Loads location identification of fiber optic smart structures based on Genetic Algorithm-Support Vector Regression

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Lingbin Shen, Zhimin Zhao Loads location identification of fiber optic smart structures based on Genetic Algorithm-Support Vector Regression (Определение локализации нагрузки, приложенной к оптоволоконному смарт-композиту, вычислением регрессии опорных векторов с использованием генетического алгоритма) [на англ. яз.] // Оптический журнал. 2017. Т. 84. № 9. С. 71–78.

Lingbin Shen, Zhimin Zhao Loads location identification of fiber optic smart structures based on Genetic Algorithm-Support Vector Regression (Определение локализации нагрузки, приложенной к оптоволоконному смарт-композиту, вычислением регрессии опорных векторов с использованием генетического алгоритма) [in English] // Opticheskii Zhurnal. 2017. V. 84. № 9. P. 71–78.

For citation (Journal of Optical Technology):

Lingbin Shen and Zhimin Zhao, "Load location identification of fiber optic smart structures based on a genetic algorithm–support vector regression," Journal of Optical Technology. 84(9), 635-641 (2017). https://doi.org/10.1364/JOT.84.000635

Abstract:

A load location identification method of fiber optic smart structures based on a prototype data acquisition system was proposed. It employed genetic algorithm — support vector regression to estimate X, Y coordinates of loads loading on a composite panel. The panel is embedded with 8 sensors. When loads act on any position of smart composite structures, the output values of embedded fiber near the loading position will change. The 8-changed signals are the features of genetic algorithm — support vector regression. The data acquisition center collects the features as the data samples. Data samples are divided into training set, validation set and testing set. Then support vector regression model was established by using the training set and validation set and the parameters were optimized by genetic algorithm. The study compared the prediction accuracy between genetic algorithm — support vector regression model and back propagation model. The comparison results showed that the prediction accuracy of testing set was 85.78% and it is better than the back propagation neuralnetwork prediction model. This paper demonstrates that using genetic algorithm — support vector regression model to identify loads is not only stable and feasible, but also with high precision. The presented method in this paper is significant for the health monitoring and damage identification of composite materials in future.

Keywords:

optical fiber sensors, genetic algorithm — support vector regression, loads location, smart composite structures

Acknowledgements:

This study was supported by the National Natural Science Foundation of China (No. 61475071), Postdoctoral Fund of China (No. 2013M531346), Funding for outstanding Doctoral Dissertation in NUAA (No. BCXJ14-13), Funding of Jiangsu Innovation Program for Graduate Education (No. KYLX_0245, the Fundamental Research Funds for the Central Universities), Funding of Jiangsu Innovation Program for Graduate Education (No. KYLX_0246, the Fundamental Research Funds
for the Central Universities), Project supported by the Jiangsu Key Laboratory of Spectral Imaging & Intelligent sense (No. 30920130122003).

OCIS codes: 060.2370

References:

1. Hao K.A., Wang Z.Q., Zhou L.M. The research of low speed impact properties of different layer depth composites and damage pattern // Appl. Mathematics and Mechanics. 2013. V. 34. Is. 7. P. 661–671.
2. Hutchins D.A., Billson D.R., Bradley R.J., Ho K.S. Structural health monitoring using polymer-based capacitive micromachined ultrasonic transducers (CMUTs) // Ultrasonics. 2011. V. 51. P. 870–877.

3. Haywood J., Coverley P.T., Staszewski W.J., Worden K. An automatic impact monitor for a composite panel employing smart sensor technology // Smart Materials and Structures. 2005. V. 14. P. 265–271.
4. Kang L.H. Vibration and impact monitoring of a composite-wing model using piezoelectric paint // Advanced Composite Materials. 2014. V. 23. Is. 1. P. 73–84.
5. Bethoux O., Godoy E., Roche I., Naccari B., Taleb M.A., Koteiche M., Nassif Y. A new state-observer of inner PEM fuel cell pressures for enhanced system monitoring // Europ. Physical J. Appl. Phys. 2014. V. 66. Is. 3. P. 30901.
6. Phang S.W., Yang H.Z., Harun S.W., Arof H., Ahmad H. Simple fiber optic sensor based on tapered fiber for aliphatic alcohol detection // J. Optoelectronics and Advanced Materials. 2011. V. 13. Is. 5–6. P. 604–608.
7. Abdullah M., Bidin N., Yasin M., Pujiyanto, Harun S.W., Shaharin M.S. Fiber optic displacement sensor for thickness measurement based on transmission and of transparent plate // J. Optoelectronics and Advanced Materials. 2014. V. 16. Is. 5–6. P. 665–671.
8. Ebrahim M., Ashraf A., Amir A. Evaluation of fiber optic sensors for remote health monitoring of bridge structures // Materials and Structures. 2009. V. 42. P. 183–199.
9. Zhao L.H., Wang K.Q., Wang Y.Q., Shi L. BP network — based damage detection for composites // Instrumentation and Measurement. 2005. V. 24. Is. 2. P. 58–60.
10. Yang Y. The research of damage location for optical fiber sensor based on neural network // J. Wuhan University of Technology. 2006. V. 28. Is. 11. P. 5–8.
11. Tan W.J. Application of optical fiber sensing technology for positioning and evaluating damage in smart materials and structures // Inform. Technol. 2007. V. 11. P. 56–58.
12. Song Cui, Yeng Chai Soh. Linearity indices and linearity improvement of 2-D tetralateral position-senstitive detector // IEEE Trans. Electron. Devices. 2010. V. 57. Is. 9. P. 2310–2316.
13. Lu J.Y., Wang B.F., Liang D.K. Identification of impact location by using FBG based on wavelet feature extraction and SVR // Optics and Precision Engineering. 2012. V. 20. Is. 4. P. 712–718.
14. Shamshirband S., Petkovic D., Pavlovic N.T., CH S., Altameem T.A., Gani A. Support vector machine firefly algorithm based optimization of lens system // Appl. Opt. 2015. V. 54. Is. 1. P. 37–45.
15. Rahman M.M., Desai B.C., Bhattacharya P. Medical image retrieval with probabilistic multi-class support vector machine classifiers and adaptive similarity fusion // Computerized Medical Imaging and Graphics. 2008. V. 32. Is. 2. P. 95–108.
16. Akay M.F., Abasikeles I. Predicting the performance measures of an optical distributed shared memory multiprocessor by using support vector regression // Expert System with Application. 2010. V. 37. Is. 9. P. 6293–6301.
17. Niu P.F., Zhang W.P. Model of turbine optimal initial pressure under off-design operation based on SVR and GA // Neurocomputing. 2012. V. 78. Is. 1. P. 64–71.
18. Ma L. Semi-supervised regression based on particle swarm optimization and support vector machine // Electron. Sci. and Technol. 2013. V. 26. Is. 9. P. 10–13.
19. Terukuni S., Hidenori A. Optimal placement of SVRs considering multiple loads // Electrical Engineering in Japan. 2013. V. 182. Is. 1. P. 39–47.
20. Emre C., Ahmet A. A new training method for support vector machines：Clustering k-NN support vector machines // Expert Systems with Applications. 2008. V. 35. Is. 3. P. 564–568.
21. Pourbasheer E., Riahi S., Gsnjali M.R., Norouzi P. Application of genetic algorithm-support vector machine (GA-SVM) for prediction of BK-channels activity // Europ. J. Medicinal Chemistry. 2009. V. 44. Is.12. P. 5023–5028.
22. Liu Y.L., Wang Z.Y., Zhu H.N., Gao X.R. Gain optimization of fiber optical parametric amplifier based on genetic algorithm with pump depletion // Appl. Opt. 2013. V. 52. Is. 31. P. 7445–7448.
23. Kessal A., Rahmani L. GA-optimized parameters of sliding-mode controller based on both output voltage and input current with an application in the PFC of AC/DC converters // IEEE Trans. Power Electronics. 2014. V. 29. Is. 6. P. 3159–3165.
24. Zhang Q.L., Cheng J., Chen Q.S., Hu W., Zhou B.H. Prediction of backfill drill-hole life based on combined model of GA-SVM and neural network // Sci. & Technol. Rev. 2013. V. 31. Is. 34. P. 34–38.
25. Liu H.L., Liu H.D. Partial discharge localization in power transformers based on the sequential quadratic programming-genetic algorithm adopting acoustic emission techniques // Europ. Phys. J. Appl. Phys. 2014. V. 68. Is. 1. P. 10801.
26. Wang Y.T., Zheng L.J., Zhang Y. The optical fiber sensing technology and application // Beijing University of Aeronautics and Astronautics Press. Beijing. 2009. P. 67–71.
27. Zhao H.B. A study on evolutionary support vector machine based on genetic algorithm // J. Shaoxing University. 2004. V. 24. Is. 9. P. 25–28.