Title: System-level BIT false alarm reducing technology based on sensor network time stress analysis and the fault propagation correlation model

Authors: Kehong Lv; Zhiao Zhao; Jing Qiu; Guanjun Liu; Peng Yang

Addresses: Laboratory of Science and Technology on Integrated Logistics Support, College of Mechatronics and Automation, National University of Defense Technology, Changsha 410073, Hunan, China ' Laboratory of Science and Technology on Integrated Logistics Support, College of Mechatronics and Automation, National University of Defense Technology, Changsha 410073, Hunan, China ' Laboratory of Science and Technology on Integrated Logistics Support, College of Mechatronics and Automation, National University of Defense Technology, Changsha 410073, Hunan, China ' Laboratory of Science and Technology on Integrated Logistics Support, College of Mechatronics and Automation, National University of Defense Technology, Changsha 410073, Hunan, China ' Laboratory of Science and Technology on Integrated Logistics Support, College of Mechatronics and Automation, National University of Defense Technology, Changsha 410073, Hunan, China

Abstract: Equipment fault propagation and sensor faults are the main causes of false alarms in built-in test (BIT) systems. Hence, the current paper analyses the mechanism of system-level BIT false alarms. The technical process of system-level BIT false alarm recognition is presented. First, sensor damage states are estimated using sensor network time stress data generated during its lifetime. In different damage states, a dual support vector machine (SVM) relevance model is built, it can recognise system-level BIT type II false alarms induced by sensor faults. Subsequently, a fault propagation correlation model of the sensor network is set up. Based on this model, a false alarm recognition method is proposed based on probability reasoning. This method can effectively reduce system-level BIT type I false alarms caused by sensor network fault propagation. Lastly, a case about the helicopter horizon system is studied to validate the proposed technology.

Keywords: built-in testing; sensor networks; false alarms; time stress; relevance models; fault propagation correlation; sensor faults; dual SVM; support vector machines; probability reasoning; helicopter horizon system.

DOI: 10.1504/IJSNET.2012.051520

International Journal of Sensor Networks, 2012 Vol.12 No.4, pp.185 - 194

Received: 10 Feb 2012
Accepted: 10 Jul 2012
Published online: 20 Jan 2013 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article