针对传统奇异值阈值(Singular Value Thresholding,SVT)数据恢复算法在对电力负荷数据恢复中忽视数据先验信息以及大规模数据计算效率低等问题,提出一种基于相空间重构与自适应变步长的改进SVT的数据恢复算法.为解决传统SVT容易忽视数...针对传统奇异值阈值(Singular Value Thresholding,SVT)数据恢复算法在对电力负荷数据恢复中忽视数据先验信息以及大规模数据计算效率低等问题,提出一种基于相空间重构与自适应变步长的改进SVT的数据恢复算法.为解决传统SVT容易忽视数据先验信息的问题,引入相空间重构算法将原始缺失数据映射到高维空间,利用数据间的关联性和结构特征,为后续数据恢复算法提供先验知识;结合对数与Sigmoid函数构建变步长基础函数,并利用等比项提高前期步长,构建自适应变步长SVT算法,克服传统SVT在大规模数据情况下计算效率低的问题.结合多项公用电力负荷数据集及多种常用电力负荷数据恢复算法进行对比实验分析,结果表明,改进SVT算法可获得更好的数据恢复效果,收敛速度、精度以及稳定性得到提升,具有较强的工程实用性.展开更多
针对中长期电力负荷序列噪声含量高、难以直接提取序列周期规律从而影响预测精度的问题,提出了一种基于完全自适应噪声集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)和奇异谱分析(sin...针对中长期电力负荷序列噪声含量高、难以直接提取序列周期规律从而影响预测精度的问题,提出了一种基于完全自适应噪声集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)和奇异谱分析(singular spectrum analysis,SSA)双重分解的双向长短时记忆网络(bidirectional long and short time memory,BiLSTM)预测模型。首先,采用CEEMDAN对历史负荷进行分解,以得到若干个周期规律更为清晰的子序列;再利用多尺度熵(multiscale entropy,MSE)计算所有子序列的复杂程度,根据不同时间尺度上的样本熵值将相似的子序列重构聚合;然后,利用SSA去噪的功能,对高度复杂的新序列进行二次分解,去除序列中的噪声并提取更为主要的规律,从而进一步提高中长序列预测精度;再将得到的最终一组子序列输入BiLSTM进行预测;最后,考虑到天气、节假日等外部因素对电力负荷的影响,提出了一种误差修正技术。选取了巴拿马某地区的用电负荷进行实验,实验结果表明,经过双重分解可以将均方根误差降低87.4%;预测未来一年的负荷序列时,采用的BiLSTM模型将拟合系数最高提高2.5%;所提出的误差修正技术可将均方根误差降低9.7%。展开更多
Vibration acceleration signals are often measured from case surface of arunning machine to monitor its condition. If the measured vibration signals display to have periodicimpulse components with a certain frequency, ...Vibration acceleration signals are often measured from case surface of arunning machine to monitor its condition. If the measured vibration signals display to have periodicimpulse components with a certain frequency, there may exist a corresponding local fault in themachine, and if further extracting the periodic impulse components from the vibration signals, theseverity of the local fault can be estimated and tracked. However, the signal-to-noise ratios (SNRs)of the vibration acceleration signals are often so small that the periodic impulse components aresubmersed in much background noises and other components, and it is difficult or inconvenient for usto detect and extract the periodic impulse components with the current common analyzing methods forvibration signals. Therefore, another technique, called singular value decomposition (SVD), istried to be introduced to solve the problem. First, the principle of detecting and extracting thesignal periodic components using singular value decomposition is summarized and discussed. Second,the infeasibility of the direct use of the existing SVD based detecting and extracting approach ispointed out. Third, the approach to construct the matrix for SVD from the signal series is improvedlargely, which is the key program to improve the SVD technique; Other associated improvement is alsoproposed. Finally, a simulating application example and a real-life application example ondetecting and extracting the periodic impulse components are given, which showed that the introducedand improved SVD technique is feasible.展开更多
We study the problem of parameter estimation for mean-reverting α-stable motion, dXt = （a0 - θ0Xt）dt ＋ dZt, observed at discrete time instants. A least squares estimator is obtained and its asymptotics is discuss...We study the problem of parameter estimation for mean-reverting α-stable motion, dXt = （a0 - θ0Xt）dt ＋ dZt, observed at discrete time instants. A least squares estimator is obtained and its asymptotics is discussed in the singular case （a0, θ0） = （0, 0）. If a0 = 0, then the mean-reverting α-stable motion becomes Ornstein-Uhlenbeck process and is studied in [7] in the ergodic case θ0 〉 0. For the Ornstein-Uhlenbeck process, asymptotics of the least squares estimators for the singular case （θ0 = 0） and for ergodic case （θ0 〉 0） are completely different.展开更多
In recent years, Empirical mode decomposition and Hilbert spectral analysis have been combined to identify system parameters. Singular-Value Decomposition is pro- posed as a signal preprocessing technique of Hilbert-H...In recent years, Empirical mode decomposition and Hilbert spectral analysis have been combined to identify system parameters. Singular-Value Decomposition is pro- posed as a signal preprocessing technique of Hilbert-Huang Transform to extract modal parameters for closely spaced modes and low-energy components. The proposed method is applied to a simulated airplane model built in Automatic Dynamic Analysis of Mechanical Systems software. The results demonstrate that the identified modal parameters are in good agreement with the baseline model.展开更多
作为解决信息过载问题的有效方式,推荐系统能够根据用户偏好对海量信息进行过滤,为用户提供个性化的推荐.但在推荐过程中,性能表现优异的协同过滤模型并没有充分利用上下文信息,这在一定程度上使系统面临性能瓶颈.为了进一步提高系统性...作为解决信息过载问题的有效方式,推荐系统能够根据用户偏好对海量信息进行过滤,为用户提供个性化的推荐.但在推荐过程中,性能表现优异的协同过滤模型并没有充分利用上下文信息,这在一定程度上使系统面临性能瓶颈.为了进一步提高系统性能,从评分上下文信息着手,通过对项目评分进行分类统计获得评分奇异性,同时借鉴多渠道扩散相似性模型将推荐系统作为用户-项目二分网络的思想,提出了融合奇异性和扩散过程的协同过滤模型(collaborative filtering model fusing singularity and diffusion process,简称CFSDP).为了表明模型的优越性,比较实验基于MovieLens,NetFlix和Jester这3个不同的数据集展开.实验结果表明,该模型不仅具有良好的扩展性,而且在合理的时间开销下,可以显著提高系统的预测和推荐质量.展开更多
文摘针对传统奇异值阈值(Singular Value Thresholding,SVT)数据恢复算法在对电力负荷数据恢复中忽视数据先验信息以及大规模数据计算效率低等问题,提出一种基于相空间重构与自适应变步长的改进SVT的数据恢复算法.为解决传统SVT容易忽视数据先验信息的问题,引入相空间重构算法将原始缺失数据映射到高维空间,利用数据间的关联性和结构特征,为后续数据恢复算法提供先验知识;结合对数与Sigmoid函数构建变步长基础函数,并利用等比项提高前期步长,构建自适应变步长SVT算法,克服传统SVT在大规模数据情况下计算效率低的问题.结合多项公用电力负荷数据集及多种常用电力负荷数据恢复算法进行对比实验分析,结果表明,改进SVT算法可获得更好的数据恢复效果,收敛速度、精度以及稳定性得到提升,具有较强的工程实用性.
文摘针对中长期电力负荷序列噪声含量高、难以直接提取序列周期规律从而影响预测精度的问题,提出了一种基于完全自适应噪声集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)和奇异谱分析(singular spectrum analysis,SSA)双重分解的双向长短时记忆网络(bidirectional long and short time memory,BiLSTM)预测模型。首先,采用CEEMDAN对历史负荷进行分解,以得到若干个周期规律更为清晰的子序列;再利用多尺度熵(multiscale entropy,MSE)计算所有子序列的复杂程度,根据不同时间尺度上的样本熵值将相似的子序列重构聚合;然后,利用SSA去噪的功能,对高度复杂的新序列进行二次分解,去除序列中的噪声并提取更为主要的规律,从而进一步提高中长序列预测精度;再将得到的最终一组子序列输入BiLSTM进行预测;最后,考虑到天气、节假日等外部因素对电力负荷的影响,提出了一种误差修正技术。选取了巴拿马某地区的用电负荷进行实验,实验结果表明,经过双重分解可以将均方根误差降低87.4%;预测未来一年的负荷序列时,采用的BiLSTM模型将拟合系数最高提高2.5%;所提出的误差修正技术可将均方根误差降低9.7%。
基金This project is supported by National Natural Science Foundation of China (No.59905011, 60275041).
文摘Vibration acceleration signals are often measured from case surface of arunning machine to monitor its condition. If the measured vibration signals display to have periodicimpulse components with a certain frequency, there may exist a corresponding local fault in themachine, and if further extracting the periodic impulse components from the vibration signals, theseverity of the local fault can be estimated and tracked. However, the signal-to-noise ratios (SNRs)of the vibration acceleration signals are often so small that the periodic impulse components aresubmersed in much background noises and other components, and it is difficult or inconvenient for usto detect and extract the periodic impulse components with the current common analyzing methods forvibration signals. Therefore, another technique, called singular value decomposition (SVD), istried to be introduced to solve the problem. First, the principle of detecting and extracting thesignal periodic components using singular value decomposition is summarized and discussed. Second,the infeasibility of the direct use of the existing SVD based detecting and extracting approach ispointed out. Third, the approach to construct the matrix for SVD from the signal series is improvedlargely, which is the key program to improve the SVD technique; Other associated improvement is alsoproposed. Finally, a simulating application example and a real-life application example ondetecting and extracting the periodic impulse components are given, which showed that the introducedand improved SVD technique is feasible.
基金Hu is supported by the National Science Foundation under Grant No.DMS0504783Long is supported by FAU Start-up funding at the C. E. Schmidt College of Science
文摘We study the problem of parameter estimation for mean-reverting α-stable motion, dXt = （a0 - θ0Xt）dt ＋ dZt, observed at discrete time instants. A least squares estimator is obtained and its asymptotics is discussed in the singular case （a0, θ0） = （0, 0）. If a0 = 0, then the mean-reverting α-stable motion becomes Ornstein-Uhlenbeck process and is studied in [7] in the ergodic case θ0 〉 0. For the Ornstein-Uhlenbeck process, asymptotics of the least squares estimators for the singular case （θ0 = 0） and for ergodic case （θ0 〉 0） are completely different.
文摘In recent years, Empirical mode decomposition and Hilbert spectral analysis have been combined to identify system parameters. Singular-Value Decomposition is pro- posed as a signal preprocessing technique of Hilbert-Huang Transform to extract modal parameters for closely spaced modes and low-energy components. The proposed method is applied to a simulated airplane model built in Automatic Dynamic Analysis of Mechanical Systems software. The results demonstrate that the identified modal parameters are in good agreement with the baseline model.
文摘作为解决信息过载问题的有效方式,推荐系统能够根据用户偏好对海量信息进行过滤,为用户提供个性化的推荐.但在推荐过程中,性能表现优异的协同过滤模型并没有充分利用上下文信息,这在一定程度上使系统面临性能瓶颈.为了进一步提高系统性能,从评分上下文信息着手,通过对项目评分进行分类统计获得评分奇异性,同时借鉴多渠道扩散相似性模型将推荐系统作为用户-项目二分网络的思想,提出了融合奇异性和扩散过程的协同过滤模型(collaborative filtering model fusing singularity and diffusion process,简称CFSDP).为了表明模型的优越性,比较实验基于MovieLens,NetFlix和Jester这3个不同的数据集展开.实验结果表明,该模型不仅具有良好的扩展性,而且在合理的时间开销下,可以显著提高系统的预测和推荐质量.
