Robust neural-network-based fault detection with sequential D-optimum bounded-error input design

Abstract A growing demand for technologically advanced systems has contributed to the increase of the awareness of systems safety and reliability. Such a situation requires the development of novel methods of robust fault diagnosis. The application of the analytical redundancy based methods for system fault detection causes that their effectiveness depends on model quality. In this paper, a new methodology for the improvement of the neural model with a D-optimum sequential experimental design technique combined with outer bounding ellipsoid algorithm is proposed. Moreover, a novel method of robust fault detection against neural model uncertainty and disturbances is developed. Such an approach is used for modelling and robust fault detection of the three-screw spindle oil pump.

[1]  Rolf Isermann,et al.  Fault-Diagnosis Applications: Model-Based Condition Monitoring: Actuators, Drives, Machinery, Plants, Sensors, and Fault-tolerant Systems , 2011 .

[2]  Beata Mrugalska,et al.  Practical application of product design method robust to disturbances , 2012 .

[3]  J. Norton,et al.  Bounding Approaches to System Identification , 1996 .

[4]  Eric Walter,et al.  Identification of Parametric Models: from Experimental Data , 1997 .

[5]  Paul M. Frank,et al.  Diagnosis strategies and systems: principles, fuzzy and neural approaches , 2000 .

[6]  Roger J.-B. Wets,et al.  Minimization by Random Search Techniques , 1981, Math. Oper. Res..

[7]  Damiano Rotondo,et al.  Robust Quasi–LPV Model Reference FTC of a Quadrotor Uav Subject to Actuator Faults , 2015, Int. J. Appl. Math. Comput. Sci..

[8]  O. Nelles.  Nonlinear System Identification: From Classical Approaches to Neural Networks and Fuzzy Models , 2000 .

[9]  Ivan N. Vuchkov,et al.  Quality Improvement with Design of Experiments: A Response Surface Approach , 2001 .

[10]  Rolf Isermann,et al.  Fault-Diagnosis Applications , 2011 .

[11]  Y. F. Huang,et al.  On the value of information in system identification - Bounded noise case , 1982, Autom..

[12]  Vicenç Puig,et al.  Robust fault detection of non-linear systems using set-membership state estimation based on constraint satisfaction , 2012, Eng. Appl. Artif. Intell..

[13]  Beata Mrugalska.  Design and Quality Control of Products Robust to Model Uncertainty and Disturbances , 2013 .

[14]  Michel Kinnaert,et al.  Diagnosis and Fault-Tolerant Control , 2006 .

[15]  V. Cerone,et al.  Bounded error identification of Hammerstein systems through sparse polynomial optimization , 2012, Autom..

[16]  Steven X. Ding,et al.  Model-based Fault Diagnosis Techniques: Design Schemes, Algorithms, and Tools , 2008 .

[17]  Vicenç Puig,et al.  Fault Diagnosis and Fault Tolerant Control in Critical Infrastructure Systems , 2015, Intelligent Monitoring, Control, and Security of Critical Infrastructure Systems.

[18]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[19]  Douglas C. Montgomery,et al.  Introduction to Statistical Quality Control , 1986 .

[20]  Robert J. Schalkoff,et al.  Artificial neural networks , 1997 .

[21]  Madan M. Gupta,et al.  Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory , 2003 .