One of the primary tasks of earthquake early warning(EEW)systems is to predict potential earthquake damage rapidly and accurately.Cumulative absolute velocity(CAV),Arias intensity(I_(A)),and spectrum intensity(SI)are ...One of the primary tasks of earthquake early warning(EEW)systems is to predict potential earthquake damage rapidly and accurately.Cumulative absolute velocity(CAV),Arias intensity(I_(A)),and spectrum intensity(SI)are important parameters for measuring ground motion intensity and assessing earthquake damage.Due to the limited available information in EEW,CAV,I_(A),and SI cannot be accurately predicted using traditional EEW methods.In this paper,we propose an end-to-end deep learning-based Ground motion Intensity prediction Network(ENGINet)for on-site EEW.The aim of the ENGINet is to predict CAV,I_(A),and SI rapidly and reliably.ENGINet is based on a convolutional neural network and recurrent neural network.The inputs of the network are three-component acceleration records,three-component velocity records,and three-component displacement records obtained by a single station.The results from the test dataset show that at 3 s after the P-wave arrival,compared with the baseline models and other traditional methods,ENGINet has better performance in predicting CAV,I_(A),and SI.Our results indicate that ENGINet can quickly and accurately predict CAV,I_(A),and SI to some extent and has good potential in EEW efforts.展开更多
Two parameters,block spectrum intensity Seq and spectrum shape factor a,which describe the characteristics of the loading block spectrum are defined,and the relationship between the parameters and fatigue crack propag...Two parameters,block spectrum intensity Seq and spectrum shape factor a,which describe the characteristics of the loading block spectrum are defined,and the relationship between the parameters and fatigue crack propagation behaviours is investigated.It is shown that the spectrum intensity is an 'average drive force' of fatigue crack propagation,and the variance of fatigue crack size at a given fatigue life is closely related to the spectrum shape factor α.展开更多
The present study is aimed to investigate the ability of different intensity measures （IMs）, including response spectral acceleration at the fundamental period of the structure, Sa（T1）, as a common scalar IM and t...The present study is aimed to investigate the ability of different intensity measures （IMs）, including response spectral acceleration at the fundamental period of the structure, Sa（T1）, as a common scalar IM and twelve vector-valued IMs for seismic collapse assessment of structures. The vector-valued IMs consist of two components, with S（T1） as the first component and different parameters that are ratios of scalar IMs, as well as the spectral shape proxies εSa and N, as the second component. After investigating the properties of an optimal IM, a new vector-valued IM that includes the ratio of Sa（T1） to the displacement spectrum intensity （DSI） as the second component is proposed. The new IM is more efficient than other IMs for predicting the collapse capacity of structures. It is also sufficient with respect to magnitude, source-to-site distance, and scale factor for collapse capacity prediction of structures. To satisfy the predictability criterion, a ground motion prediction equation （GMPE） is determined for Sa（T1）/DSI by using the existing GMPEs. Furthermore, an empirical equation is proposed for obtaining the correlation between the components of the proposed IM. The results of this study show that using the new vector-valued IM leads to a more reliable seismic collapse assessment of structures.展开更多
The determination of collapse margin ratio(CMR)of structure is influenced by many uncertain factors.Some factors that can affect the calculation of CMR,e.g.,the elongation of the structural fundamental period prior to...The determination of collapse margin ratio(CMR)of structure is influenced by many uncertain factors.Some factors that can affect the calculation of CMR,e.g.,the elongation of the structural fundamental period prior to collapse,the determination of earthquake intensity measure,the seismic hazard probability,and the difference of the spectral shapes between the median spectrum of the ground motions and the design spectrum,were discussed.Considering the elongation of the structural fundamental period,the intensity measure Sa(T1)should be replaced with *aS in the calculation of CMR for short-period and medium-period structures.The reasonable intensity measure should be determined by the correlation analysis between the earthquake intensity measure and the damage index of the structure.Otherwise,CMR should be adjusted according to the seismic hazard probability and the difference in the spectral shapes.For important long-period structures,CMR should be determined by the special site spectrum.The results indicate that both Sa(T1)and spectrum intensity(SI)could be used as intensity measures in the calculation of CMR for medium-period structures,but SI would be a better choice for long-period structures.Moreover,an adjusted CMR that reflects the actual seismic collapse safety of structures is provided.展开更多
The agricultural sector,a cornerstone of economies worldwide,faces significant challenges due to plant diseases,which severely affect crop yield and quality.Early and accurate detection of these diseases is crucial fo...The agricultural sector,a cornerstone of economies worldwide,faces significant challenges due to plant diseases,which severely affect crop yield and quality.Early and accurate detection of these diseases is crucial for effective mitigation strategies.The current methods used often lack accuracy and adaptability,especially in diverse environmental conditions.This study introduces a novel,synergistic approach that integrates deep transfer learning with multimodal techniques,specifically canny edges,colour spectrum intensity analysis,and custom data augmentation strategies.Unlike existing methods that rely solely on pre-trained models,the approach utilised in this study offers an innovative fusion of distinct feature extraction techniques.The canny edges highlighted the structural intricacies of leaf diseases,while colour spectrum intensity analysis enhanced the detection of disease-specific colour markers.The customized data augmentation techniques employed(in the study)was shown to enhance the learning process of the models,resulting in their adaptability to diverse agricultural environments.This integration applied to DenseNet201 and EfficientNetB3,achieved detection accuracies of 99.03%and 98.23%,respectively,surpassing traditional models and setting new benchmarks in plant disease detection.These results demonstrate the effectiveness of the proposed multi-faceted approach and its potential to significantly enhance crop disease management systems.展开更多
基金Scientific Research Fund of Institute of Engineering Mechanics,China Earthquake Administration under Grant No.2024B08。
文摘One of the primary tasks of earthquake early warning(EEW)systems is to predict potential earthquake damage rapidly and accurately.Cumulative absolute velocity(CAV),Arias intensity(I_(A)),and spectrum intensity(SI)are important parameters for measuring ground motion intensity and assessing earthquake damage.Due to the limited available information in EEW,CAV,I_(A),and SI cannot be accurately predicted using traditional EEW methods.In this paper,we propose an end-to-end deep learning-based Ground motion Intensity prediction Network(ENGINet)for on-site EEW.The aim of the ENGINet is to predict CAV,I_(A),and SI rapidly and reliably.ENGINet is based on a convolutional neural network and recurrent neural network.The inputs of the network are three-component acceleration records,three-component velocity records,and three-component displacement records obtained by a single station.The results from the test dataset show that at 3 s after the P-wave arrival,compared with the baseline models and other traditional methods,ENGINet has better performance in predicting CAV,I_(A),and SI.Our results indicate that ENGINet can quickly and accurately predict CAV,I_(A),and SI to some extent and has good potential in EEW efforts.
文摘Two parameters,block spectrum intensity Seq and spectrum shape factor a,which describe the characteristics of the loading block spectrum are defined,and the relationship between the parameters and fatigue crack propagation behaviours is investigated.It is shown that the spectrum intensity is an 'average drive force' of fatigue crack propagation,and the variance of fatigue crack size at a given fatigue life is closely related to the spectrum shape factor α.
文摘The present study is aimed to investigate the ability of different intensity measures （IMs）, including response spectral acceleration at the fundamental period of the structure, Sa（T1）, as a common scalar IM and twelve vector-valued IMs for seismic collapse assessment of structures. The vector-valued IMs consist of two components, with S（T1） as the first component and different parameters that are ratios of scalar IMs, as well as the spectral shape proxies εSa and N, as the second component. After investigating the properties of an optimal IM, a new vector-valued IM that includes the ratio of Sa（T1） to the displacement spectrum intensity （DSI） as the second component is proposed. The new IM is more efficient than other IMs for predicting the collapse capacity of structures. It is also sufficient with respect to magnitude, source-to-site distance, and scale factor for collapse capacity prediction of structures. To satisfy the predictability criterion, a ground motion prediction equation （GMPE） is determined for Sa（T1）/DSI by using the existing GMPEs. Furthermore, an empirical equation is proposed for obtaining the correlation between the components of the proposed IM. The results of this study show that using the new vector-valued IM leads to a more reliable seismic collapse assessment of structures.
基金Projects(51161120359,90915005)supported by the National Natural Science Foundation of ChinaProject(NCET-08-0096)supported by the Program for New Century Excellent Talents in University of the Ministry of China
文摘The determination of collapse margin ratio(CMR)of structure is influenced by many uncertain factors.Some factors that can affect the calculation of CMR,e.g.,the elongation of the structural fundamental period prior to collapse,the determination of earthquake intensity measure,the seismic hazard probability,and the difference of the spectral shapes between the median spectrum of the ground motions and the design spectrum,were discussed.Considering the elongation of the structural fundamental period,the intensity measure Sa(T1)should be replaced with *aS in the calculation of CMR for short-period and medium-period structures.The reasonable intensity measure should be determined by the correlation analysis between the earthquake intensity measure and the damage index of the structure.Otherwise,CMR should be adjusted according to the seismic hazard probability and the difference in the spectral shapes.For important long-period structures,CMR should be determined by the special site spectrum.The results indicate that both Sa(T1)and spectrum intensity(SI)could be used as intensity measures in the calculation of CMR for medium-period structures,but SI would be a better choice for long-period structures.Moreover,an adjusted CMR that reflects the actual seismic collapse safety of structures is provided.
文摘The agricultural sector,a cornerstone of economies worldwide,faces significant challenges due to plant diseases,which severely affect crop yield and quality.Early and accurate detection of these diseases is crucial for effective mitigation strategies.The current methods used often lack accuracy and adaptability,especially in diverse environmental conditions.This study introduces a novel,synergistic approach that integrates deep transfer learning with multimodal techniques,specifically canny edges,colour spectrum intensity analysis,and custom data augmentation strategies.Unlike existing methods that rely solely on pre-trained models,the approach utilised in this study offers an innovative fusion of distinct feature extraction techniques.The canny edges highlighted the structural intricacies of leaf diseases,while colour spectrum intensity analysis enhanced the detection of disease-specific colour markers.The customized data augmentation techniques employed(in the study)was shown to enhance the learning process of the models,resulting in their adaptability to diverse agricultural environments.This integration applied to DenseNet201 and EfficientNetB3,achieved detection accuracies of 99.03%and 98.23%,respectively,surpassing traditional models and setting new benchmarks in plant disease detection.These results demonstrate the effectiveness of the proposed multi-faceted approach and its potential to significantly enhance crop disease management systems.
