Sodium potassium niobate (KNN) (K0.5Na0.5NbO3) nanopowder with a mean particle size of about 20 - 30 nm was synthesized by wet chemical route using Nb2O5 as Nb source. A solution of K, Na and Nb cations was prepared, ...Sodium potassium niobate (KNN) (K0.5Na0.5NbO3) nanopowder with a mean particle size of about 20 - 30 nm was synthesized by wet chemical route using Nb2O5 as Nb source. A solution of K, Na and Nb cations was prepared, which resulted in a clear gel after the thermal treatment. Phase analysis, microstructure and morphology of the powder were determined by X-ray Diffraction (XRD), Fourier Transform Infrared Spectroscopy (FTIR) and Field Emission Scanning Electron Microscopy (FESEM). The obtained gel was first analyzed by Thermo Gravimetric Analyzer (TGA) and Differential Scanning Calorimetry (DSC), and then calcined at different temperatures of 400℃, 500℃, 600℃ and 700℃. The X-Ray Diffraction (XRD) patterns of the synthesized samples confirmed the formation of the orthorhombic crystal phase of K0.5Na0.5NbO3 at 500?C, a temperature significantly lower than that typically used in the conventional mixed oxide route. The process developed in this work is convenient to realize the mass production of KNN nanopowders at low cost and suitable for various industrial applications.展开更多
在智能交通系统中,准确和高效的短时交通流量预测是交通诱导、管理和控制的前提。由于交通流量动态变化中表现出的时变性和非平稳性特征,其预测难度较大,是交通领域中亟待解决的难题。为提高短时交通流量的预测精度,本文设计与实现了基...在智能交通系统中,准确和高效的短时交通流量预测是交通诱导、管理和控制的前提。由于交通流量动态变化中表现出的时变性和非平稳性特征,其预测难度较大,是交通领域中亟待解决的难题。为提高短时交通流量的预测精度,本文设计与实现了基于自适应时序剖分与KNN(A-TS-KNN)的短时交通流量预测算法。①基于动态时间规整(Dynamic Time Warping,DTW)动态剖分单日时序为不同的交通模式;②在不同交通模式,采用互信息法求解每个预测时刻时间延迟的最大阈值,构造不同时间延迟的状态向量,生成交通流量历史数据库;③采用十次十折交叉验证的方法求解每个时刻不同时间延迟与不同K值的正交误差结果分布,提取误差最小的正交结果,得到自适应时间延迟与K值的参数组合;④采用K个最相似的近邻的距离倒数加权值作为预测结果。对比K近邻(K-nearest neighbors,KNN)、支持向量回归(Support vector regression,SVR)、长短期记忆神经网络(Long-short term memory neural network,LSTM)以及门控递归单元神经网络(Gate recurrent unit neural network,GRU)共4种主流预测模型,A-TS-KNN算法预测精度显著提升;将A-TS-KNN算法用于福州市城市路网中其他交叉路口的短时交通流量预测,结果表现出良好的泛化能力。展开更多
文摘Sodium potassium niobate (KNN) (K0.5Na0.5NbO3) nanopowder with a mean particle size of about 20 - 30 nm was synthesized by wet chemical route using Nb2O5 as Nb source. A solution of K, Na and Nb cations was prepared, which resulted in a clear gel after the thermal treatment. Phase analysis, microstructure and morphology of the powder were determined by X-ray Diffraction (XRD), Fourier Transform Infrared Spectroscopy (FTIR) and Field Emission Scanning Electron Microscopy (FESEM). The obtained gel was first analyzed by Thermo Gravimetric Analyzer (TGA) and Differential Scanning Calorimetry (DSC), and then calcined at different temperatures of 400℃, 500℃, 600℃ and 700℃. The X-Ray Diffraction (XRD) patterns of the synthesized samples confirmed the formation of the orthorhombic crystal phase of K0.5Na0.5NbO3 at 500?C, a temperature significantly lower than that typically used in the conventional mixed oxide route. The process developed in this work is convenient to realize the mass production of KNN nanopowders at low cost and suitable for various industrial applications.
文摘在智能交通系统中,准确和高效的短时交通流量预测是交通诱导、管理和控制的前提。由于交通流量动态变化中表现出的时变性和非平稳性特征,其预测难度较大,是交通领域中亟待解决的难题。为提高短时交通流量的预测精度,本文设计与实现了基于自适应时序剖分与KNN(A-TS-KNN)的短时交通流量预测算法。①基于动态时间规整(Dynamic Time Warping,DTW)动态剖分单日时序为不同的交通模式;②在不同交通模式,采用互信息法求解每个预测时刻时间延迟的最大阈值,构造不同时间延迟的状态向量,生成交通流量历史数据库;③采用十次十折交叉验证的方法求解每个时刻不同时间延迟与不同K值的正交误差结果分布,提取误差最小的正交结果,得到自适应时间延迟与K值的参数组合;④采用K个最相似的近邻的距离倒数加权值作为预测结果。对比K近邻(K-nearest neighbors,KNN)、支持向量回归(Support vector regression,SVR)、长短期记忆神经网络(Long-short term memory neural network,LSTM)以及门控递归单元神经网络(Gate recurrent unit neural network,GRU)共4种主流预测模型,A-TS-KNN算法预测精度显著提升;将A-TS-KNN算法用于福州市城市路网中其他交叉路口的短时交通流量预测,结果表现出良好的泛化能力。
