Rapid urbanization has substantially increased the complexity of urban underground spaces.This complexity leads to frequent road collapse incidents that pose significant threats to the safety and property of urban res...Rapid urbanization has substantially increased the complexity of urban underground spaces.This complexity leads to frequent road collapse incidents that pose significant threats to the safety and property of urban residents.Therefore,accurate methods of performing early road collapse risk assessments are crucial for preventing these incidents and emergency preparedness.In this study,road collapse incident data for 20162021 were collected for Foshan,Guangdong Province,a city in southern China.Utilizing InSAR time-series data from Sentinel-1 satellites,ground subsidence maps were generated,and the publicly accessible Ground Subsidence Trend-Based Urban Road Collapse Risk Dataset(GSTURCRD)was constructed.A novel risk assessment method for urban road collapse based on an extended long short-term memory(xLSTM)network was proposed.This method introduces two new LSTM variants,the scalar LSTM(sLSTM)and the matrix LSTM(mLSTM),incorporating exponential gating and an innovative matrix memory structure.These variants are integrated using residual connections to form a comprehensive network architecture that enables effective learning and representation of the temporal features.The experimental results from the dataset demonstrate that the proposed method significantly outperforms the original LSTM network and traditional machine learning methods regarding assessment capability(its accuracy was 0.886,and its recall was 0.857).Furthermore,the method's effectiveness was validated by an analysis of actual incidents that occurred in Foshan;thus,its ability to generate accurate and timely detections and provide early warnings for high-risk road sections in urban areas was confirmed.展开更多
Images are complex multimedia data which contain rich semantic information.Most of current image description generator algorithms only generate plain description,with the lack of distinction between primary and second...Images are complex multimedia data which contain rich semantic information.Most of current image description generator algorithms only generate plain description,with the lack of distinction between primary and secondary object,leading to insufficient high-level semantic and accuracy under public evaluation criteria.The major issue is the lack of effective network on high-level semantic sentences generation,which contains detailed description for motion and state of the principal object.To address the issue,this paper proposes the Attention-based Feedback Long Short-Term Memory Network(AFLN).Based on existing codec framework,there are two independent sub tasks in our method:attention-based feedback LSTM network during decoding and the Convolutional Block Attention Module(CBAM)in the coding phase.First,we propose an attentionbased network to feedback the features corresponding to the generated word from the previous LSTM decoding unit.We implement feedback guidance through the related field mapping algorithm,which quantifies the correlation between previous word and latter word,so that the main object can be tracked with highlighted detailed description.Second,we exploit the attention idea and apply a lightweight and general module called CBAM after the last layer of VGG 16 pretraining network,which can enhance the expression of image coding features by combining channel and spatial dimension attention maps with negligible overheads.Extensive experiments on COCO dataset validate the superiority of our network over the state-of-the-art algorithms.Both scores and actual effects are proved.The BLEU 4 score increases from 0.291 to 0.301 while the CIDEr score rising from 0.912 to 0.952.展开更多
In order to effectively solve the problems of low accuracy,large amount of computation and complex logic of deep learning algorithms in behavior recognition,a kind of behavior recognition based on the fusion of 3 dime...In order to effectively solve the problems of low accuracy,large amount of computation and complex logic of deep learning algorithms in behavior recognition,a kind of behavior recognition based on the fusion of 3 dimensional batch normalization visual geometry group(3D-BN-VGG)and long short-term memory(LSTM)network is designed.In this network,3D convolutional layer is used to extract the spatial domain features and time domain features of video sequence at the same time,multiple small convolution kernels are stacked to replace large convolution kernels,thus the depth of neural network is deepened and the number of network parameters is reduced.In addition,the latest batch normalization algorithm is added to the 3-dimensional convolutional network to improve the training speed.Then the output of the full connection layer is sent to LSTM network as the feature vectors to extract the sequence information.This method,which directly uses the output of the whole base level without passing through the full connection layer,reduces the parameters of the whole fusion network to 15324485,nearly twice as much as those of 3D-BN-VGG.Finally,it reveals that the proposed network achieves 96.5%and 74.9%accuracy in the UCF-101 and HMDB-51 respectively,and the algorithm has a calculation speed of 1066 fps and an acceleration ratio of 1,which has a significant predominance in velocity.展开更多
Monitoring and predicting of urban surface subsidence are important for urban disaster prevention and mitigation.In this paper,the Long Short-Term Memory(LSTM)network was used to predict the surface subsidence process...Monitoring and predicting of urban surface subsidence are important for urban disaster prevention and mitigation.In this paper,the Long Short-Term Memory(LSTM)network was used to predict the surface subsidence process of Changchun City from 2018 to 2020 based on PS-InSAR monitoring data.The results show that the prediction error of 57.89% of PS points in the LSTM network was less than 1mm with the average error of 1.8 mm and the standard deviation of 2.8 mm.The accuracy and reliability of the prediction were better than regression analysis,time series analysis and grey model.展开更多
针对工业装配任务,尤其是不规则轴孔工件装配中,基于学习的前期样本质量低、训练过程不稳定等问题,提出一种融合引斥力模型(Attraction-Repulsion Model,ARM)引导机制和长短期记忆网络(Long Short Term Memory,LSTM)的柔性演员-评论家(S...针对工业装配任务,尤其是不规则轴孔工件装配中,基于学习的前期样本质量低、训练过程不稳定等问题,提出一种融合引斥力模型(Attraction-Repulsion Model,ARM)引导机制和长短期记忆网络(Long Short Term Memory,LSTM)的柔性演员-评论家(Soft Actor-Critic,SAC)算法。首先,为解决训练初期探索效率低的问题,提出一种基于引斥力模型的策略引导机制,通过目标位置信息引导机械臂运动,加速收敛过程;其次,基于长短期记忆网络对算法的策略网络和价值网络进行改进,有效利用历史信息,增强策略学习能力,提高算法的收敛速度和稳定性。仿真结果表明,所提出的算法在行星减速器中心轴装配任务中取得显著的效果,装配成功率高达99.4%,与普通SAC算法相比,平均最大接触力和力矩分别降低了68.8%和79.2%。在物理环境中装配成功率达95%以上,最大接触力和力矩分别小于10 N和1.5 N·m,验证了算法的有效性。展开更多
为了准确判断电池可用容量,采用长短期记忆神经网络对电池容量进行估算。首先分析电池各参数全生命周期变化曲线,计算其与电池容量之间的皮尔逊相关系数,选择电池电压、内阻、等压降时间等参数作为健康因子构建电池容量估计模型。使用...为了准确判断电池可用容量,采用长短期记忆神经网络对电池容量进行估算。首先分析电池各参数全生命周期变化曲线,计算其与电池容量之间的皮尔逊相关系数,选择电池电压、内阻、等压降时间等参数作为健康因子构建电池容量估计模型。使用美国先进寿命周期工程中心CALCE(Center for Advanced Life Cycle Engineering)电池数据集进行模型训练并估算电池容量,估计模型的平均百分误差为1.19%。分析估算误差产生的原因,通过电池初始容量参数修正和电池老化参数修正进行模型优化。优化结果表明,使用电池电压、内阻、恒流充电时间和4.0~3.4 V等压降时间构建模型估计误差在0.55%左右。展开更多
Complicated loads encountered by floating offshore wind turbines(FOWTs)in real sea conditions are crucial for future optimization of design,but obtaining data on them directly poses a challenge.To address this issue,w...Complicated loads encountered by floating offshore wind turbines(FOWTs)in real sea conditions are crucial for future optimization of design,but obtaining data on them directly poses a challenge.To address this issue,we applied machine learning techniques to obtain hydrodynamic and aerodynamic loads of FOWTs by measuring platform motion responses and wave-elevation sequences.First,a computational fluid dynamics(CFD)simulation model of the floating platform was established based on the dynamic fluid body interaction technique and overset grid technology.Then,a long short-term memory(LSTM)neural network model was constructed and trained to learn the nonlinear relationship between the waves,platform-motion inputs,and hydrodynamic-load outputs.The optimal model was determined after analyzing the sensitivity of parameters such as sample characteristics,network layers,and neuron numbers.Subsequently,the effectiveness of the hydrodynamic load model was validated under different simulation conditions,and the aerodynamic load calculation was completed based on the D'Alembert principle.Finally,we built a hybrid-scale FOWT model,based on the software in the loop strategy,in which the wind turbine was replaced by an actuation system.Model tests were carried out in a wave basin and the results demonstrated that the root mean square errors of the hydrodynamic and aerodynamic load measurements were 4.20%and 10.68%,respectively.展开更多
针对长短期记忆神经网络(Long Short Term Memory Neural Network,LSTMNN)在辨识异步电机故障时,因人工选择网络超参数导致的辨识精度下降问题,提出一种改进的蜣螂优化算法寻优LSTMNN的重要参数。首先,建立具有定子匝间短路故障的异步...针对长短期记忆神经网络(Long Short Term Memory Neural Network,LSTMNN)在辨识异步电机故障时,因人工选择网络超参数导致的辨识精度下降问题,提出一种改进的蜣螂优化算法寻优LSTMNN的重要参数。首先,建立具有定子匝间短路故障的异步电机系统模型;其次,利用精英反向学习策略、分段线性混沌映射、动态混沌权重因子和动态权重系数等方法改进蜣螂优化算法;最后,使用改进蜣螂优化算法对LSTMNN的关键超参数进行寻优。仿真结果表明,相较于基于蜣螂优化算法和基于改进麻雀算法的LSTMNN,提出的优化LSTMNN对故障及其他变量的辨识均方根误差分别降低了51.93%、36.49%,平均绝对误差分别降低了56.83%、43.99%,平均绝对百分误差分别降低了29.91%、22.25%,表明采用改进的蜣螂优化算法对LSTMNN的关键超参数寻优,可显著提高LSTM网络对电机故障及其他变量的辨识能力。展开更多
基金supported by the Guangdong Provincial Key Laboratory of New Technology in Urban Rail Transit Engineering Construction[2017B030302009]the Guangzhou Academician Expert Workstation[2021CXZX030].
文摘Rapid urbanization has substantially increased the complexity of urban underground spaces.This complexity leads to frequent road collapse incidents that pose significant threats to the safety and property of urban residents.Therefore,accurate methods of performing early road collapse risk assessments are crucial for preventing these incidents and emergency preparedness.In this study,road collapse incident data for 20162021 were collected for Foshan,Guangdong Province,a city in southern China.Utilizing InSAR time-series data from Sentinel-1 satellites,ground subsidence maps were generated,and the publicly accessible Ground Subsidence Trend-Based Urban Road Collapse Risk Dataset(GSTURCRD)was constructed.A novel risk assessment method for urban road collapse based on an extended long short-term memory(xLSTM)network was proposed.This method introduces two new LSTM variants,the scalar LSTM(sLSTM)and the matrix LSTM(mLSTM),incorporating exponential gating and an innovative matrix memory structure.These variants are integrated using residual connections to form a comprehensive network architecture that enables effective learning and representation of the temporal features.The experimental results from the dataset demonstrate that the proposed method significantly outperforms the original LSTM network and traditional machine learning methods regarding assessment capability(its accuracy was 0.886,and its recall was 0.857).Furthermore,the method's effectiveness was validated by an analysis of actual incidents that occurred in Foshan;thus,its ability to generate accurate and timely detections and provide early warnings for high-risk road sections in urban areas was confirmed.
基金This research study is supported by the National Natural Science Foundation of China(No.61672108).
文摘Images are complex multimedia data which contain rich semantic information.Most of current image description generator algorithms only generate plain description,with the lack of distinction between primary and secondary object,leading to insufficient high-level semantic and accuracy under public evaluation criteria.The major issue is the lack of effective network on high-level semantic sentences generation,which contains detailed description for motion and state of the principal object.To address the issue,this paper proposes the Attention-based Feedback Long Short-Term Memory Network(AFLN).Based on existing codec framework,there are two independent sub tasks in our method:attention-based feedback LSTM network during decoding and the Convolutional Block Attention Module(CBAM)in the coding phase.First,we propose an attentionbased network to feedback the features corresponding to the generated word from the previous LSTM decoding unit.We implement feedback guidance through the related field mapping algorithm,which quantifies the correlation between previous word and latter word,so that the main object can be tracked with highlighted detailed description.Second,we exploit the attention idea and apply a lightweight and general module called CBAM after the last layer of VGG 16 pretraining network,which can enhance the expression of image coding features by combining channel and spatial dimension attention maps with negligible overheads.Extensive experiments on COCO dataset validate the superiority of our network over the state-of-the-art algorithms.Both scores and actual effects are proved.The BLEU 4 score increases from 0.291 to 0.301 while the CIDEr score rising from 0.912 to 0.952.
基金the National Natural Science Foundation of China(No.61772417,61634004,61602377)Key R&D Program Projects in Shaanxi Province(No.2017GY-060)Shaanxi Natural Science Basic Research Project(No.2018JM4018).
文摘In order to effectively solve the problems of low accuracy,large amount of computation and complex logic of deep learning algorithms in behavior recognition,a kind of behavior recognition based on the fusion of 3 dimensional batch normalization visual geometry group(3D-BN-VGG)and long short-term memory(LSTM)network is designed.In this network,3D convolutional layer is used to extract the spatial domain features and time domain features of video sequence at the same time,multiple small convolution kernels are stacked to replace large convolution kernels,thus the depth of neural network is deepened and the number of network parameters is reduced.In addition,the latest batch normalization algorithm is added to the 3-dimensional convolutional network to improve the training speed.Then the output of the full connection layer is sent to LSTM network as the feature vectors to extract the sequence information.This method,which directly uses the output of the whole base level without passing through the full connection layer,reduces the parameters of the whole fusion network to 15324485,nearly twice as much as those of 3D-BN-VGG.Finally,it reveals that the proposed network achieves 96.5%and 74.9%accuracy in the UCF-101 and HMDB-51 respectively,and the algorithm has a calculation speed of 1066 fps and an acceleration ratio of 1,which has a significant predominance in velocity.
基金Supported by the National Key Research and Development Program of China(No.2020YFA0714103).
文摘Monitoring and predicting of urban surface subsidence are important for urban disaster prevention and mitigation.In this paper,the Long Short-Term Memory(LSTM)network was used to predict the surface subsidence process of Changchun City from 2018 to 2020 based on PS-InSAR monitoring data.The results show that the prediction error of 57.89% of PS points in the LSTM network was less than 1mm with the average error of 1.8 mm and the standard deviation of 2.8 mm.The accuracy and reliability of the prediction were better than regression analysis,time series analysis and grey model.
文摘针对工业装配任务,尤其是不规则轴孔工件装配中,基于学习的前期样本质量低、训练过程不稳定等问题,提出一种融合引斥力模型(Attraction-Repulsion Model,ARM)引导机制和长短期记忆网络(Long Short Term Memory,LSTM)的柔性演员-评论家(Soft Actor-Critic,SAC)算法。首先,为解决训练初期探索效率低的问题,提出一种基于引斥力模型的策略引导机制,通过目标位置信息引导机械臂运动,加速收敛过程;其次,基于长短期记忆网络对算法的策略网络和价值网络进行改进,有效利用历史信息,增强策略学习能力,提高算法的收敛速度和稳定性。仿真结果表明,所提出的算法在行星减速器中心轴装配任务中取得显著的效果,装配成功率高达99.4%,与普通SAC算法相比,平均最大接触力和力矩分别降低了68.8%和79.2%。在物理环境中装配成功率达95%以上,最大接触力和力矩分别小于10 N和1.5 N·m,验证了算法的有效性。
文摘为了准确判断电池可用容量,采用长短期记忆神经网络对电池容量进行估算。首先分析电池各参数全生命周期变化曲线,计算其与电池容量之间的皮尔逊相关系数,选择电池电压、内阻、等压降时间等参数作为健康因子构建电池容量估计模型。使用美国先进寿命周期工程中心CALCE(Center for Advanced Life Cycle Engineering)电池数据集进行模型训练并估算电池容量,估计模型的平均百分误差为1.19%。分析估算误差产生的原因,通过电池初始容量参数修正和电池老化参数修正进行模型优化。优化结果表明,使用电池电压、内阻、恒流充电时间和4.0~3.4 V等压降时间构建模型估计误差在0.55%左右。
基金This work is supported by the National Key Research and Development Program of China(No.2023YFB4203000)the National Natural Science Foundation of China(No.U22A20178)
文摘Complicated loads encountered by floating offshore wind turbines(FOWTs)in real sea conditions are crucial for future optimization of design,but obtaining data on them directly poses a challenge.To address this issue,we applied machine learning techniques to obtain hydrodynamic and aerodynamic loads of FOWTs by measuring platform motion responses and wave-elevation sequences.First,a computational fluid dynamics(CFD)simulation model of the floating platform was established based on the dynamic fluid body interaction technique and overset grid technology.Then,a long short-term memory(LSTM)neural network model was constructed and trained to learn the nonlinear relationship between the waves,platform-motion inputs,and hydrodynamic-load outputs.The optimal model was determined after analyzing the sensitivity of parameters such as sample characteristics,network layers,and neuron numbers.Subsequently,the effectiveness of the hydrodynamic load model was validated under different simulation conditions,and the aerodynamic load calculation was completed based on the D'Alembert principle.Finally,we built a hybrid-scale FOWT model,based on the software in the loop strategy,in which the wind turbine was replaced by an actuation system.Model tests were carried out in a wave basin and the results demonstrated that the root mean square errors of the hydrodynamic and aerodynamic load measurements were 4.20%and 10.68%,respectively.
文摘针对长短期记忆神经网络(Long Short Term Memory Neural Network,LSTMNN)在辨识异步电机故障时,因人工选择网络超参数导致的辨识精度下降问题,提出一种改进的蜣螂优化算法寻优LSTMNN的重要参数。首先,建立具有定子匝间短路故障的异步电机系统模型;其次,利用精英反向学习策略、分段线性混沌映射、动态混沌权重因子和动态权重系数等方法改进蜣螂优化算法;最后,使用改进蜣螂优化算法对LSTMNN的关键超参数进行寻优。仿真结果表明,相较于基于蜣螂优化算法和基于改进麻雀算法的LSTMNN,提出的优化LSTMNN对故障及其他变量的辨识均方根误差分别降低了51.93%、36.49%,平均绝对误差分别降低了56.83%、43.99%,平均绝对百分误差分别降低了29.91%、22.25%,表明采用改进的蜣螂优化算法对LSTMNN的关键超参数寻优,可显著提高LSTM网络对电机故障及其他变量的辨识能力。
