Abstract
This chapter introduces a method for fault classification in mechanical systems in the presence of missing data entries. The method is based on auto-associative neural networks where the network is trained to recall the input data through some non-linear neural network mapping. An error equation with missing inputs as design variables is constructed from the trained network. The genetic algorithm was used to solve for the missing input values. The presented method is tested on a fault classification problem for a population of cylindrical shells. It was found that the method could estimate single-missing-entries to an accuracy of 93% and two-missing-entries to an accuracy of 91%. The estimated values were then used in the classification of faults and a fault classification accuracy of 94% was observed for single-missing-entry cases and 91% for two-missing-entry cases while the full database set gave a classification accuracy of 96%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdella M, Marwala T (2006) The use of a genetic algorithm and neural networks to approximate missing data in database. Comput Inform 24:1001–1013
Akula VR, Ganguli R (2003) Finite element model updating for helicopter rotor blade using a genetic algorithm. AIAA J. doi:10.2514/2.1983
Almeida FS, Awruch AM (2009) Design optimization of composite laminated structures using a genetic algorithm and finite element analysis. Compos Struct 88:443–454
Amiri M, Saeb S, Yazdanpanah MJ, Seyyedsalehi SA (2008) Analysis of the dynamical behavior of a feedback auto-associative memory. Neurocomputing 71:486–494
Arifovic J, Gençay R (2001) Using a genetic algorithms to select architecture of a feedforward artificial neural network. Phys A: Stat Mech Appl 289:574–594
Atalla MJ, Inman DJ (1998) On model updating using neural networks. Mech Syst Signal Proc 12:135–161
Balamurugan R, Ramakrishnan CV, Singh N (2008) Performance evaluation of a two stage adaptive genetic algorithm (TSAGA) in structural topology optimization. Appl Soft Comput 8:1607–1624
Balin S (2011) Non-identical parallel machine scheduling using genetic algorithm. Expert Syst Appl 38:6814–6821
Banzhaf W, Nordin P, Keller R, Francone F (1998) Genetic programming – an introduction: on the automatic evolution of computer programs and its applications. Morgan Kaufmann Publishers, San Francisco
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford
Canyurt OE, Kim HR, Lee KY (2008) Estimation of laser hybrid welded joint strength by using a genetic algorithm approach. Mech Mater 40:825–831
Chen Q, Chan YW, Worden K (2003) Structural fault diagnosis and isolation using neural networks based on response only data. Comput Struct 81:2165–2172
Crossingham B, Marwala T (2007) Using a genetic algorithms to optimise rough set partition sizes for HIV data analysis. Stud Comput Intell 78:245–250
de Zubicaray G, McMahon K, Eastburn M, Pringle AJ, Lorenz L, Humphreys MS (2007) Support for an auto-associative model of spoken cued recall: evidence from fMRI. Neuropsychologia 45:824–835
Doebling SW, Farrar CR, Prime MB, Shevitz DW (1996) Damage identification and health monitoring of structural and mechanical systems from changes in their vibration characteristics: a literature review. Los Alamos National Laboratory report LA-13070-MS
Ewins DJ (1995) Modal testing: theory and practice. Research Studies Press, Letchworth
Forrest S (1996) Genetic algorithms. ACM Comput Surv 28:77–80
Franulović M, Basan R, Prebil I (2009) A genetic algorithm in material model parameters’ identification for low-cycle fatigue. Comput Mater Sci 45:505–510
Gladwin D, Stewart P, Stewart J (2011) A controlled migration genetic algorithm operator for hardware-in-the-loop experimentation. Eng Appl Art Intell 24:586–594
Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning. Addison-Wesley, Reading
Gwiazda TD (2006) A genetic algorithms reference Vol.1 Cross-over for single-objective numerical optimization problems. Adobe eBook, Lomianki
Hines JW, Uhrig RE, Wrest DJ (1998) Use of autoassociative neural networks for signal validation. J Intell Robot Syst 21:143–154
Holland J (1975) Adaptation in natural and artificial systems. University of Michigan Press, Ann Arbor
Houck CR, Joines JA, Kay MG (1995) A genetic algorithm for function optimisation: a MATLAB implementation. Technical Report NCSU-IE TR 95–09, North Carolina State University, Raleigh
Hulley G, Marwala T (2007) A genetic algorithm based incremental learning for optimal weight and classifier selection. Comput Mod Life Sci Am Inst Phys Ser 952:258–267
Jensen CA, El-Sharkawi MA, Marks RJ II (2001) Power system security assessment using neural networks: feature selection using fisher discrimination. IEEE Trans Energ Convers 16:757–763
Kramer MA (1991) Nonlinear principal component analysis using autoassociative neural networks. AIChE J 37:233–234
Kramer MA (1992) Autoassociative neural networks. Comput Chem Eng 16:313–328
KubalÃk J, Lazanský J (1999) Genetic algorithms and their testing. In: Proceedings of the AIP Conference, pp 217–229
Kwak HG, Kim J (2009) An integrated genetic algorithm complemented with direct search for optimum design of RC frames. Comput Aid Des 41:490–500
Levin RI, Lieven NAJ (1998) Dynamic finite element model updating using simulated annealing and genetic algorithms. Mech Syst Signal Proc 12:91–120
Li X, Du G (2012) Inequality constraint handling in genetic algorithms using a boundary simulation method. Comput Oper Res 39:521–540
Lopes V, Park G, Cudney HH, Inman DJ (2000) Impedance-based structural health monitoring with artificial neural networks. J Intell Mater Syst Struct 11:206–216
Lu PJ, Hsu TC (2002) Application of autoassociative neural network on gas-path sensor data validation. J Propul Power 18:879–888
Maia NMM, Silva JMM (1997) Theoretical and experimental modal analysis. Research Studies Press, Letchworth
Marwala T (2000) Fault identification using neural networks and vibration data. PhD thesis, University of Cambridge
Marwala T (2001) Probabilistic fault identification using a committee of neural networks and vibration data. J Aircraft 38:138–146
Marwala T (2002) Finite element updating using wavelet data and a genetic algorithm. AIAA J Aircraft 39:709–711
Marwala T (2003) Fault classification using pseudo modal energies and neural networks. Am Inst Aeronaut Astronaut J 41:82–89
Marwala T (2004) Fault classification using pseudo modal energies and probabilistic neural networks. J Eng Mech 130:1346–1355
Marwala T (2007) Bayesian training of neural network using genetic programming. Pattern Recognit Lett 28:1452–1458
Marwala T (2010) Finite element model updating using computational intelligence techniques. Springer, London
Marwala T, Chakraverty S (2006) Fault classification in structures with incomplete measured data using autoassociative neural networks and genetic algorithms. Curr Sci 90:542–548
Marwala T, Hunt HEM (1999) Fault identification using finite element models and neural networks. Mech Syst Signal Proc 13:475–490
Marwala T, de Wilde P, Correia L, Mariano P, Ribeiro R, Abramov V, Szirbik N, Goossenaerts J (2001) Scalability and optimisation of a committee of agents using a genetic algorithm. In: Proceedings of the 2001 international symposium on soft computing and intelligence systems for Industry, Scotland
Michalewicz Z (1996) Genetic algorithms + data structures = evolution programs. Springer, New York
Mitchell M (1996) An introduction to genetic algorithms. MIT Press, Cambridge
Mohamed AK, Nelwamondo FV, Marwala T (2008) Estimation of missing data: neural networks, principal component analysis and genetic algorithms. In: Proceedings of the 12th world multi-conference on systems, cybern and inform, pp 36–41
Møller M (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 6:525–533
Mosalman Yazdi HA, Ramli Sulong NH (2001) Optimization of off-centre bracing system using genetic algorithm. J Constr Steel Res 67:1435–1441
Musharavati F, Hamoud ASM (2011) Modified genetic algorithms for manufacturing process planning in multiple parts manufacturing lines. Expert Syst Appl. doi:10.1016/j.eswa.2011.01.129
Neal RM (1993) Probabilistic inference using Markov Chain Monte Carlo methods. Technical Report CRG-TR-93-1, University of Toronto
Nelwamondo FV (2008) Computational intelligence techniques for missing data imputation. PhD thesis, University of the Witwatersrand
Nelwamondo FV, Marwala T (2007) Handling missing data from heteroskedastic and nonstationary data. Lect Notes Comput Sci 449:1297–1306
Oh S, Pedrycz W (2006) Genetic optimization-driven multi-layer hybrid fuzzy neural networks. Simulat Mod Pract Theory 14:597–613
Paluch B, Grédiac M, Faye A (2008) Combining a finite element programme and a genetic algorithm to optimize composite structures with variable thickness. Compos Struct 83:284–294
Park BJ, Choi HR, Kim HS (2003) A hybrid genetic algorithm for the job shop scheduling problems. Comput Ind Eng 45:597–613
Pawar PP, Ganguli R (2003) Genetic fuzzy system for damage detection in beams and helicopter rotor blades. Comput Meth Appl Mech Eng 192:2031
Pendharkar PC, Rodger JA (1999) An empirical study of non-binary genetic algorithm-based neural approaches for classification. In: Proceedings of the 20th international conference on information systems, pp 155–165
Perera R, Ruiz A, Manzano C (2009) Performance assessment of multi-criteria damage identification genetic algorithms. Comput Struct 87:120–127
Reddy RRK, Ganguli R (2003) Structural damage detection in a helicopter rotor using radial basis function neural networks. Smart Struct Mater 12:232–241
Reed RD, Marks RJ II (1999) Neural smithing: supervised learning in feedforward artificial neural networks. MIT Press, Cambridge
Ritter GX, Urcid G, Schmalz MS (2009) Autonomous single-pass end member approximation using lattice auto-associative memories. Neurocomputing 72:2101–2110
Roy T, Chakraborty D (2009) Optimal vibration control of smart fiber reinforced composite shell structures using improved a genetic algorithm. J Sound Vib 319:15–40
Royston TJ, Spohnholtz T, Ellington WA (2000) Use of non-degeneracy in nominally axisymmetric structures for fault detection with application to cylindrical geometries. J Sound Vibr 230:791–808
Sanz J, Perera R, Huerta C (2007) Fault diagnosis of rotating machinery based on auto-associative neural networks and wavelet transforms. J Sound Vibr 302:981–999
Stern H, Chassidim Y, Zofi M (2006) Multi-agent visual area coverage using a new genetic algorithm selection scheme. Eur J Oper Res 175:1890–1907
Suresh S, Omkar SN, Ganguli R, Mani V (2004) Identification of crack location and depth in a centilever beam using a modular neural network approach. Smart Mater Struct 13:907–916
Tettey T, Marwala T (2006) Controlling interstate conflict using neuro-fuzzy modeling and a genetic algorithms. In: Proceedings of the 10th IEEE international conference on intelligent engineering systems, pp 30–44
Tu Z, Lu Y (2008) Finite element model updating using artificial boundary conditions with genetic algorithms. Comput Struct 86:714–727
Upadhyaya BR, Eryurek E (1992) Application of neural networks for sensor validation and plant monitoring. Nuclear Technol 97:170–176
Vose MD (1999) The simple genetic algorithm: foundations and theory. MIT Press, Cambridge
Waszczyszyn Z, Ziemianski L (2001) Neural networks in mechanics of structures and materials – new results and prospects of applications. Comput Struct 79:2261–2276
Wu X, Ghaboussi J, Garret JH (1992) Use of neural networks in the detection of structural damage. Comput Struct 42:649–659
Zang C, Imregun M (2001) Combined neural network and reduced FRF techniques for slight damage detection using measured response data. Arch Appl Mech 71:525–536
Zhang H, Ishikawa M (2004) A solution to combinatorial optimization with time-varying parameters by a hybrid genetic algorithm. Int Congr Ser 1269:149–152
Zhou HF, Ni YQ, Ko JM (2011) Structural damage alarming using auto-associative neural network technique: exploration of environment-tolerant capacity and setup of alarming threshold. Mech Syst Signal Proc 25:1508–1526
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag London Limited
About this chapter
Cite this chapter
Marwala, T. (2012). Condition Monitoring with Incomplete Information. In: Condition Monitoring Using Computational Intelligence Methods. Springer, London. https://doi.org/10.1007/978-1-4471-2380-4_9
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2380-4_9
Published:
Publisher Name: Springer, London
Print ISBN: 978-1-4471-2379-8
Online ISBN: 978-1-4471-2380-4
eBook Packages: EngineeringEngineering (R0)