原文传递
High-Dimensional Reliability Analysis with Error-Guided Active-Learning Probabilistic Support Vector Machine: Application to Wind-Reliability Analysis of Transmission Towers
| 题名： | High-Dimensional Reliability Analysis with Error-Guided Active-Learning Probabilistic Support Vector Machine: Application to Wind-Reliability Analysis of Transmission Towers |
| 正文语种： | eng |
| 作者： | Song, Chaolin;Shafieezadeh, Abdollah;Xiao, Rucheng |
| 作者单位： | Ohio State Univ Dept Civil Environm & Geodet Engn Risk Assessment & Management Struct & Infrastruct Columbus OH 43210 USA|Tongji Univ Dept Bridge Engn Shanghai 200092 Peoples R China;Ohio State Univ Dept Civil Environm & Geodet Engn Risk Assessment & Management Struct & Infrastruct Columbus OH 43210 USA;Tongji Univ Dept Bridge Engn Shanghai 200092 Peoples R China |
| 关键词： | Support vector machine (SVM);Reliability analysis;Probabilistic classification;High-dimensional problems |
| 摘要： | Adaptive reliability analysis methods based on surrogate models, especially kriging, have been successfully implemented in many problems. However, the application of kriging is limited to low-dimensional problems with noncategorical performance data. Support vector machine (SVM), by contrast, addresses these limitations, but its application in reliability analysis faces several challenges with regard to robustness, accuracy, and efficiency. This study proposed a new adaptive approach based on probabilistic support vector machine for reliability analysis (PSVM-RA). Different from existing methods that only select training points in the margin of the SVM, the proposed method adopts a new learning function that considers the wrong classification probability for each realization and maximizes the potential for new information offered by a candidate sample for the training set. Moreover, the upper bound of the error that is introduced by the SVM in estimating the failure probability is derived based on a Poisson binomial distribution model considering the likelihood of wrong classification for all the points in the margin of the SVM. This upper bound of error was used in the proposed framework as a stopping criterion to guarantee the desired accuracy. Three numerical examples and an engineering application regarding the wind-reliability analysis of transmission towers were investigated to demonstrate the performance of the proposed method. It was demonstrated that PSVM-RA can provide robust estimates of failure probability when other state-of-the-art methods fail. Moreover, it offers a balance between efficiency and accuracy. |
| 出版年： | 2022 |
| 期刊名称： | Journal of structural engineering |
| 卷： | 148 |
| 期： | 5 |
| 页码： | 04022036.1-04022036.13 |
相关文献
- Predicting System-Specific Human Factors Risks
- This study conducted experimental research on inelastic behavior of RC beams under cyclic loading. The experimental results were investigated and compared for two types of plastic behavior, ductile and nominally ductile, and for two types of plastic hinge mechanism, unidirectional (nonreversing) and bidirectional (reversing) behavior. For test samples with different transverse reinforcement detailing and inelastic demand, displacement capacities, curvature ductility ratios, longitudinal reinforcement strain capacities, plastic hinge lengths, concrete contribution to shear force, and cumulative dissipated energy capacities were obtained for various damage limit states. A new cumulative damage index is proposed based on plastic hinge behavior of RC beams taking into account the low-cycle fatigue behavior of longitudinal reinforcing steel. Tbe proposed damage model was compared with experimental results. DOI: 10.106l/(ASCE)ST.1943-541X.0002688. © 2020 American Society of Civil Engineers.
- Reliability of Tower and Tower-Line Systems under Spatiotemporally Varying Wind or Earthquake Loads
- Applying the Cognitive Reliability and Error Analysis Method to DPS Accidents
- Applying the Cognitive Reliability and Error Analysis Method to DPS Accidents
- Robustness of Load and Resistance Design Factors for RC Columns with Wind-Dominated Combination Considering Random Eccentricity
检索历史
应用推荐
