In order to study the infl uence of pile spacing on the seismic response of piled raft in soft clay, a series of shaking table tests were conducted by using a geotechnical centrifuge. The dynamic behavior of accelerat...In order to study the infl uence of pile spacing on the seismic response of piled raft in soft clay, a series of shaking table tests were conducted by using a geotechnical centrifuge. The dynamic behavior of acceleration, displacement and internal forces was examined. The test results indicate that the seismic acceleration responses of models are generally greater than the surrounding soil surface in the period ranges of 2–10 seconds. Foundation instant settlements for 4×4 and 3×3 piled raft (with pile spacing equal to 4 and 6 times pile diameter) are somewhat close to each other at the end of the earthquake, but reconsolidation settlements are greater for 3×3 piled raft. The seismic acceleration of superstructure, the uneven settlement of the foundation and the maximum bending moment of pile are relatively lower for 3×3 piled raft. Successive earthquakes lead to the softening behavior of soft clay, which causes a reduction of the pile bearing capacity and thus loads are transferred from the pile group to the raft. For the case of a 3×3 piled raft, there is relatively smaller change of the load sharing ratio of the pile group and raft after the earthquake and the distribution of maximum bending moments at the pile head is more uniform.展开更多
Training samples for deep learning networks are typically obtained through various field experiments,which require significant manpower,resource and time consumption.However,it is possible to utilize simulated data to...Training samples for deep learning networks are typically obtained through various field experiments,which require significant manpower,resource and time consumption.However,it is possible to utilize simulated data to augment the training samples.In this paper,by comparing the actual experimental model with the simulated model generated by the gprMax[1]forward simulation method,the feasibility of obtaining simulated samples through gprMax simulation is validated.Subsequently,the samples generated by gprMax forward simulation are used for training the network to detect objects in existing real samples.At the same time,aiming at the detection and intelligent recognition of road sub-surface defects,the Swin-YOLOX algorithm is introduced,and the excellence of the detection network,which is improved by augmenting the simulated samples with real samples,is further verified.By comparing the prediction performance of the object detection models,it is observed that the model trained with mixed samples achieved a recall of 94.74%and a mean average precision(maP)of 97.71%,surpassing the model trained only on real samples by 12.95%and 15.64%,respectively.The feasibility and excellence of training the model with mixed samples are confirmed.The potential of using a fusion of simulated and existing real samples instead of repeatedly acquiring new real samples by field experiment is demonstrated by this study,thereby improving detection efficiency,saving resources,and providing a new approach to the problem of multiple interpretations in ground penetrating radar(GPR)data.展开更多
This paper presents a new approach for automatical classification of structural state through deep learning.In this work,a Convolutional Neural Network(CNN)was designed to fuse both the feature extraction and classifi...This paper presents a new approach for automatical classification of structural state through deep learning.In this work,a Convolutional Neural Network(CNN)was designed to fuse both the feature extraction and classification blocks into an intelligent and compact learning system and detect the structural state of a steel frame;the input was a series of vibration signals,and the output was a structural state.The digital image correlation(DIC)technology was utilized to collect vibration information of an actual steel frame,and subsequently,the raw signals,without further pre-processing,were directly utilized as the CNN samples.The results show that CNN can achieve 99%classification accuracy for the research model.Besides,compared with the backpropagation neural network(BPNN),the CNN had an accuracy similar to that of the BPNN,but it only consumes 19%of the training time.The outputs of the convolution and pooling layers were visually displayed and discussed as well.It is demonstrated that:1)the CNN can extract the structural state information from the vibration signals and classify them;2)the detection and computational performance of the CNN for the incomplete data are better than that of the BPNN;3)the CNN has better anti-noise ability.展开更多
基金National Natural Science Foundation of China under Grand No.41372274
文摘In order to study the infl uence of pile spacing on the seismic response of piled raft in soft clay, a series of shaking table tests were conducted by using a geotechnical centrifuge. The dynamic behavior of acceleration, displacement and internal forces was examined. The test results indicate that the seismic acceleration responses of models are generally greater than the surrounding soil surface in the period ranges of 2–10 seconds. Foundation instant settlements for 4×4 and 3×3 piled raft (with pile spacing equal to 4 and 6 times pile diameter) are somewhat close to each other at the end of the earthquake, but reconsolidation settlements are greater for 3×3 piled raft. The seismic acceleration of superstructure, the uneven settlement of the foundation and the maximum bending moment of pile are relatively lower for 3×3 piled raft. Successive earthquakes lead to the softening behavior of soft clay, which causes a reduction of the pile bearing capacity and thus loads are transferred from the pile group to the raft. For the case of a 3×3 piled raft, there is relatively smaller change of the load sharing ratio of the pile group and raft after the earthquake and the distribution of maximum bending moments at the pile head is more uniform.
文摘Training samples for deep learning networks are typically obtained through various field experiments,which require significant manpower,resource and time consumption.However,it is possible to utilize simulated data to augment the training samples.In this paper,by comparing the actual experimental model with the simulated model generated by the gprMax[1]forward simulation method,the feasibility of obtaining simulated samples through gprMax simulation is validated.Subsequently,the samples generated by gprMax forward simulation are used for training the network to detect objects in existing real samples.At the same time,aiming at the detection and intelligent recognition of road sub-surface defects,the Swin-YOLOX algorithm is introduced,and the excellence of the detection network,which is improved by augmenting the simulated samples with real samples,is further verified.By comparing the prediction performance of the object detection models,it is observed that the model trained with mixed samples achieved a recall of 94.74%and a mean average precision(maP)of 97.71%,surpassing the model trained only on real samples by 12.95%and 15.64%,respectively.The feasibility and excellence of training the model with mixed samples are confirmed.The potential of using a fusion of simulated and existing real samples instead of repeatedly acquiring new real samples by field experiment is demonstrated by this study,thereby improving detection efficiency,saving resources,and providing a new approach to the problem of multiple interpretations in ground penetrating radar(GPR)data.
文摘This paper presents a new approach for automatical classification of structural state through deep learning.In this work,a Convolutional Neural Network(CNN)was designed to fuse both the feature extraction and classification blocks into an intelligent and compact learning system and detect the structural state of a steel frame;the input was a series of vibration signals,and the output was a structural state.The digital image correlation(DIC)technology was utilized to collect vibration information of an actual steel frame,and subsequently,the raw signals,without further pre-processing,were directly utilized as the CNN samples.The results show that CNN can achieve 99%classification accuracy for the research model.Besides,compared with the backpropagation neural network(BPNN),the CNN had an accuracy similar to that of the BPNN,but it only consumes 19%of the training time.The outputs of the convolution and pooling layers were visually displayed and discussed as well.It is demonstrated that:1)the CNN can extract the structural state information from the vibration signals and classify them;2)the detection and computational performance of the CNN for the incomplete data are better than that of the BPNN;3)the CNN has better anti-noise ability.
