Reliability Prediction of SMRF Based on the Combination of Neural Network And Incremental Dynamic Analysis

Abstract

This paper conducts a comprehensive vulnerability analysis of steel structures, taking into account the stringent HAZUS restrictions. The demand distribution for each mode of failure takes the form of a normal logarithm after extracting the fragility chart. Thus, the two parameters of mean and standard deviation can be used to construct the fragility chart. A total of five modes of failure were used in this paper. Therefore, 10 unknown values were used to derive the fragility curves. Afterward, Incremental Dynamic Analysis (IDA) was used under 40 natural records to obtain the fragility curve. To save time in the analysis and prediction of structural responses, a neural network method was used to select records more efficiently. It was observed that this method is better than the analytical method in considering random uncertainty in steel structures when several acceleration values are used.

Keywords

• MLP algorithm
• Monte Carlo method
• Aleatory uncertainty
• Fragility curve
• IDA.

SMRF'nin Sinir Ağı ve Artımlı Dinamik Analizin Birleşimine Dayanan Güvenilirlik Tahmini

Öz

Bu makale, sıkı HAZUS kısıtlamalarını dikkate alarak çelik yapıların kapsamlı bir güvenlik açığı analizini yürütmektedir. Her başarısızlık türü için talep dağılımı, kırılganlık tablosunun çıkarılmasından sonra normal bir logaritma şeklini alır. Böylece, kırılganlık tablosunu oluşturmak için ortalama ve standart sapma olmak üzere iki parametre kullanılabilir. Bu yazıda toplam beş başarısızlık modu kullanıldı. Bu nedenle kırılganlık eğrilerini türetmek için 10 bilinmeyen değer kullanılmıştır. Daha sonra kırılganlık eğrisini elde etmek için 40 doğal kayıt altında Artımlı Dinamik Analiz (IDA) kullanılmıştır. Yapısal yanıtların analizinde ve tahmininde zaman kazanmak amacıyla, kayıtları daha verimli bir şekilde seçmek için bir sinir ağı yöntemi kullanılmıştır. Çeşitli ivme değerleri kullanıldığında çelik yapılarda rastgele belirsizliğin dikkate alınmasında bu yöntemin analitik yönteme göre daha iyi olduğu görülmüştür.

Anahtar Kelimeler

• MLP algoritması
• Monte Carlo yöntemi
• Rastgele belirsizlik
• Kırılganlık eğrisi
• IDA.

References

1. 2800 SN. (2007). Iranian Code of Practice for Seismic Resistant Design of Buildings. Iran: Building and Housing Research Center.
2. Baker J. W, Allin Cornell. C. (2005). A Vector‐Valued Ground Motion Intensity Measure Consisting of Spectral Acceleration and Epsilon. Earthquake Engineering & Structural Dynamics, 34(10), 1193-1217.
3. Celarec D, Dolšek M. (2013). The Impact of Modelling Uncertainties on the Seismic Performance Assessment of Reinforced Concrete Frame Buildings. Engineering Structures, 52, 340-354.
4. FEMA F. (2003). Hazus-Mh-Mr1. Multi-Hazard Loss Estimation Methodology.
5. Foutch. D. A. (2000). State of Art Report on Performance Prediction and Evaluation of Moment-Resisting Steel Frame Structures. SAC Rep. No. FEMA 355f.
6. Jough. F. K. G, Şensoy S. (2016). Prediction of Seismic Collapse Risk of Steel Moment Frame Mid-Rise Structures By Meta-Heuristic Algorithms. Earthquake Engineering and Engineering Vibration, 15(4), 743-757.
7. Karimi ghaleh jough F, Veghar M, Beheshti-Aval, S. B. (2021). Epistemic Uncertainty Treatment Using Group Method of Data Handling Algorithm in Seismic Collapse Fragility. Latin American Journal of Solids and Structures, 18,355.
8. Karimi Ghaleh Jough F, Ghasemzadeh B. (2023). Uncertainty Interval Analysis of Steel Moment Frame by Development of 3D-Fragility Curves Towards Optimized Fuzzy Method. Arab J Sci Eng https://doi.org/10.1007/s13369-023-08223-8.

9. Karimi Ghaleh Jough F, Şensoy S. (2020). Steel Moment-Resisting Frame Reliability via the Interval Analysis by FCM-PSO Approach Considering Various Uncertainties. Journal of Earthquake Engineering, 24(1), 109-128.
10. Karimi Ghaleh Jough. F, Beheshti Aval. S. (2018). Uncertainty analysis through development of seismic fragility curve for an SMRF structure using an adaptive neuro-fuzzy inference system based on fuzzy C-means algorithm. Scientia Iranica, 25(6), 2938-2953. doi: 10.24200/sci.2017.4232
11. Kircher. C. A, Whitman. R. V, Holmes. W. T. (2006). HAZUS earthquake loss estimation methods. Natural Hazards Review, 7(2), 45-59.
12. Lagaros. N. D, Fragiadakis. M. (2007). Fragility Assessment of Steel Frames Using Neural Networks. Earthquake Spectra, 23(4), 735-752.
13. Lagaros. N. D, Tsompanakis. Y, Psarropoulos. P. N, Georgopoulos. E. C. (2009). Computationally Efficient Seismic Fragility Analysis of Geostructures. Computers & Structures, 87(19-20), 1195-1203.
14. Li, X. (1996). Simultaneous Approximations of Multivariate Functions and Their Derivatives by Neural Networks with One Hidden Layer. Neurocomputing, 12(4), 327-343.
15. McKenna, F. (2011). OpenSees: a framework for earthquake engineering simulation. Computing in Science & Engineering, 13(4), 58-66.
16. Papadrakakis. M, Papadopoulos V, Lagaros, N. D, Oliver. J, Huespe. A. E, Sánchez P. (2008). Vulnerability Analysis of Large Concrete Dams Using the Continuum Strong Discontinuity Approach and Neural Networks. Structural Safety, 30(3), 217-235.
17. Riedmiller. M, Braun. H. (1993). A Direct Adaptive Method for Faster Back propagation learning: The RPROP Algorithm. In IEEE international conference on neural networks (pp. 586-591). IEEE.
18. Wyllie LA, Filson JR, Agbabian M, Der Kiureghian A. (1989). Armenia earthquake Reconnaissance report: Earthquake Engineering Research Institute.