Accurately predicting fluid forces acting on the sur-face of a structure is crucial in engineering design.However,this task becomes particularly challenging in turbulent flow,due to the complex and irregular changes i...Accurately predicting fluid forces acting on the sur-face of a structure is crucial in engineering design.However,this task becomes particularly challenging in turbulent flow,due to the complex and irregular changes in the flow field.In this study,we propose a novel deep learning method,named mapping net-work-coordinated stacked gated recurrent units(MSU),for pre-dicting pressure on a circular cylinder from velocity data.Specifi-cally,our coordinated learning strategy is designed to extract the most critical velocity point for prediction,a process that has not been explored before.In our experiments,MSU extracts one point from a velocity field containing 121 points and utilizes this point to accurately predict 100 pressure points on the cylinder.This method significantly reduces the workload of data measure-ment in practical engineering applications.Our experimental results demonstrate that MSU predictions are highly similar to the real turbulent data in both spatio-temporal and individual aspects.Furthermore,the comparison results show that MSU predicts more precise results,even outperforming models that use all velocity field points.Compared with state-of-the-art methods,MSU has an average improvement of more than 45%in various indicators such as root mean square error(RMSE).Through comprehensive and authoritative physical verification,we estab-lished that MSU’s prediction results closely align with pressure field data obtained in real turbulence fields.This confirmation underscores the considerable potential of MSU for practical applications in real engineering scenarios.The code is available at https://github.com/zhangzm0128/MSU.展开更多
The millimeter wave(mm Wave)is a potential solution for high data rate communication due to its availability of large bandwidth.However,it is challenging to perform beam tracking in vehicular mm Wave communication sys...The millimeter wave(mm Wave)is a potential solution for high data rate communication due to its availability of large bandwidth.However,it is challenging to perform beam tracking in vehicular mm Wave communication systems due to high mobility and narrow beams.In this paper,an adaptive beam tracking algorithm is proposed to improve the network throughput performance while reducing the training signal overhead.In particular,based on the mobility prediction at base station(BS),a novel frame structure with dynamic bundled timeslot is designed.Moreover,an actor-critic reinforcement learning based algorithm is proposed to obtain the joint optimization of both beam width and the number of bundled timeslots,which makes the beam tracking adapt to the changing environment.Simulation results demonstrate that,compared with the traditional full scan and Kalman filter based beam tracking algorithms,our proposed algorithm can improve the time-averaged throughput by 11.34%and 24.86%respectively.With the newly designed frame structure,it also outperforms beam tracking with conventional frame structure,especially in scenarios with large range of vehicle speeds.展开更多
臭氧浓度的预测对于大气环境治理、空气质量改善等起到了重要的作用。本文提出了一种交互差分时空LSTM网络预测模型(ST-IDN)来挖掘臭氧浓度历史数据的时间相关性和空间相关性,并成功将其应用到网格化臭氧浓度数据预测上。在该模型中,首...臭氧浓度的预测对于大气环境治理、空气质量改善等起到了重要的作用。本文提出了一种交互差分时空LSTM网络预测模型(ST-IDN)来挖掘臭氧浓度历史数据的时间相关性和空间相关性,并成功将其应用到网格化臭氧浓度数据预测上。在该模型中,首先交互模块(IC)可以通过一系列的卷积操作来捕捉短期上下文信息,其次层融合模块(LF)可以融合不同层的空间信息来获得上一时刻丰富的空间信息,最后差分时空LSTM模块(DSTM)将捕捉到的时间信息和空间信息进行统一建模实现臭氧浓度预测。所构建模型分别与卷积LSTM网络(ConvLSTM)、预测循环神经网络(PredRNN)以及Memory in Memory网络(MIM)模型在河北省气象局提供的臭氧浓度数据上进行了对比分析,ST-IDN模型的平均绝对误差分别降低了19.836%、12.924%、7.506%。实验结果表明,所提出的模型能够提高臭氧浓度的预测精度。展开更多
基金supported by the Japan Society for the Promotion of Science(JSPS)KAKENHI(JP22H03643)Japan Science and Technology Agency(JST)Support for Pioneering Research Initiated by the Next Generation(SPRING)(JPMJSP2145)+2 种基金JST Through the Establishment of University Fellowships Towards the Creation of Science Technology Innovation(JPMJFS2115)the National Natural Science Foundation of China(52078382)the State Key Laboratory of Disaster Reduction in Civil Engineering(CE19-A-01)。
文摘Accurately predicting fluid forces acting on the sur-face of a structure is crucial in engineering design.However,this task becomes particularly challenging in turbulent flow,due to the complex and irregular changes in the flow field.In this study,we propose a novel deep learning method,named mapping net-work-coordinated stacked gated recurrent units(MSU),for pre-dicting pressure on a circular cylinder from velocity data.Specifi-cally,our coordinated learning strategy is designed to extract the most critical velocity point for prediction,a process that has not been explored before.In our experiments,MSU extracts one point from a velocity field containing 121 points and utilizes this point to accurately predict 100 pressure points on the cylinder.This method significantly reduces the workload of data measure-ment in practical engineering applications.Our experimental results demonstrate that MSU predictions are highly similar to the real turbulent data in both spatio-temporal and individual aspects.Furthermore,the comparison results show that MSU predicts more precise results,even outperforming models that use all velocity field points.Compared with state-of-the-art methods,MSU has an average improvement of more than 45%in various indicators such as root mean square error(RMSE).Through comprehensive and authoritative physical verification,we estab-lished that MSU’s prediction results closely align with pressure field data obtained in real turbulence fields.This confirmation underscores the considerable potential of MSU for practical applications in real engineering scenarios.The code is available at https://github.com/zhangzm0128/MSU.
基金supported by the National Key R&D Program of China(2020YFB1807204)Beijing Natural Science Foundation(L212003)。
文摘The millimeter wave(mm Wave)is a potential solution for high data rate communication due to its availability of large bandwidth.However,it is challenging to perform beam tracking in vehicular mm Wave communication systems due to high mobility and narrow beams.In this paper,an adaptive beam tracking algorithm is proposed to improve the network throughput performance while reducing the training signal overhead.In particular,based on the mobility prediction at base station(BS),a novel frame structure with dynamic bundled timeslot is designed.Moreover,an actor-critic reinforcement learning based algorithm is proposed to obtain the joint optimization of both beam width and the number of bundled timeslots,which makes the beam tracking adapt to the changing environment.Simulation results demonstrate that,compared with the traditional full scan and Kalman filter based beam tracking algorithms,our proposed algorithm can improve the time-averaged throughput by 11.34%and 24.86%respectively.With the newly designed frame structure,it also outperforms beam tracking with conventional frame structure,especially in scenarios with large range of vehicle speeds.
文摘臭氧浓度的预测对于大气环境治理、空气质量改善等起到了重要的作用。本文提出了一种交互差分时空LSTM网络预测模型(ST-IDN)来挖掘臭氧浓度历史数据的时间相关性和空间相关性,并成功将其应用到网格化臭氧浓度数据预测上。在该模型中,首先交互模块(IC)可以通过一系列的卷积操作来捕捉短期上下文信息,其次层融合模块(LF)可以融合不同层的空间信息来获得上一时刻丰富的空间信息,最后差分时空LSTM模块(DSTM)将捕捉到的时间信息和空间信息进行统一建模实现臭氧浓度预测。所构建模型分别与卷积LSTM网络(ConvLSTM)、预测循环神经网络(PredRNN)以及Memory in Memory网络(MIM)模型在河北省气象局提供的臭氧浓度数据上进行了对比分析,ST-IDN模型的平均绝对误差分别降低了19.836%、12.924%、7.506%。实验结果表明,所提出的模型能够提高臭氧浓度的预测精度。
