Structural damages during an earthquake are typically controlled by seismic demands,which are represented by the combination of amplitude of ground motion and cyclic load effects.Since traditional methods normally ass...Structural damages during an earthquake are typically controlled by seismic demands,which are represented by the combination of amplitude of ground motion and cyclic load effects.Since traditional methods normally assume the lognormal distributions of seismic demands and resistance parameters,uncertainties are inevitably induced in the seismic fragility analysis.In this paper,the Copula function and adaptive bandwidth kernel density estimation method(ABKDE)are used to establish a novel multidimensional seismic fragility analysis framework.Based on the results of incremental dynamic analysis for subway station structures,ABKDE is adopted to establish single-parameter seismic fragility curves for both the maximum inter-story drift ratio(MIDR)and cumulated dissipated hysteretic energy(CDHE),respectively.Subsequently,the Copula function is used to formulate a bivariate seismic fragility function considering the correlations among seismic demand measures and establish the corresponding fragility curves.Finally,comparative analyses are conducted to evaluate seismic fragility curves using Copula-based dual and single-parameter damage models as well as the traditional damage models.It is found that the seismic fragility analysis method using the Copula function has the ability to gain a comprehensive consideration of the MIDR and CDHE during the damage process of subway station structures.Moreover,this newly developed seismic fragility analysis framework can capture the influence of the correlation between deformation and energy under various peak ground accelerations on structural damage.Thus,this framework can provide a scientific basis for predicting structural damage in subway stations subjected to varying intensities of ground motion while considering multiple damage indicators.展开更多
Mechanical properties are critical to the quality of hot-rolled steel pipe products.Accurately understanding the relationship between rolling parameters and mechanical properties is crucial for effective prediction an...Mechanical properties are critical to the quality of hot-rolled steel pipe products.Accurately understanding the relationship between rolling parameters and mechanical properties is crucial for effective prediction and control.To address this,an industrial big data platform was developed to collect and process multi-source heterogeneous data from the entire production process,providing a complete dataset for mechanical property prediction.The adaptive bandwidth kernel density estimation(ABKDE)method was proposed to adjust bandwidth dynamically based on data density.Combining long short-term memory neural networks with ABKDE offers robust prediction interval capabilities for mechanical properties.The proposed method was deployed in a large-scale steel plant,which demonstrated superior prediction interval performance compared to lower upper bound estimation,mean variance estimation,and extreme learning machine-adaptive bandwidth kernel density estimation,achieving a prediction interval normalized average width of 0.37,a prediction interval coverage probability of 0.94,and the lowest coverage width-based criterion of 1.35.Notably,shapley additive explanations-based explanations significantly improved the proposed model’s credibility by providing a clear analysis of feature impacts.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.52178315,and 51578100)the Fundamental Research Funds for the Central Universities(Grant No.3132023504)+1 种基金the Dalian Science and Technology Innovation Fund(Grant No.2022JJ12GX031)the Project of Shenyang Key Laboratory of Safety Evaluation and Disaster Prevention of Engineering Structures(Grant No.S230184).
文摘Structural damages during an earthquake are typically controlled by seismic demands,which are represented by the combination of amplitude of ground motion and cyclic load effects.Since traditional methods normally assume the lognormal distributions of seismic demands and resistance parameters,uncertainties are inevitably induced in the seismic fragility analysis.In this paper,the Copula function and adaptive bandwidth kernel density estimation method(ABKDE)are used to establish a novel multidimensional seismic fragility analysis framework.Based on the results of incremental dynamic analysis for subway station structures,ABKDE is adopted to establish single-parameter seismic fragility curves for both the maximum inter-story drift ratio(MIDR)and cumulated dissipated hysteretic energy(CDHE),respectively.Subsequently,the Copula function is used to formulate a bivariate seismic fragility function considering the correlations among seismic demand measures and establish the corresponding fragility curves.Finally,comparative analyses are conducted to evaluate seismic fragility curves using Copula-based dual and single-parameter damage models as well as the traditional damage models.It is found that the seismic fragility analysis method using the Copula function has the ability to gain a comprehensive consideration of the MIDR and CDHE during the damage process of subway station structures.Moreover,this newly developed seismic fragility analysis framework can capture the influence of the correlation between deformation and energy under various peak ground accelerations on structural damage.Thus,this framework can provide a scientific basis for predicting structural damage in subway stations subjected to varying intensities of ground motion while considering multiple damage indicators.
基金supported by the National Key Research and Development Plan(Grant No.2023YFB3712400)the National Key Research and Development Plan(Grant No.2020YFB1713600).
文摘Mechanical properties are critical to the quality of hot-rolled steel pipe products.Accurately understanding the relationship between rolling parameters and mechanical properties is crucial for effective prediction and control.To address this,an industrial big data platform was developed to collect and process multi-source heterogeneous data from the entire production process,providing a complete dataset for mechanical property prediction.The adaptive bandwidth kernel density estimation(ABKDE)method was proposed to adjust bandwidth dynamically based on data density.Combining long short-term memory neural networks with ABKDE offers robust prediction interval capabilities for mechanical properties.The proposed method was deployed in a large-scale steel plant,which demonstrated superior prediction interval performance compared to lower upper bound estimation,mean variance estimation,and extreme learning machine-adaptive bandwidth kernel density estimation,achieving a prediction interval normalized average width of 0.37,a prediction interval coverage probability of 0.94,and the lowest coverage width-based criterion of 1.35.Notably,shapley additive explanations-based explanations significantly improved the proposed model’s credibility by providing a clear analysis of feature impacts.
