To address the shortcomings in decision-making methods for ground motion threshold warning models in high-speed rail earthquake early warning systems(HSREEWs),we propose a dual judgement method and corresponding early...To address the shortcomings in decision-making methods for ground motion threshold warning models in high-speed rail earthquake early warning systems(HSREEWs),we propose a dual judgement method and corresponding early warning process for earthquake early warning decisions based on joint peak ground acceleration(PGA)and complex earthquake environmental risk evaluation(ERE)values.First,we analyse the characteristics of four complex earthquake environments based on the characteristics of high-speed rail(HSR)operating environments.Second,we establish an earthquake environmental risk evaluation index system and propose an adversarial interpretive structure modelling method-based complex earthquake situation evaluation model(AISM-based ESEM).The AISM method firstly evaluates the proximity by the TOPSIS(technique for order preference by similarity to an ideal solution)method,then effectively rank targets with fuzzy attributes through opposite hierarchical extraction rules without sacrificing system functionality.Since PGA can reflect the current size of earthquake energy,combining PGA thresholds with ESEM-derived values of ERE can effectively determine the risk status of each train and make decisions on the most appropriate alarm form and control measures for that status.Finally,case analysis results under the background of Wenchuan Earthquake show that the new early warning decisionmaking method accurately assesses environmental risks in affected areas and provides corresponding warning levels as a supplement to existing HSREEWs warning models.展开更多
Statistical learning theory is for small-sample statistics. And support vector machine is a new machine learning method based on the statistical learning theory. The support vector machine not only has solved certain ...Statistical learning theory is for small-sample statistics. And support vector machine is a new machine learning method based on the statistical learning theory. The support vector machine not only has solved certain problems in many learning methods, such as small sample, over fitting, high dimension and local minimum, but also has a higher generalization （forecasting） ability than that of artificial neural networks. The strong earthquakes in Chinese mainland are related to a certain extent to the intensive seismicity along the main plate boundaries in the world, however, the relation is nonlinear. In the paper, we have studied this unclear relation by the support vector machine method for the purpose of forecasting strong earthquakes in Chinese mainland.展开更多
基金supported in part by the Key Scientific and Technological projects of Henan Province(Grant No.182102310004)the Postgraduate Research&Practice Innovation Program of Jiangsu Province(Grant No.KYCX19_0304)the scholarship of China Scholarship Council(Grant No.201906840033,202006840084).
文摘To address the shortcomings in decision-making methods for ground motion threshold warning models in high-speed rail earthquake early warning systems(HSREEWs),we propose a dual judgement method and corresponding early warning process for earthquake early warning decisions based on joint peak ground acceleration(PGA)and complex earthquake environmental risk evaluation(ERE)values.First,we analyse the characteristics of four complex earthquake environments based on the characteristics of high-speed rail(HSR)operating environments.Second,we establish an earthquake environmental risk evaluation index system and propose an adversarial interpretive structure modelling method-based complex earthquake situation evaluation model(AISM-based ESEM).The AISM method firstly evaluates the proximity by the TOPSIS(technique for order preference by similarity to an ideal solution)method,then effectively rank targets with fuzzy attributes through opposite hierarchical extraction rules without sacrificing system functionality.Since PGA can reflect the current size of earthquake energy,combining PGA thresholds with ESEM-derived values of ERE can effectively determine the risk status of each train and make decisions on the most appropriate alarm form and control measures for that status.Finally,case analysis results under the background of Wenchuan Earthquake show that the new early warning decisionmaking method accurately assesses environmental risks in affected areas and provides corresponding warning levels as a supplement to existing HSREEWs warning models.
基金Joint Seismological Science Foundation of China (104090)
文摘Statistical learning theory is for small-sample statistics. And support vector machine is a new machine learning method based on the statistical learning theory. The support vector machine not only has solved certain problems in many learning methods, such as small sample, over fitting, high dimension and local minimum, but also has a higher generalization （forecasting） ability than that of artificial neural networks. The strong earthquakes in Chinese mainland are related to a certain extent to the intensive seismicity along the main plate boundaries in the world, however, the relation is nonlinear. In the paper, we have studied this unclear relation by the support vector machine method for the purpose of forecasting strong earthquakes in Chinese mainland.
