Multi‐hazard typhoon and earthquake collapse fragility models for transmission towers: An active learning reliability approach using gradient boosting classifiers
نویسندگان
چکیده
Natural hazards such as earthquakes and typhoons pose a considerable threat to the power transmission grid. In regions prone both hazards, overhead infrastructure may experience multi-hazard effects where two consecutive can occur within an interval shorter than time that would be needed repair system for damages occurred in first event. This consequently increases susceptibility damage during subsequent hazard. this context, paper presents set of fragility models earthquakes. The computational cost numerical simulations analyses is high due complex nonlinear behavior towers, numerous sources material geometric uncertainty, multifaceted events. To tackle challenge, we introduce novel active learning approach probabilistic classification physics-based collapse data. An initial pool labeled data generated by performing limited number history on random realizations high-fidelity finite element model common double circuit tower. A machine learning-based extreme gradient boosting (XGBoost) trained via query committee (QBC) task predicting probability belonging class (i.e., collapse). Active established leveraging disagreement information between learners points are sequentially added collapse/survival Using approach, typhoon earthquake surfaces towers different directions sequences developed. Results point significance structures. They also reveal efficacy introduced reducing complexity assessments. developed study constitute key step toward resilience assessment optimal management
منابع مشابه
Combining Active Learning and Boosting for Naïve Bayes Text Classifiers
This paper presents a variant of the AdaBoost algorithm for boosting Näıve Bayes text classifier, called AdaBUS, which combines active learning with boosting algorithm. Boosting has been evaluated to effectively improve the accuracy of machine-learning based classifiers. However, Näıve Bayes classifier, which is remarkably successful in practice for text classification problems, is known not to...
متن کاملSupervised projection approach for boosting classifiers
In this paper we present a new approach for boosting methods for the construction of ensembles of classifiers. The approach is based on using the distribution given by the weighting scheme of boosting to construct a non-linear supervised projection of the original variables, instead of using the weights of the instances to train the next classifier. With this method we construct ensembles that ...
متن کاملAdaptive Incremental Learning for Statistical Relational Models Using Gradient-Based Boosting
We consider the problem of incrementally learning models from relational data. Most existing learning methods for statistical relational models use batch learning, which becomes computationally expensive and eventually infeasible for large datasets. The majority of the previous work in relational incremental learning assumes the model’s structure is given and only the model’s parameters needed ...
متن کاملa new approach to credibility premium for zero-inflated poisson models for panel data
هدف اصلی از این تحقیق به دست آوردن و مقایسه حق بیمه باورمندی در مدل های شمارشی گزارش نشده برای داده های طولی می باشد. در این تحقیق حق بیمه های پبش گویی بر اساس توابع ضرر مربع خطا و نمایی محاسبه شده و با هم مقایسه می شود. تمایل به گرفتن پاداش و جایزه یکی از دلایل مهم برای گزارش ندادن تصادفات می باشد و افراد برای استفاده از تخفیف اغلب از گزارش تصادفات با هزینه پائین خودداری می کنند، در این تحقیق ...
15 صفحه اولImitation Learning in Relational Domains: A Functional-Gradient Boosting Approach
Imitation learning refers to the problem of learning how to behave by observing a teacher in action. We consider imitation learning in relational domains, in which there is a varying number of objects and relations among them. In prior work, simple relational policies are learned by viewing imitation learning as supervised learning of a function from states to actions. For propositional worlds,...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Earthquake Engineering & Structural Dynamics
سال: 2022
ISSN: ['0098-8847', '1096-9845']
DOI: https://doi.org/10.1002/eqe.3735