Artificial intelligence technology is introduced into the simulation of muzzle flow field to improve its simulation efficiency in this paper.A data-physical fusion driven framework is proposed.First,the known flow fie...Artificial intelligence technology is introduced into the simulation of muzzle flow field to improve its simulation efficiency in this paper.A data-physical fusion driven framework is proposed.First,the known flow field data is used to initialize the model parameters,so that the parameters to be trained are close to the optimal value.Then physical prior knowledge is introduced into the training process so that the prediction results not only meet the known flow field information but also meet the physical conservation laws.Through two examples,it is proved that the model under the fusion driven framework can solve the strongly nonlinear flow field problems,and has stronger generalization and expansion.The proposed model is used to solve a muzzle flow field,and the safety clearance behind the barrel side is divided.It is pointed out that the shape of the safety clearance under different launch speeds is roughly the same,and the pressure disturbance in the area within 9.2 m behind the muzzle section exceeds the safety threshold,which is a dangerous area.Comparison with the CFD results shows that the calculation efficiency of the proposed model is greatly improved under the condition of the same calculation accuracy.The proposed model can quickly and accurately simulate the muzzle flow field under various launch conditions.展开更多
短时交通流预测在智能交通系统中扮演重要的角色。针对交通流复杂多变的时空特征、非平稳性及外部因素引发的数据异常,提出考虑异常因素的混合深度神经网络预测模型(hybrid deep neural network forecasting model considering anomalou...短时交通流预测在智能交通系统中扮演重要的角色。针对交通流复杂多变的时空特征、非平稳性及外部因素引发的数据异常,提出考虑异常因素的混合深度神经网络预测模型(hybrid deep neural network forecasting model considering anomalous factors,HDNNF-CAF)。该模型将邻接矩阵、交通流量矩阵及交通流其他参数矩阵结合异常数据处理理论,进行数据预处理和异常数据识别。建立异常数据时空特征提取理论,捕获异常数据时空信息;利用变分模态分解(VMD)降低交通流数据非平稳性,并提出图卷积网络(GCN)优化Informer理论分别对各个子序列进行特征提取,以组合生成交通流时空信息。最终结合异常数据与交通流数据的时空信息生成预测结果。在真实数据集PeMS04上进行验证,实验结果表明,HDNNF-CAF能够有效识别交通流异常数据,提高预测精度,优于一些现有方法。展开更多
深度学习在飞机设计中备受瞩目,特别是在AI for Science的推动下,基于神经网络的数据驱动方法在翼型流场预测方面取得了显著成功。然而,在标注数据有限的情况下,这些方法往往表现欠佳。针对该问题,提出了一种名为Semi-Flow的半监督学习...深度学习在飞机设计中备受瞩目,特别是在AI for Science的推动下,基于神经网络的数据驱动方法在翼型流场预测方面取得了显著成功。然而,在标注数据有限的情况下,这些方法往往表现欠佳。针对该问题,提出了一种名为Semi-Flow的半监督学习方法,用于翼型流场预测。Semi-Flow利用神经网络的损失记忆特性,根据损失函数值,将伪标签数据分为简单和困难两个子集。这种聚类方法基于高斯混合模型,将损失函数结合数据损失和辅助物理监督,确保模型结果符合气动特性和数据约束。在数据选择过程中,选择两个模型共同的简单样本作为训练样本,避免噪声样本的影响。训练过程首先对标注样本进行几轮热身训练,然后逐步添加经过过滤的简单样本。实验结果表明,Semi-Flow方法在标记数据有限的情况下相比于仅基于少量标记数据训练表现优异,总体预测性能提升了近30%。消融研究和定性结果验证了其有效性。Semi-Flow展示了AI for Science的潜力,通过减少对大量标注数据的依赖,为流场预测提供了有前景的方法。展开更多
为建立准确有效的空中交通短期流量预测模型,提高终端区管理效率,以进场交通流为对象进行研究。首先采用自回归移动平均(autoregressive moving average,ARMA)模型对流量时间序列进行初步线性预测,然后通过长短期记忆网络(long short te...为建立准确有效的空中交通短期流量预测模型,提高终端区管理效率,以进场交通流为对象进行研究。首先采用自回归移动平均(autoregressive moving average,ARMA)模型对流量时间序列进行初步线性预测,然后通过长短期记忆网络(long short term memory,LSTM)模型对线性预测后的残差序列进行非线性修正预测。考虑到冗余特征会降低LSTM模型预测精度的问题,采用自编码器(autoencoder,AE)模型对LSTM模型的天气以及流量特征输入进行自适应压缩优化,最后设置对比实验对ARMA-AE-LSTM模型的准确性、鲁棒性以及时效性进行验证。实验结果表明:预测绝对误差在1.3架以内的占比达到75%;LSTM模型的平均每轮迭代时间降低为1.014 s;与其他常用深度学习预测模型相比,ARMA-AE-LSTM模型的均方根误差(root mean square error,RMSE)、平均绝对误差(mean absolute error,MAE)以及决定系数(r-squared,R2)评价指标分别改善了45.98%~67.66%、48.56%~67.35%、5.18%~21.07%;恶劣天气影响下,ARMA-AE-LSTM模型的鲁棒性更好。由此可见,该方法能够准确有效快速的预测空中交通流量。展开更多
基金Supported by the Natural Science Foundation of Jiangsu Province of China(Grant No.BK20210347)Supported by the National Natural Science Foundation of China(Grant No.U2141246).
文摘Artificial intelligence technology is introduced into the simulation of muzzle flow field to improve its simulation efficiency in this paper.A data-physical fusion driven framework is proposed.First,the known flow field data is used to initialize the model parameters,so that the parameters to be trained are close to the optimal value.Then physical prior knowledge is introduced into the training process so that the prediction results not only meet the known flow field information but also meet the physical conservation laws.Through two examples,it is proved that the model under the fusion driven framework can solve the strongly nonlinear flow field problems,and has stronger generalization and expansion.The proposed model is used to solve a muzzle flow field,and the safety clearance behind the barrel side is divided.It is pointed out that the shape of the safety clearance under different launch speeds is roughly the same,and the pressure disturbance in the area within 9.2 m behind the muzzle section exceeds the safety threshold,which is a dangerous area.Comparison with the CFD results shows that the calculation efficiency of the proposed model is greatly improved under the condition of the same calculation accuracy.The proposed model can quickly and accurately simulate the muzzle flow field under various launch conditions.
文摘短时交通流预测在智能交通系统中扮演重要的角色。针对交通流复杂多变的时空特征、非平稳性及外部因素引发的数据异常,提出考虑异常因素的混合深度神经网络预测模型(hybrid deep neural network forecasting model considering anomalous factors,HDNNF-CAF)。该模型将邻接矩阵、交通流量矩阵及交通流其他参数矩阵结合异常数据处理理论,进行数据预处理和异常数据识别。建立异常数据时空特征提取理论,捕获异常数据时空信息;利用变分模态分解(VMD)降低交通流数据非平稳性,并提出图卷积网络(GCN)优化Informer理论分别对各个子序列进行特征提取,以组合生成交通流时空信息。最终结合异常数据与交通流数据的时空信息生成预测结果。在真实数据集PeMS04上进行验证,实验结果表明,HDNNF-CAF能够有效识别交通流异常数据,提高预测精度,优于一些现有方法。
文摘深度学习在飞机设计中备受瞩目,特别是在AI for Science的推动下,基于神经网络的数据驱动方法在翼型流场预测方面取得了显著成功。然而,在标注数据有限的情况下,这些方法往往表现欠佳。针对该问题,提出了一种名为Semi-Flow的半监督学习方法,用于翼型流场预测。Semi-Flow利用神经网络的损失记忆特性,根据损失函数值,将伪标签数据分为简单和困难两个子集。这种聚类方法基于高斯混合模型,将损失函数结合数据损失和辅助物理监督,确保模型结果符合气动特性和数据约束。在数据选择过程中,选择两个模型共同的简单样本作为训练样本,避免噪声样本的影响。训练过程首先对标注样本进行几轮热身训练,然后逐步添加经过过滤的简单样本。实验结果表明,Semi-Flow方法在标记数据有限的情况下相比于仅基于少量标记数据训练表现优异,总体预测性能提升了近30%。消融研究和定性结果验证了其有效性。Semi-Flow展示了AI for Science的潜力,通过减少对大量标注数据的依赖,为流场预测提供了有前景的方法。
文摘为建立准确有效的空中交通短期流量预测模型,提高终端区管理效率,以进场交通流为对象进行研究。首先采用自回归移动平均(autoregressive moving average,ARMA)模型对流量时间序列进行初步线性预测,然后通过长短期记忆网络(long short term memory,LSTM)模型对线性预测后的残差序列进行非线性修正预测。考虑到冗余特征会降低LSTM模型预测精度的问题,采用自编码器(autoencoder,AE)模型对LSTM模型的天气以及流量特征输入进行自适应压缩优化,最后设置对比实验对ARMA-AE-LSTM模型的准确性、鲁棒性以及时效性进行验证。实验结果表明:预测绝对误差在1.3架以内的占比达到75%;LSTM模型的平均每轮迭代时间降低为1.014 s;与其他常用深度学习预测模型相比,ARMA-AE-LSTM模型的均方根误差(root mean square error,RMSE)、平均绝对误差(mean absolute error,MAE)以及决定系数(r-squared,R2)评价指标分别改善了45.98%~67.66%、48.56%~67.35%、5.18%~21.07%;恶劣天气影响下,ARMA-AE-LSTM模型的鲁棒性更好。由此可见,该方法能够准确有效快速的预测空中交通流量。
