sens. Networks.

[15]  Elias S. Manolakos,et al.  Estimating the Spatiotemporal Evolution Characteristics of Diffusive Hazards Using Wireless Sensor Networks , 2015, IEEE Transactions on Parallel and Distributed Systems.

[16]  Jie Gao,et al.  How to identify global trends from local decisions? Event region detection on mobile networks , 2014, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[17]  Wajeb Gharibi,et al.  Wireless Sensor Networks in oil and gas industry: Recent advances, taxonomy, requirements, and open challenges , 2018, J. Netw. Comput. Appl..

[18]  Maizura Mokhtar,et al.  Sensor Failure Detection, Identification, and Accommodation Using Fully Connected Cascade Neural Network , 2015, IEEE Transactions on Industrial Electronics.

[19]  Jianxin Wang,et al.  On Threshold-Free Error Detection for Industrial Wireless Sensor Networks , 2018, IEEE Transactions on Industrial Informatics.

[20]  Xi Zhang,et al.  HMRF-based distributed fault detection for wireless sensor networks , 2012, 2012 IEEE Global Communications Conference (GLOBECOM).

[21]  John R. Hershey,et al.  Approximating the Kullback Leibler Divergence Between Gaussian Mixture Models , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[22]  Athanasios V. Vasilakos,et al.  A review of industrial wireless networks in the context of Industry 4.0 , 2015, Wireless Networks.

[23]  Jie Ma,et al.  Fault-Tolerant Event Detection in Wireless Sensor Networks using Evidence Theory , 2015, KSII Trans. Internet Inf. Syst..

[24]  Makhlouf Aliouat,et al.  FDS: Fault Detection Scheme for Wireless Sensor Networks , 2015, Wireless Personal Communications.