شبیه‌سازی شتاب‌نگاشت مصنوعی زلزله سازگار با طیف ساختگاه با استفاده از تحلیل سری‌های زمانی

نوع مقاله : علمی - پژوهشی

نویسندگان

1 دانشجوی دکتری مهندسی کامپیوتر، دانشکده مهندسی کامپیوتر و فناوری اطلاعات، دانشگاه صنعتی شاهرود، شاهرود، ایران

2 دانشیار، دانشکده مهندسی برق، دانشگاه صنعتی شاهرود، شاهرود، ایران

3 استاد، دانشکده مهندسی کامپیوتر و فناوری اطلاعات، دانشگاه صنعتی شاهرود، شاهرود، ایران

4 استادیار، دانشکده مهندسی عمران، دانشگاه صنعتی شاهرود، شاهرود، ایران

چکیده

در طراحی سازه‌های مهم و حیاتی مانند سدها، نیروگاه‌ها و پل‌ها، لزوم انجام تحلیل تاریخچه زمانی لرزه‌ای یکی از مهم‌ترین نیازهای مهندسی می‌باشد. با توجه به اینکه شتاب‌نگاشت­های واقعی مربوط به ساختگاه این سازه‌ها در بسیاری از موارد وجود ندارد و یا به تعداد کافی در دسترس نیست، لذا تولید شتاب‌نگاشت مصنوعی یکی از موضوعات مهم پژوهشی و کاربردی در این زمینه می‌باشد. این مقاله به ارائه روشی نوین برای تولید شتابنگاشت‌های مصنوعی منطبق با طیف ساختگاه سازه با استفاده از تحلیل سری‌های زمانی، شبکه­های عصبی مصنوعی، تبدیل موجک و الگوریتم ژنتیک می‌پردازد. در روش پیشنهادی ابتدا تعدادی شتاب‌نگاشت ثبت شده در ایستگاه‌های شتاب‌نگاری و بر اساس نوع خاک انتخاب می‌شوند. این خاک‌ها با توجه به سرعت موج برشی ایستگاه‌های ثبت کننده به دو گروه خاک و سنگ تقسیم می‌شوند و سپس با استفاده از تبدیل موجک به تحلیل  و پردازش  آنها پرداخته می‌شود. در قدم بعدی از توانایی یادگیری شبکه­های عصبی برای نگاشت معکوس از طیف پاسخ این شتابنگاشت‌ها به ضرایب تبدیل ویولتی استفاده می‌گردد.  به موازات استفاده از الگوریتم­های آموزشی موجود برای شبکه­های عصبی، از توانایی الگوریتم ژنتیک برای جستجو در یک فضای گسترده کمک گرفته می‌شود تا ماتریس‌های وزن و بایاس شبکه­ها بهینه گردند و از محبوس شدن شبکه­ها در نقاط بهینه محلی جلوگیری به عمل آید. در نهایت شتابنگاشت‌های سازگار با طیف ساختگاه تولید می‌شود. در این مقاله با ارائه مثال‌هایی از شتابنگاشت­های ثبت شده در ایران، به آزمایش الگوریتم پیشنهادی پرداخته شده و کارایی موثر آن نشان داده می­شود. استفاده ترکیبی از شبکه عصبی مصنوعی، تبدیل موجک، الگوریتم ژنتیک و تحلیل سری‌های زمانی موجب ارتقاء توانایی روش از نظر سرعت و دقت در تولید شتاب‌نگاشت مصنوعی سازگار با طیف برای شرایط ساختگاهی مختلف می‌شود

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Simulation of artificial earthquake records compatible with site specific response spectra using time series analysis

نویسندگان [English]

  • Mohammad Reza Fadavi Amiri 1
  • Sayed Ali Soleymani Eyvari 2
  • Hamid Hasanpoor 3
  • Mohammad Shamekhi Amiri 4
1 PhD Student of Computer Engineering, School of Computer and Information Technology, Shahrood University of Technology, Shahrood, Iran
2 Associate Professor,School of Electrical Engineering, Shahrood University of Technology, Shahrood, Iran
3 Professor, School of Computer & Information Technology, Shahrood University of Technology, Shahrood, Iran
4 Assistant Professor, School of Civil Engineering, Shahrood University of Technology, Shahrood, Iran
چکیده [English]

Time history analysis of infrastructures like dams, bridges and nuclear power plants is one of the fundamental parts of their design process. But there are not sufficient and suitable site specific earthquake records to do such time history analysis; therefore, generation of artificial accelerograms is required for conducting research works in this area.  Using time series analysis, wavelet transforms, artificial neural networks and genetic algorithm, a new method is introduced to produce artificial accelerograms compatible with response spectra for the specified site condition. In the proposed method, first, some recorded accelerograms are selected based on the soil condition at the recording station. The soils in these stations are divided into two groups of soil and rock according to their measured shear wave velocity. These accelerograms are then analyzed using wavelet transform. Next, artificial neural networks ability to produce reverse signal from response spectra is used to produce wavelet coefficients. Furthermore, a genetic algorithm is employed to optimize the network weight and bias matrices by searching in a wide range of values and prevent neural network convergence on local optima. At the end site specific accelerograms are produced. In this paper a number of recorded accelerograms in Iran are employed to test the neural network performances and to demonstrate the effectiveness of the method. It is shown that using synthetic time series analysis, genetic algorithm, neural network and wavelet transform will increase the capabilities of the algorithm and improve its speed and accuracy in generating accelerograms compatible with site specific response spectra for different site conditions.

کلیدواژه‌ها [English]

  • Spectrum Compatible Records
  • time series analysis
  • Genetic algorithm
  • Artificial Neural Network
  • wavelet transform
[1]       Iranian Code of Practice for Seismic Resistant Design of Buildings, Standard No. 2800 (4th Edition), Ministry of Roads and Urban Development, Iran, 2015.
[2]      Fadavi Amiri, M., Akbari, A. and Ghodrati Amiri, G. (2008), New Method for Generation of Artificial Earthquake Record , Proceedings of the 14th World Conference on Earthquake Engineering , Beijing, China, Oct. 12-17.
[3]      Priestley, M.B. (1967), "Power Spectral Analysis of Non-Stationary Random Processes", Journal of Sound and Vibration, Vol. 6, No. 1, 86-97.
[4]      Tajimi, H. (1960), "Statistical Method of Determining the Maximum Response of Building Structure during an Earthquake", Proceedings of the 2nd World Conference on Earthquake Engineering, 2, Tokyo and Kyoto, Japan, July 11-18.
[5]      Brune, J.N. (1970), "Tectonic Stress and Spectra of Seismic Shear Waves from Earthquakes", Journal of Geophysical Research, Vol. 75, No. 26, 4997-5009.
[6]      Fereydouni, H. (1999), "Review and Production of Artificial Accelerograms and its Associated Parameters", MSc Thesis, University of Tehran, Faculty of Engineering.
[7]      Bagheri, A. (2005), "Production of Artificial Accelerograms using Kanay-Tjymy Pattern and Wavelet Analysis", MSc Thesis, Iran University of Science and Technology, School of Civil Engineering.
[8]      Housner, G.W. and Jennings, P.C. (1964), "Generation of Artificial Earthquakes", Journal of Engineering Mechanics, ASCE, Vol. 90, Issue 1, 113–152.
[9]      Cohen, L. (1995), "Time-Frequency Analysis", Prentice Hall PTR. Englewood Cliffs, NJ.
[10]   Arfken G.B. and Weber H.J. (1995), "Mathematical Methods for Physicists", Academic Press, San Diego.
[11]   Kanai, K. (1957), "Semi-Empirical Formula for the Seismic Characteristics of the Ground Motion", Bulletin of Earthquake Research Institute, University of Tokyo, Vol. 35, No. 2, 309–325.
[12]   Fan, F.G. and Ahmadi, G. (1990), "Nonstationary Kanai-Tajimi Models for El Centro 1940 and Mexico City 1985 Earthquakes", Probabilistic Engineering Mechanics, Vol. 5, Issue 4, 171-181.
[13]   Ghodrati Amiri, G., Raeisi Dehkordi, M. and Bagheri, A. (2005), "Generation of Artificial Earthquake Records with a Nonstationary Kanai-Tajimi Model and Wavelet Transform", Proceedings of the International Symposium on Innovation & Sustainability of Structures in Civil Enginieering Including Seismic Engineering(ISISS'2005), Nanjing, China, November 20-22.
[14]   Fatemi, A.A., Bagheri, A., Ghodrati Amiri, G. and Ghafory-Ashtiany, M. (2012), "Generation of Uniform Hazard Earthquake Accelerograms and Near-Field Ground Motions." Journal of Earthquake and Tsunami, Vol. 6, No. 2,  12500013(17 pages).
[15]   Refooei, F.R., Mobarake, A. and Ahmadi, G. (2001), "Generation of Artificial Earthquake Records with a Nonstationary Kanai-Tajimi Model", Engineering Structures, Vol. 23, Issue 7, 827-837.
[16]   Olafsson, S. and Sigbjornsson, R. (1995), "Application of ARMA Models to Estimate Earthquake Ground Motion and Structural Response",  Earthquake Engineering & Structural Dynamics, Vol. 24, Issue 7, 951-966.
[17]   Mobarakeh, A.A., Rofooei, F.R. and Ahmadi, G. (2002), "Simulation of Earthquake Records Using Time-Varying Arma (2, 1) Model", Probabilistic Engineering Mechanics, Vol. 17, No. 1, 15-34.
[18]   Aghababaei, M. (1998), "Generation of Artificial Accelerograms using Kanai-Tajimi Model and Auto Regressive Moving Average Model (ARMA)", MSc Thesis, Sharif University of Technology, School of Civil Engineering.
[19]   Zhang, C.R., Chen, H.Q. and Li, M. (2007), "Earthquake Accelerogram Simulation with Statistical Law of Evolutionary Power Spectrum", Acta Seismologica Sinica, Vol. 20, Issue 4, 435-446.
[20]   Ebeling, R.M. (1992), "Introduction to the Computation of Response Spectrum for Earthquake Loading (No. WES-TR/ITL-92-4)”, Army Engineer Waterways Experiment Station Vicksburg MS Information Technology Lab.
[21]   Ghaboussi, J. and Lin, C.J. (1998), "New Method of Generation Spectrum Compatible Accelerograms using Neural Network", Earthquake Engineering & Structural Dynamics, Vol. 27, Issue 4, 377-396.
[22]   Amiri, G.G., Bagheri, A. and Seyed Razaghi, S.A. (2009), "Generation of Multiple Earthquake Accelerograms Compatible with Spectrum via the Wavelet Packet Transform and Stochastic Neural Networks", Journal of Earthquake Engineering, Vol. 13, No. 7, 899-915.
[23]   Mkrtychev, O.V. and Reshetov, A.A. (2013), "Using WaveletAnalysis toObtain Characteristics ofAccelerograms", Vestnik MGSU, Proceedings of Moscow State University of Civil Engineeering, No. 7, 59-67.
[24]   Soleymani Eyvari, S.A., Fadavi Amiri, M. and Marvi,  H. (2016), "New Method for Generation of Artificial Earthquake Record by New Model in Compression and Artificial Neural Networks", Journal of Modeling in Engineering, Vol. 14, No. 46, 77-90.
[25]   Asadi, A., Fadavi, M., Bagheri, A. and Ghodrati Amiri, G. (2011), "Application of Neural Networks and an Adapted Wavelet Packet for Generating Artificial Ground Motion", International Journal of Structural Engineering and Mechanics, Vol. 37, No. 6, 575-592.
[26]   Bargi, K., Kaveh, A., Lux, C. and Rahami, H. (2011), "Generation of Artificial Accelerograms using a Combination of Neural Networks and Wavelets", Sharif Civil Engineering Journal, Vol. 2-28, No. 3. 79-88.
[27]   Karami, M. and Shahryari, H. (2015), "Production of Artificial Accelerograms to Estimate the Incremental Dynamic Analysis Parameters", Modares Civil Engineering Journal, , Vol. 15, No. 2, 117-207.
[28]   Cacciola, P. and Zentner, I. (2012), "Generation of Response-Spectrum-Compatible Artificial Earthquake Accelerograms with Random Joint Time–Frequency Distributions", Probabilistic Engineering Mechanics, Vol. 28, 52-58.
[29]   Mitropoulou, C.C., Lagaros, N.D. and Papadrakakis, M. (2015), "Generation of Artificial Accelerograms for Efficient Life-Cycle Cost Analysis of Structures" Engineering Structures, Vol. 88, 138-153.
[30]   Batou, A. and Soize, C. (2013), "Generation of Accelerograms Compatible with Design Specifications uses Information Theory", Bulletin of Earthquake Engineering, Vol. 12, No. 2, 769-794.
[31]   Batou, A. and Soize, C. (2013), "Generation of Spectrum-Compatible Accelerograms using Information Theory", Vienna Congress on Recent Advances in Earthquake Engineering and Structural Dynamics 2013 (VEESD 2013).
[32]   Gurney, K. (1997), “An Introduction to Neural Networks”, CRC Press; First Edition.
[33]   Mitchell, M. (1995), “Genetic Algorithms: An Overview”, Complexity, Vol. 1, No. 1, 31-39.
[34]   Niroomand, H. and Bozorgnia, A. (1995), "Introduction to Time Series Analysis", Ferdowsi University of Mashhad Publications.
[35]   Zarfam, P. and Nikou, M. (2010), "Use of Time Series in Evolutionary Artificial Neural Networks to Evaluate the Vulnerability of Concrete Moment Frame", Journal of Civil Engineering, Islamic Azad University, Vol. 3, Issue 3, 17-26.
[36]   Ramazi, H. (1997), "Basic Accelerogram Data Record of Accelerograph Network of Iran", Building and Housing Research Center, Publication, No. 256, Tehran.