In this paper, a novel approach to model-based fault detection for non-linear systems is presented. An immune model of the system is used for the generation of residual. The orthogonal least-squares method is implemented to select the significant receptor vectors of the immune model. After the model identification, the filtered residual scheme and the fault alarm concentration are applied for the fault detection. To verify and demonstrate the performance of the proposed methodology, a simulation example on a two-link robot was studied. The results show the effectiveness and robustness in both system identification and fault detection.
BassevilleM.Detecting changes in signals and systems—a survey. Automatica, 1988, 24 (3), 309–326.
2.
FrankP. M.On-line fault detection in uncertain nonlinear systems using diagnostic observers—a survey. Int. J. Systems Sci., 1994, 25, 2129–2154.
3.
IsermannR.Process fault detection based on modeling and estimation methods: A survey. Automatica, 1984, 20 (4), 387–404.
4.
WillskyA. S.A survey of design methods for failure detection in dynamic systems. Automatica, 1976, 12, 601–611.
5.
GertlerJ. J.Survey of model-based failure detection and isolation in complex plants. IEEE Control System Mag., 1988, 8 (6), 3–11.
6.
PattonR. J.ChenJ.A survey of robustness in quantitative model-based fault diagnosis. Appl. Math. Computer. Sci., 1993, 3 (3), 399–416.
7.
GertlerJ. J.Fault Detection and Diagnosis in Engineering Systems, 1998 (Marcel Dekker, New York).
8.
PattonR. J.FrankP. M.ClarkR. N. (Eds) Fault Diagnosis in Dynamic Systems, Theory and Applications, 1989 (Prentice-Hall, Englewood Cliffs, New Jersey).
9.
ChenJ.PattonR. J.Robust Model-based Fault Diagnosis for Dynamic Systems, 1999 (Kluwer, Dordrecht, The Netherlands).
10.
BassevilleM.NikiforovI. V. (Eds) Detection of Abrupt Changes, Theory and Applications, 1993 (Prentice-Hall, Englewood Cliffs, New Jersey).
11.
IsermannR.BalléP.Trends in the applications of model-based fault detection and diagnosis of technical processes. Control Engng Practice, 1997, 5 (5), 709–719.
12.
SneiderH.FrankP. M.Observer-based supervision and fault detection in robots using nonlinear and fuzzy logic residual evaluation. IEEE Trans. Control Systems Technol., 1996, 4 (3), 274–282.
13.
FrankP. M.Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy—a survey of some new results. Automatica, 1990, 26, 459–474.
14.
KrishnaswamiV.RizzoniG.Nonlinear parity equation residual generation for fault detection and isolation. In Proceedings of the IFAC-IMACS Symposium onFault Detection, Supervision and Safety for Technical Processes, Espoo, Finland, 1994, pp. 317–322.
15.
KrishnaswamiV.LuhG.-C.RizzoniG.Nonlinear parity equation based residual generation for diagnosis of automotive engine fault. Control Engng Practice, 1995, 3 (10), 1385–1392.
MedvedevA.Fault detection and isolation by a continuous parity space method. Automatica, 1995, 31 (7), 1039–1044.
18.
FrankP. M.DingX.Survey of robust residual generation and evaluation methods in observer-based fault detection systems. J. Process Control, 1997, 7 (6), 403–424.
19.
PattonR. J.ChenJ.Observer-based fault detection and isolation: Robustness and applications. Control Engng Practice, 1996, 5 (5), 671–682.
20.
TarantinoR.SzigetiF.Colina-MorlesE.Generalized Luenberger observer-based fault-detection filter design: An industrial application. Control Engng Practice, 2000, 8, 665–671.
21.
ChenY. M.LeeM. L.Neural networks-based scheme for system failure detection and diagnosis. Math. Computers Simulation, 2002, 58, 101–109.
22.
ThomasP.LefebvreD.Fault detection and isolation in non-linear systems by using oversized neural networks. Math. Computers Simulation, 2002, 60, 181–192.
23.
Costa BrancoP. J.DenteJ. A.Vilela MendesR.Using immunology principles for fault detection. IEEE Trans. Ind. Electron., 2003, 50 (2), 362–373.
24.
DasguptaD.ForrestS.Novelty detection in time series data using ideas from immunology. In Proceedings of the International Conference onIntelligent Systems, Reno, Nevada, 19–21 June 1996, pp. 82–87.
25.
GonzalezF.DasguptaD.KozmaR.Combining negative selection and classification techniques for anomaly detection. In Proceedings of the IEEE Congress onEvolutionary Computation, Hawaii, 12–17 May 2002, pp. 705–710 (IEEE, New York).
26.
IshiguroA.WatanabeY.UchikawaY.Fault diagnosis of plant systems using immune networks. In Proceedings of the IEEE International Conference onMultisensor Fusion and Integration for Intelligent Systems, Las Vegas, Nevada, 2–5 October 1994, pp. 34–42 (IEEE, New York).
27.
DasguptaD.Artificial neural networks and artificial immune systems: Similarities and differences. In Proceedings of the IEEE International Conference onSystem, Man, and Cybernetics, Orlando, Florida, 12–15 October 1997, pp. 873–878 (IEEE, New York).
28.
de CastroL. N.Comparing immune and neural networks. In Proceedings of the Seventh Brazilian Symposium onNeural Networks, Brazil, 11–14 November 2002, pp. 250–255.
29.
LuhG. C.ChengW. C.Non-linear system identification using an artificial immune system. Proc. Instn Mech. Engrs, Part I: J. Systems and Control Engineering, 2001, 215 (16), 569–585.
30.
DasguptaD.Artificial Immune Systems and Their Applications, 1999 (Springer-Verlag, Berlin, Germany).
31.
de CastroL. N.Von ZubenF. J.Artificial immune systems. Part I: Basic theory and applications. Technical Report TR-DCA 01/99, State University of Campinas, Brazil, 1999.
32.
de CastroL. N.JonathanT.Artificial Immune Systems: A New Computational Intelligence Approach, 2002 (Springer-Verlag, Berlin, Germany).
RoittI.BrostoffJ.MaleD. K.Immunology, 5th edition, 1998 (Mosby International Limited).
35.
HightowerR.ForrestS.PerelsonA. S.The evolution of emergent organization in immune system gene libraties. In Proceedings of the Sixth International Conference onGenetic Algorithms, San Mateo, California, 1995, pp. 344–350 (Morgan Kaufmann, San Mateo, California).
36.
ForrestS.PerelsonA. S.AllenL.CherukuriR.Self-nonself discrimination in a computer. In Proceedings of IEEE Symposium onResearch in Security and Privacy, Oakland, California, 16–18 May 1994, pp. 202–212 (IEEE, New York).
37.
TaniguchiS.DoteY.Sensor fault detection for uninterruptible power supply (UPS) control system using fast fuzzy-neural network and immune network. In Proceedings of the IEEE International Conference onSystems, Man, and Cybernetics, Tucson, Arizona, 7–10 October 2001, pp. 99–104 (IEEE, New York).
38.
HuntJ. E.CookeD. E.An adaptive distributed learning system based on immune system. In Proceedings of the IEEE International Conference onSystems, Man, and Cybernetics, 22–25 October 1995, Vancouver, British Columbia, Canada, pp. 2494–2499 (IEEE, New York).
39.
DasguptaD.Attoh-OkinN.Immunity-based systems: A survey. Computational Cybernetics and Simulation. In Proceedings of the IEEE International Conference onSystems, Man, and Cybernetics, Orlando, Florida, 12–15 October 1997, pp. 369–374 (IEEE, New York).
40.
ForrestS.HightowerR.PerelsonA. S.The Baldwin effect in the immune system: Learning by somatic hypermutation. In Individual Plasticity in Evolving Populations: Models and Algorithms, 1996 (Addison-Wesley, Reading, Massachusetts).
41.
TimmisJ.NealM.HuntJ.Data analysis using artificial immune systems, cluster analysis and Kohonen networks: Some comparisons. In Proceedings of the IEEE International Conference onSystems, Man, and Cybernetics, Tokyo, Japan, 12–15 October 1999, pp. 922–927 (IEEE, New York).
42.
KnightT.TimmisJ.AINE: An immunological approach to data mining. In Proceedings of the International Conference onData Mining, San Jose, California, 29 November-2 December 2001, pp. 297–304 (IEEE, New York).
LinJ. H.IsikC. A.Maximum entropy radial basis function network based neuro-fuzzy controller. In Proceedings of the Fifth IEEE International Conference onFuzzy Systems, New Orleans, Louisiana, 8–11 September 1996, pp. 156–161 (IEEE, New York).
45.
OpreaM. L.Antibody repertories and pathogen recognition: The role of germline diversity and somatic hypermutation. PhD dissertation, Department of Computer Science, The University of New Mexico, Albuquerque, New Mexico, 1999.
46.
SherstinskyA.PicardR. W.On the efficiency of the orthogonal least squares training method for radial basis function networks. IEEE Trans. Neural Networks, 1996, 7 (1), 195–200.
47.
ChenS.CowanC. F.N.GrantP. M.Orthogonal least squares learning algorithm for radial basis function networks. IEEE Trans. Neural Networks, 1991, 2 (2), 302–309.
48.
Eng-SiongC.YangH. H.BosS.Orthogonal least-squares learning algorithm with local adaptation process for the radial basis function networks. IEEE Signal Processing Lett., 1996, 3 (8), 253–255.
49.
HongX.HarrisC. J.Nonlinear model structure design and construction using orthogonal least squares and D-optimality design. IEEE Trans. Neural Networks, 2002, 13 (5), 1245–1250.
50.
BrouwnG. G.KrijgsmanA. J.Hybrid neural networks for nonlinear system identification. In Proceedings of the International Conference onControl, Coventry, 21–24 March 1994, pp. 504–509 (IEEE, New York).
51.
ChenS.GrantP. M.CowanC. F. N.Orthogonal least squares algorithm for training multi-output radial basis function networks. In Proceedings of the International Conference onArtifical Neural Networks, Bournemouth, November 1991, pp. 336–339 (IEEE, New York).
52.
SneiderH.FrankP. M.Observer-based supervision and fault detection in robots using nonlinear and fuzzy logic residual evaluation. IEEE Trans. Control Systems Technol., 1996, 4 (3), 274–282.
53.
YaochuJ.Decentralized adaptive fuzzy control of robot manipulators. IEEE Trans. Systems, Man Cybernetics B, 1998, 28 (1), 47–57.
54.
LiW.ShahS.Structured residual vector-based approach to sensor fault detection and isolation. J. Process Control, 2002, 12 (3), 429–443.
