بهینه‌سازی انتخاب ویژگی‌ها در کلان داده‌های حاصل از پایش سلامت سازه با استفاده از الگوریتم فراکاوشی
نویسندگان
دانشکده مهندسی عمران، دانشگاه سیستان و بلوچستان، زاهدان
چکیده
پژوهش حاضر به مبحث کلان داده‌ها در حوزه پایش سلامت سازه‌ها می‌پردازد. بدین منظور، بعد از استخراج ویژگیهای پاسخ شتاب سازه، با استفاده از الگوریتم بهینه‌ساز ویژگیهای کم‌اثر و اضافی حذف می‌شوند و با انتخاب ویژگیهای تاثیرگذار و کاهش ابعاد داده‌ها دقت و سرعت روند عیب‌یابی سازه‌ها افزایش می‌یابد. انتخاب زیرمجموعه‌ای از ویژگی‌ها با استفاده از الگوریتم فراکاوشی هارمونی-پرندگان پیشنهادی در این پژوهش صورت خواهد پذیرفت که موجب افزایش تطبیق‌پذیری روند پیشنهادی در مواجه با کلان داده‌های ناشی از حسگرها و عدم قطعیت‌های ناشی از اختلال در داده‌های ورودی می‌شود. در روش پیشنهادی، برای استخراج ویژگیهای پاسخ شتاب از شاخص‌های مبتنی بر خصوصیات آماری و انرژی بسته‌های موجکی استفاده شده است. به‌علاوه از دو الگوریتم ماشین‌بردار پشتیبان حداقل مربعات موجکی وزن‌دار و شبکه عصبی تابع پایه شعاعی به‌عنوان مدل جایگزین تحلیل اجزای محدود سازه استفاده شده و با استفاده از آنها شدت و مکان خرابی در سازه‌ها شناسایی می‌شود. به‌عنوان مسائل کاربردی، عیب‌یابی سازه بنچ مارک گروه پایش سلامت سازه IASC-ASCE و سازه فضاکار ۱۲۰ عضوی مدنظر قرار گرفته است. نتایج نشان می‌دهد که انرژی بسته‌های موجکی حساسیت بالاتری نسبت به وجود خرابی در سازه نسبت به خصوصیات آماری دارد. به‌علاوه مقایسه الگوریتم ترکیبی هارمونی-پرندگان ارائه شده با چهار الگوریتم مطرح در حوزه عیب‌یابی، نشان‌دهنده سرعت و بازدهی بهتر این الگوریتم است. درنهایت استفاده از روش پیشنهادی موجب کاهش ۹۰ درصدی ابعاد داده‌ها در روند پایش سلامت سازه‌ها می‌شود
کلیدواژه‌ها
عنوان مقاله [English]
Feature Selection in Structural Health Monitoring Big Data Using a Meta-Heuristic Optimization Algorithm
نویسندگان [English]
- R. Ghiasi
- M. R. Ghasemi
This paper focuses on the processing of structural health monitoring (SHM) big data. Extracted features of a structure are reduced using an optimization algorithm to find a minimal subset of salient features by removing noisy, irrelevant and redundant data. The PSO-Harmony algorithm is introduced for feature selection to enhance the capability of the proposed method for processing the measured big data, which have been collected from sensors of the structure and uncertainties associated with this process. Structural response signals under ambient vibration are preprocessed according to wavelet packet decomposition (WPD) and statistical characteristics for feature extraction. It optimizes feature vectors to be used as inputs to surrogate models based on the wavelet weighted support vector machine (WWLS-SVM) and radial basis function neural network (RBFNN). Two illustrative test examples are considered, the benchmark dataset from IASC-ASCE SHM group and a 120-bar dome truss. The results indicate that the features acquired by WPT from vibrational signal have higher sensitivity to the damage of the structure. Furthermore, the proposed PSO-Harmony is compared with four well-known metaheuristic optimization algorithms. The obtaind results show that the proposed method has a better performance and convergence rate. Finally, the proposed feature subset selection method has the capability of 90% data reduction
کلیدواژه‌ها [English]
- Structural health monitoring
- Big data
- Surrogate model
- PSO-harmony algorithm
- Wavelet packet decomposition
1. Boller, C., Chang, F.K., and Fujino, Y., Encyclopedia of Structural Sealth Monitoring, John Wiley & Sons, 2009.
2. Ghiasi, R., Ghasemi, M. R. and Sohrabi, M. R., “Structural Damage Detection using Frequency Response Function Index and Surrogate Model Based on Optimized Extreme Learning Machine Algorithm,” Journal of Computational Methods In Engineering, Vol. 36, No. 1, pp. 1-17, 2017 (in persian).
3. Ghodrati Amir, G. and Zare Hosseinzadeh, A., “Damage Identification in Shear Frames via Grey Relation Theory and Static Displacement Estimated by Limited Modal Data, ”Journal of Computational Methods in Engineering, Vol. 34, No. 1, pp. 139–154, 2015 (in persian).
4. Fan, W., and Qiao, P., “Vibration-based Damage Identification Methods: A Review and Comparative Study”, Structural Health Monitoring, Vol. 10, No. 1, pp. 83–111, 2011.
5. Das, S., Saha, P., and Patro, S. K., “Vibration-based Damage Detection Techniques Used for Health Monitoring of Structures: A Review”, Journal of Civil Structural Health Monitoring, Vol. 6, pp. 477–507, 2016.
6. Hakim, S. J. S., and Razak, H. A., “Modal Parameters Based Structural Damage Detection Using Artificial Neural Networks-A Review”, Smart Structure and Systems, Vol. 14, No. 2, pp. 159–189, 2014.
7. Matarazzo, T. J., Shahidi, S. G., Chang, M., and Pakzad, S. N., “Are Today’s SHM Procedures Suitable For Tomorrow’s BIGDATA”, In Structural Health Monitoring and Damage Detection, Vol. 7, pp. 59–65, 2015.
8. Morabito, V., Big Data and Analytics, Springer International Publishing, 2015.
9. Matarazzo, T. J., and Pakzad, S. N., “Truncated Physical Model for Dynamic Sensor Networks with Applications In High-Resolution Mobile Sensing And BIGDATA”, Journal of Engineering Mechanics, Vol. 142, No. 5, pp. 1–13, 2016.
10. Kashef, S. And Nezamabadi-Pour, H., “An Advanced ACO Algorithm for Feature Subset Selection”, Neurocomputing, Vol. 147, pp. 271–279, 2015.
11. Liu, H. And Yu, L., “Toward Integrating Feature Selection Algorithms for Classification and Clustering”, IEEE Transaction Knowledge and Data Engineering, Vol. 17, No. 4, pp. 491–502, 2005.
12. Ghiasi, R., Ghasemi, M. R. and Noori, M., “Comparative Studies of Metamodeling and AI-Based Techniques in Damage Detection of Structures”, Advances in Engineering Software, Vol. 125, pp. 101–112, 2018.
13. Han, J. G., Ren, W. X. and Sun, Z. S., "Wavelet Packet Based Damage Identification of Beam Structures." International Journal of Solids and Structures, Vol. 42, No. 26, pp. 6610-6627, 2005.
14. Ghiasi, R., Torkzadeh, P. and Noori, M., “A Machine-Learning Approach for Structural Damage Detection Using Least Square Support Vector Machine Based on a New Combinational Kernel Function”, Structural Health Monitoring, Vol. 15 , No. 3 , PP. 302–316, 2016.
15. Farrar, C. R., and Worden, K., Structural Health Monitoring: A Machine Learning Perspective, John Wiley & Sons, 2012.
16. Laney, D., “3D Data Management: Controlling Data Volume, Velocity and Variety”, META Group Research Note 6, No. 70, pp. 1, 2001.
17. Ivanov, T., Korfiatis, N., and Zicari, R. V., “on The Inequality of the 3V's of Big Data Architectural Paradigms: A Case for Heterogeneity”, Arxiv Preprint Arxiv:1311.0805, 2013.
18. Bilal, M., Oyedele, L. O., Qadir, J., Munir, K., Ajayi, S. O., Akinade, O. O., Owolabi, H. A., Alaka, H. A. and Pasha, M., “Big Data in the Construction Industry: A Review of Present Status, Opportunities, and Future Trends”, Advanced Engineering Informatics, Vol. 30, No. 3, pp. 500–521, 2016.
19. Malekzadeh, M., and Catbas, F. N. “A Machine Learning Framework for Automated Functionality Monitoring of Movable Bridges”, In Dynamics of Civil Structures, Vol. 2, pp. 57–63, 2016.
20. Zhong, L., Song, H., and Han, B. “Extracting Structural Damage Features: Comparison between PCA and ICA”, Proceedings of International Conference on Intelligent Computing, ICIC 2006 Kunming, China, pp. 840-845, 2006.
21. Liu, Y. Y., Ju, Y. F., Duan, C. D. and Zhao, X. F., ”Structure Damage Diagnosis Using Neural Network and Feature Fusion”, Engineering Applications of Artificial Intelligence, Vol. 24, No. 1, pp. 87-92, 2011.
22. Cortes, C. and Vapnik, V., ”Support-Vector Networks”, Machine Learning, Vol. 20, No. 3, pp. 273-297, 1995.
23. Suykens, J. A., De Brabanter, J., Lukas, L. and Vandewalle, J., “Weighted Least Squares Support Vector Machines: Robustness and Sparse Approximation” Neurocomputing, Vol. 48, No. 1-4, pp. 85-105, 2002.
24. Daubechies, I., Ten Lectures on Wavelets, SIAM, Pennsylvania, 1992.
25. Geem, Z. W, Kim, J. H., and Loganathan. G. V. “A New Heuristic Optimization Algorithm: Harmony Search”, Simulation, Vol. 76, No. 2, pp. 60-68, 2001.
26. Kennedy J. Particle Swarm Optimization, In Encyclopedia of Machine Learning, pp. 760-766. Springer, Boston, MA, 2011.
27. Nguyen N. T, Lee H. H, and Kwon J. M. “Optimal Feature Selection Using Genetic Algorithm For Mechanical Fault Detection of Induction Motor”, Journal of Mechanical Science and Technology, Vol. 22, No. 3, pp. 490-496, 2008.
28. Johnson, E. A., Lam, H. F, Katafygiotis, L. S., and Beck J. L. “Phase I IASC-ASCE Structural Health Monitoring Benchmark Problem Using Simulated Data”, Journal of Engineering Mechanics, Vol. 130, No. 1, pp. 3-15, 2004.
29. Yang, X. A New Metaheuristic Bat-Inspired Algorithm, Proceedings of Nature inspired Cooperative Strategies for Optimization (NICSO 2010), Granada, Spain, pp. 65-74, 2010.
30. Kaveh, A., and Mahdavi. V., R., “Colliding Bodies Optimization: A Novel Meta-Heuristic Method”, Computers & Structures Vol. 139, pp. 18-27, 2014.
31. Kaveh, A., and Talatahari, S., “Particle Swarm Optimizer, Ant Colony Strategy and Harmony Search Scheme Hybridized for Optimization of Truss Structures”, Computers & Structures, Vol. 87, No. 5-6, pp. 267-283, 2009.
32. Mckenna, F., Fenves, G. L. and Scott, M. H., Open System For Earthquake Engineering Simulation, University of California, Berkeley, CA, 2000.
2. Ghiasi, R., Ghasemi, M. R. and Sohrabi, M. R., “Structural Damage Detection using Frequency Response Function Index and Surrogate Model Based on Optimized Extreme Learning Machine Algorithm,” Journal of Computational Methods In Engineering, Vol. 36, No. 1, pp. 1-17, 2017 (in persian).
3. Ghodrati Amir, G. and Zare Hosseinzadeh, A., “Damage Identification in Shear Frames via Grey Relation Theory and Static Displacement Estimated by Limited Modal Data, ”Journal of Computational Methods in Engineering, Vol. 34, No. 1, pp. 139–154, 2015 (in persian).
4. Fan, W., and Qiao, P., “Vibration-based Damage Identification Methods: A Review and Comparative Study”, Structural Health Monitoring, Vol. 10, No. 1, pp. 83–111, 2011.
5. Das, S., Saha, P., and Patro, S. K., “Vibration-based Damage Detection Techniques Used for Health Monitoring of Structures: A Review”, Journal of Civil Structural Health Monitoring, Vol. 6, pp. 477–507, 2016.
6. Hakim, S. J. S., and Razak, H. A., “Modal Parameters Based Structural Damage Detection Using Artificial Neural Networks-A Review”, Smart Structure and Systems, Vol. 14, No. 2, pp. 159–189, 2014.
7. Matarazzo, T. J., Shahidi, S. G., Chang, M., and Pakzad, S. N., “Are Today’s SHM Procedures Suitable For Tomorrow’s BIGDATA”, In Structural Health Monitoring and Damage Detection, Vol. 7, pp. 59–65, 2015.
8. Morabito, V., Big Data and Analytics, Springer International Publishing, 2015.
9. Matarazzo, T. J., and Pakzad, S. N., “Truncated Physical Model for Dynamic Sensor Networks with Applications In High-Resolution Mobile Sensing And BIGDATA”, Journal of Engineering Mechanics, Vol. 142, No. 5, pp. 1–13, 2016.
10. Kashef, S. And Nezamabadi-Pour, H., “An Advanced ACO Algorithm for Feature Subset Selection”, Neurocomputing, Vol. 147, pp. 271–279, 2015.
11. Liu, H. And Yu, L., “Toward Integrating Feature Selection Algorithms for Classification and Clustering”, IEEE Transaction Knowledge and Data Engineering, Vol. 17, No. 4, pp. 491–502, 2005.
12. Ghiasi, R., Ghasemi, M. R. and Noori, M., “Comparative Studies of Metamodeling and AI-Based Techniques in Damage Detection of Structures”, Advances in Engineering Software, Vol. 125, pp. 101–112, 2018.
13. Han, J. G., Ren, W. X. and Sun, Z. S., "Wavelet Packet Based Damage Identification of Beam Structures." International Journal of Solids and Structures, Vol. 42, No. 26, pp. 6610-6627, 2005.
14. Ghiasi, R., Torkzadeh, P. and Noori, M., “A Machine-Learning Approach for Structural Damage Detection Using Least Square Support Vector Machine Based on a New Combinational Kernel Function”, Structural Health Monitoring, Vol. 15 , No. 3 , PP. 302–316, 2016.
15. Farrar, C. R., and Worden, K., Structural Health Monitoring: A Machine Learning Perspective, John Wiley & Sons, 2012.
16. Laney, D., “3D Data Management: Controlling Data Volume, Velocity and Variety”, META Group Research Note 6, No. 70, pp. 1, 2001.
17. Ivanov, T., Korfiatis, N., and Zicari, R. V., “on The Inequality of the 3V's of Big Data Architectural Paradigms: A Case for Heterogeneity”, Arxiv Preprint Arxiv:1311.0805, 2013.
18. Bilal, M., Oyedele, L. O., Qadir, J., Munir, K., Ajayi, S. O., Akinade, O. O., Owolabi, H. A., Alaka, H. A. and Pasha, M., “Big Data in the Construction Industry: A Review of Present Status, Opportunities, and Future Trends”, Advanced Engineering Informatics, Vol. 30, No. 3, pp. 500–521, 2016.
19. Malekzadeh, M., and Catbas, F. N. “A Machine Learning Framework for Automated Functionality Monitoring of Movable Bridges”, In Dynamics of Civil Structures, Vol. 2, pp. 57–63, 2016.
20. Zhong, L., Song, H., and Han, B. “Extracting Structural Damage Features: Comparison between PCA and ICA”, Proceedings of International Conference on Intelligent Computing, ICIC 2006 Kunming, China, pp. 840-845, 2006.
21. Liu, Y. Y., Ju, Y. F., Duan, C. D. and Zhao, X. F., ”Structure Damage Diagnosis Using Neural Network and Feature Fusion”, Engineering Applications of Artificial Intelligence, Vol. 24, No. 1, pp. 87-92, 2011.
22. Cortes, C. and Vapnik, V., ”Support-Vector Networks”, Machine Learning, Vol. 20, No. 3, pp. 273-297, 1995.
23. Suykens, J. A., De Brabanter, J., Lukas, L. and Vandewalle, J., “Weighted Least Squares Support Vector Machines: Robustness and Sparse Approximation” Neurocomputing, Vol. 48, No. 1-4, pp. 85-105, 2002.
24. Daubechies, I., Ten Lectures on Wavelets, SIAM, Pennsylvania, 1992.
25. Geem, Z. W, Kim, J. H., and Loganathan. G. V. “A New Heuristic Optimization Algorithm: Harmony Search”, Simulation, Vol. 76, No. 2, pp. 60-68, 2001.
26. Kennedy J. Particle Swarm Optimization, In Encyclopedia of Machine Learning, pp. 760-766. Springer, Boston, MA, 2011.
27. Nguyen N. T, Lee H. H, and Kwon J. M. “Optimal Feature Selection Using Genetic Algorithm For Mechanical Fault Detection of Induction Motor”, Journal of Mechanical Science and Technology, Vol. 22, No. 3, pp. 490-496, 2008.
28. Johnson, E. A., Lam, H. F, Katafygiotis, L. S., and Beck J. L. “Phase I IASC-ASCE Structural Health Monitoring Benchmark Problem Using Simulated Data”, Journal of Engineering Mechanics, Vol. 130, No. 1, pp. 3-15, 2004.
29. Yang, X. A New Metaheuristic Bat-Inspired Algorithm, Proceedings of Nature inspired Cooperative Strategies for Optimization (NICSO 2010), Granada, Spain, pp. 65-74, 2010.
30. Kaveh, A., and Mahdavi. V., R., “Colliding Bodies Optimization: A Novel Meta-Heuristic Method”, Computers & Structures Vol. 139, pp. 18-27, 2014.
31. Kaveh, A., and Talatahari, S., “Particle Swarm Optimizer, Ant Colony Strategy and Harmony Search Scheme Hybridized for Optimization of Truss Structures”, Computers & Structures, Vol. 87, No. 5-6, pp. 267-283, 2009.
32. Mckenna, F., Fenves, G. L. and Scott, M. H., Open System For Earthquake Engineering Simulation, University of California, Berkeley, CA, 2000.
)