Integrated built-in-test false and missed alarms reduction based on forward infinite impulse response & recurrent finite impulse response dynamic neural networks

Abstract Built-in tests (BITs) are widely used in mechanical systems to perform state identification, whereas the BIT false and missed alarms cause trouble to the operators or beneficiaries to make correct judgments. Artificial neural networks (ANN) are previously used for false and missed alarms identification, which has the features such as self-organizing and self-study. However, these ANN models generally do not incorporate the temporal effect of the bottom-level threshold comparison outputs and the historical temporal features are not fully considered. To improve the situation, this paper proposes a new integrated BIT design methodology by incorporating a novel type of dynamic neural networks (DNN) model. The new DNN model is termed as Forward IIR & Recurrent FIR DNN (FIRF-DNN), where its component neurons, network structures, and input/output relationships are discussed. The condition monitoring false and missed alarms reduction implementation scheme based on FIRF-DNN model is also illustrated, which is composed of three stages including model training, false and missed alarms detection, and false and missed alarms suppression. Finally, the proposed methodology is demonstrated in the application study and the experimental results are analyzed.

[1]  Gangbing Song,et al.  Time-delayed dynamic neural network-based model for hysteresis behavior of shape-memory alloys , 2015, Neural Computing and Applications.

[2]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[3]  Balbir S. Dhillon,et al.  Early fault diagnosis of rotating machinery based on wavelet packets—Empirical mode decomposition feature extraction and neural network , 2012 .

[4]  Jing Qiu,et al.  System-level BIT false alarm reducing technology based on fault propagation analysis of complex system , 2012, 2012 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering.

[5]  Lam-for Kwok,et al.  Towards an Information-Theoretic Approach for Measuring Intelligent False Alarm Reduction in Intrusion Detection , 2013, 2013 12th IEEE International Conference on Trust, Security and Privacy in Computing and Communications.

[6]  Khashayar Khorasani,et al.  Adaptive time delay neural network structures for nonlinear system identification , 2002, Neurocomputing.

[7]  Yi Shen,et al.  Empirical mode decomposition based reducing false alarm filter for built-in test signal , 2011, 2011 IEEE International Instrumentation and Measurement Technology Conference.

[8]  Alice M. Agogino,et al.  Management of uncertainty in sensor validation, sensor fusion, and diagnosis of mechanical systems using soft computing techniques , 1996 .

[9]  Sherif Abdelwahed,et al.  Practical Implementation of Diagnosis Systems Using Timed Failure Propagation Graph Models , 2009, IEEE Transactions on Instrumentation and Measurement.

[10]  Jacob Savir.  Built-in online and offline test of airborne digital systems , 2005, IEEE Transactions on Instrumentation and Measurement.

[11]  Xuyang Lou,et al.  Synchronization of competitive neural networks with different time scales , 2007 .

[12]  Shikai Jing,et al.  An Approach to Fault Diagnosis Considering False Alarm and Middle State , 2013 .

[13]  V. G. Zourides.  Smart built-in-test (BIT): an overview , 1989, IEEE Automatic Testing Conference.The Systems Readiness Technology Conference. Automatic Testing in the Next Decade and the 21st Century. Conference Record..

[14]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[15]  Tien-Hsin Chao,et al.  Neural network target identification system for false alarm reduction , 2009, Defense + Commercial Sensing.

[16]  Y-T Tsai,et al.  A study of function-based diagnosis strategy and testability analysis for a system , 2012 .

[17]  Viliam Makis,et al.  Adaptive state detection of gearboxes under varying load conditions based on parametric modelling , 2006 .

[18]  S. Sorooshian,et al.  An Artificial Neural Network Model to Reduce False Alarms in Satellite Precipitation Products Using MODIS andCloudSatObservations , 2013 .

[19]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[20]  Shan Shi,et al.  Research on Reducing Built-in Test Subsystem’s False Alarm in Aero-Engine Control System , 2014 .

[21]  Simon Iwnicki,et al.  Application of power spectrum, cepstrum, higher order spectrum and neural network analyses for induction motor fault diagnosis , 2013 .

[22]  Peter Söderholm.  A system view of the No Fault Found (NFF) phenomenon , 2007, Reliab. Eng. Syst. Saf..

[23]  Jinfeng Li,et al.  Research of Fault Alarm Correlation Analysis Based on Association Rules in Communication Network , 2011, ICAIC.

[24]  Anke Meyer-Bäse,et al.  Singular Perturbation Analysis of Competitive Neural Networks with Different Time Scales , 1996, Neural Computation.

[25]  Iman Izadi,et al.  Study of generalized delay-timers in alarm configuration , 2013 .

[26]  Paul Phillips,et al.  No Fault Found events in maintenance engineering Part 2: Root causes, technical developments and future research , 2014, Reliab. Eng. Syst. Saf..

[27]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[28]  R. X. Gao,et al.  Diagnosis from within the system [built-in test] , 2002 .

[29]  Stephen J. Wright,et al.  Numerical Optimization , 2018, Fundamental Statistical Inference.

[30]  K. Westervelt.  F/A-18D(RC) built-in-test false alarms , 2002, Proceedings, IEEE Aerospace Conference.

[31]  Jun Tani,et al.  Emergence of Functional Hierarchy in a Multiple Timescale Neural Network Model: A Humanoid Robot Experiment , 2008, PLoS Comput. Biol..

[32]  Mustafa Ilarslan,et al.  Mitigating the impact of false alarms and no fault found events in military systems , 2016, IEEE Instrumentation & Measurement Magazine.

[33]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[34]  M. Stakkeland,et al.  Estimating instantaneous false alarm rate in a CFAR system by Bayesian and empirical Bayesian methods , 2007, 2007 IEEE Radar Conference.

[35]  Sirish L. Shah,et al.  A Framework for Optimal Design of Alarm Systems , 2009 .

[36]  Giovanni Soda,et al.  Local Feedback Multilayered Networks , 1992, Neural Computation.

[37]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[38]  Ah Chung Tsoi,et al.  FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling , 1991, Neural Computation.

[39]  Song Bifeng,et al.  An Improved KNN Algorithm of Intelligent Built-in Test , 2008, 2008 IEEE International Conference on Networking, Sensing and Control.

[40]  François Guillet,et al.  Hard competitive growing neural network for the diagnosis of small bearing faults , 2013 .

[41]  H.B. Land,et al.  System design that minimizes both missed detections and false alarms: a case study in arc fault detection , 2004, Proceedings of the 21st IEEE Instrumentation and Measurement Technology Conference (IEEE Cat. No.04CH37510).

[42]  Yaoyu Li,et al.  Discrimination of steady state and transient state of dither extremum seeking control via sinusoidal detection , 2016 .

[43]  K. Anderson,et al.  Smart BIT-2: adding intelligence to built-in-test , 1989, Proceedings of the IEEE National Aerospace and Electronics Conference.

[44]  Danilo P. Mandic,et al.  Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability , 2001 .

[45]  D. Allen.  Probabilities associated with a built-in-test system, focus on false alarms , 2003, Proceedings AUTOTESTCON 2003. IEEE Systems Readiness Technology Conference..

[46]  Iman Izadi,et al.  On expected detection delays for alarm systems with deadbands and delay-timers , 2011 .

[47]  Antonio Pietrosanto,et al.  A neural network approach to instrument fault detection and isolation , 1994, Conference Proceedings. 10th Anniversary. IMTC/94. Advanced Technologies in I & M. 1994 IEEE Instrumentation and Measurement Technolgy Conference (Cat. No.94CH3424-9).

[48]  Giansalvo Cirrincione,et al.  Neural model of the dynamic behaviour of a non-linear mechanical system , 2009 .

[49]  Mihiar Ayoubi.  Fault Diagnosis with Dynamic Neural Structure and Application to a Turbocharger , 1994 .

[50]  Junyou Shi,et al.  Intermittent failure process and false alarm interaction modelling of threshold-based monitoring built-in tests (BITs) , 2016 .

[51]  Hong-Zhong Huang,et al.  Analysis and study on BIT false alarm of flight control system in the sensing layer , 2012, 2012 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering.

[52]  Guangsheng Li,et al.  Study on False Alarm of the Armored Vehicles Electrical System BIT , 2010, 2010 International Conference on Intelligent Computation Technology and Automation.

[53]  A. Sarma,et al.  Robust adaptive threshold for control of false alarms , 2001, IEEE Signal Processing Letters.