There are multiple operating modes in the real industrial process, and the collected data follow the complex multimodal distribution, so most traditional process monitoring methods are no longer applicable because the...There are multiple operating modes in the real industrial process, and the collected data follow the complex multimodal distribution, so most traditional process monitoring methods are no longer applicable because their presumptions are that sampled-data should obey the single Gaussian distribution or non-Gaussian distribution. In order to solve these problems, a novel weighted local standardization(WLS) strategy is proposed to standardize the multimodal data, which can eliminate the multi-mode characteristics of the collected data, and normalize them into unimodal data distribution. After detailed analysis of the raised data preprocessing strategy, a new algorithm using WLS strategy with support vector data description(SVDD) is put forward to apply for multi-mode monitoring process. Unlike the strategy of building multiple local models, the developed method only contains a model without the prior knowledge of multi-mode process. To demonstrate the proposed method's validity, it is applied to a numerical example and a Tennessee Eastman(TE) process. Finally, the simulation results show that the WLS strategy is very effective to standardize multimodal data, and the WLS-SVDD monitoring method has great advantages over the traditional SVDD and PCA combined with a local standardization strategy(LNS-PCA) in multi-mode process monitoring.展开更多
According to the chaotic and non-linear characters of power load data,the time series matrix is established with the theory of phase-space reconstruction,and then Lyapunov exponents with chaotic time series are comput...According to the chaotic and non-linear characters of power load data,the time series matrix is established with the theory of phase-space reconstruction,and then Lyapunov exponents with chaotic time series are computed to determine the time delay and the embedding dimension.Due to different features of the data,data mining algorithm is conducted to classify the data into different groups.Redundant information is eliminated by the advantage of data mining technology,and the historical loads that have highly similar features with the forecasting day are searched by the system.As a result,the training data can be decreased and the computing speed can also be improved when constructing support vector machine(SVM) model.Then,SVM algorithm is used to predict power load with parameters that get in pretreatment.In order to prove the effectiveness of the new model,the calculation with data mining SVM algorithm is compared with that of single SVM and back propagation network.It can be seen that the new DSVM algorithm effectively improves the forecast accuracy by 0.75%,1.10% and 1.73% compared with SVM for two random dimensions of 11-dimension,14-dimension and BP network,respectively.This indicates that the DSVM gains perfect improvement effect in the short-term power load forecasting.展开更多
为解决传统检测方法在处理复杂、动态以及数据长度实时变化的飞行轨迹数据时特征提取不准确、检测效率较低的问题,提出一种结合长短时记忆(Long Short-Term Memory, LSTM)网络和支持向量数据描述(Support Vector Data Description, SVDD...为解决传统检测方法在处理复杂、动态以及数据长度实时变化的飞行轨迹数据时特征提取不准确、检测效率较低的问题,提出一种结合长短时记忆(Long Short-Term Memory, LSTM)网络和支持向量数据描述(Support Vector Data Description, SVDD)的无监督异常检测方法。利用LSTM网络提取可变长度飞行轨迹的关键特征,并将其转化为固定长度的序列表示;通过SVDD算法构建多维超球分类器,对正常飞行轨迹进行建模,从而识别潜在异常轨迹。为进一步提升模型性能,引入基于梯度的优化算法(Gradient-Based training algorithm, GB),实现LSTM与SVDD参数的联合训练,大幅度提高检测精度和计算效率。仿真实验结果表明,新提出的基于梯度优化的长短时记忆网络和支持向量数据描述模型(Long Short-Term Memory network and Support Vector Data Description model based on Gradient-Based training algorithm optimization, LSTM-GBSVDD)的飞行轨迹异常检测方法在处理复杂、多变的飞行轨迹异常检测任务中表现出较好的有效性和优越性,有较强的应用前景。展开更多
稀疏线性方程组求解等高性能计算应用常常涉及稀疏矩阵向量乘(SpMV)序列Ax,A2x,…,Asx的计算.上述SpMV序列操作又称为稀疏矩阵幂函数(matrix power kernel,MPK).由于MPK执行多次SpMV且稀疏矩阵保持不变,在缓存(cache)中重用稀疏矩阵,可...稀疏线性方程组求解等高性能计算应用常常涉及稀疏矩阵向量乘(SpMV)序列Ax,A2x,…,Asx的计算.上述SpMV序列操作又称为稀疏矩阵幂函数(matrix power kernel,MPK).由于MPK执行多次SpMV且稀疏矩阵保持不变,在缓存(cache)中重用稀疏矩阵,可避免每次执行SpMV均从主存加载A,从而缓解SpMV访存受限问题,提升MPK性能.但缓存数据重用会导致相邻SpMV操作之间的数据依赖,现有MPK优化多针对单次SpMV调用,或在实现数据重用时引入过多额外开销.提出了缓存感知的MPK(cache-awareMPK,Ca-MPK),基于稀疏矩阵的依赖图,设计了体系结构感知的递归划分方法,将依赖图划分为适合缓存大小的子图/子矩阵,通过构建分割子图解耦数据依赖,根据特定顺序在子矩阵上调度执行SpMV,实现缓存数据重用.测试结果表明,Ca-MPK相对于Intel OneMKL库和最新MPK实现,平均性能提升分别多达约1.57倍和1.40倍.展开更多
鲁棒优化作为应对风电等新能源出力不确定性的重要工具,广泛应用于微电网优化调度中。传统的不确定集不够紧凑,无法准确刻画风电不确定性,同时不确定集包围的数据中可能存在部分异常值,导致调度结果过于保守。针对上述问题,提出了一种...鲁棒优化作为应对风电等新能源出力不确定性的重要工具,广泛应用于微电网优化调度中。传统的不确定集不够紧凑,无法准确刻画风电不确定性,同时不确定集包围的数据中可能存在部分异常值,导致调度结果过于保守。针对上述问题,提出了一种基于数据驱动不确定集的微电网两阶段鲁棒优化调度方法。首先,通过风电历史数据构建条件正态Copula(conditional normal copula,CNC)模型,再将日前风电预测值输入CNC模型生成次日风电功率样本。然后,通过支持向量聚类(support vector clustering,SVC)和维度分解构建考虑风电时间相关性的数据驱动不确定集。该不确定集可更为准确地刻画风电不确定性,并将风电数据中的异常值排除在外,从而在降低鲁棒优化保守性的同时具备异常值抵抗性。其次,提出了基于上述不确定集的两阶段鲁棒优化调度模型,并采用列约束生成(column and constraint generation,C&CG)算法求解。最后通过仿真证明了相较传统不确定集,本文构建的不确定集保守性更低,同时对风电数据异常值具有良好的抵抗性。展开更多
基金Project(61374140)supported by the National Natural Science Foundation of China
文摘There are multiple operating modes in the real industrial process, and the collected data follow the complex multimodal distribution, so most traditional process monitoring methods are no longer applicable because their presumptions are that sampled-data should obey the single Gaussian distribution or non-Gaussian distribution. In order to solve these problems, a novel weighted local standardization(WLS) strategy is proposed to standardize the multimodal data, which can eliminate the multi-mode characteristics of the collected data, and normalize them into unimodal data distribution. After detailed analysis of the raised data preprocessing strategy, a new algorithm using WLS strategy with support vector data description(SVDD) is put forward to apply for multi-mode monitoring process. Unlike the strategy of building multiple local models, the developed method only contains a model without the prior knowledge of multi-mode process. To demonstrate the proposed method's validity, it is applied to a numerical example and a Tennessee Eastman(TE) process. Finally, the simulation results show that the WLS strategy is very effective to standardize multimodal data, and the WLS-SVDD monitoring method has great advantages over the traditional SVDD and PCA combined with a local standardization strategy(LNS-PCA) in multi-mode process monitoring.
基金Project(70671039) supported by the National Natural Science Foundation of China
文摘According to the chaotic and non-linear characters of power load data,the time series matrix is established with the theory of phase-space reconstruction,and then Lyapunov exponents with chaotic time series are computed to determine the time delay and the embedding dimension.Due to different features of the data,data mining algorithm is conducted to classify the data into different groups.Redundant information is eliminated by the advantage of data mining technology,and the historical loads that have highly similar features with the forecasting day are searched by the system.As a result,the training data can be decreased and the computing speed can also be improved when constructing support vector machine(SVM) model.Then,SVM algorithm is used to predict power load with parameters that get in pretreatment.In order to prove the effectiveness of the new model,the calculation with data mining SVM algorithm is compared with that of single SVM and back propagation network.It can be seen that the new DSVM algorithm effectively improves the forecast accuracy by 0.75%,1.10% and 1.73% compared with SVM for two random dimensions of 11-dimension,14-dimension and BP network,respectively.This indicates that the DSVM gains perfect improvement effect in the short-term power load forecasting.
基金Supported by National High Technology Research and Development Program of China （863 Program） （2006AA040308）, National Natural Science Foundation of China （60736021）, and the National Creative Research Groups Science Foundation of China （60721062）
文摘为解决传统检测方法在处理复杂、动态以及数据长度实时变化的飞行轨迹数据时特征提取不准确、检测效率较低的问题,提出一种结合长短时记忆(Long Short-Term Memory, LSTM)网络和支持向量数据描述(Support Vector Data Description, SVDD)的无监督异常检测方法。利用LSTM网络提取可变长度飞行轨迹的关键特征,并将其转化为固定长度的序列表示;通过SVDD算法构建多维超球分类器,对正常飞行轨迹进行建模,从而识别潜在异常轨迹。为进一步提升模型性能,引入基于梯度的优化算法(Gradient-Based training algorithm, GB),实现LSTM与SVDD参数的联合训练,大幅度提高检测精度和计算效率。仿真实验结果表明,新提出的基于梯度优化的长短时记忆网络和支持向量数据描述模型(Long Short-Term Memory network and Support Vector Data Description model based on Gradient-Based training algorithm optimization, LSTM-GBSVDD)的飞行轨迹异常检测方法在处理复杂、多变的飞行轨迹异常检测任务中表现出较好的有效性和优越性,有较强的应用前景。
文摘稀疏线性方程组求解等高性能计算应用常常涉及稀疏矩阵向量乘(SpMV)序列Ax,A2x,…,Asx的计算.上述SpMV序列操作又称为稀疏矩阵幂函数(matrix power kernel,MPK).由于MPK执行多次SpMV且稀疏矩阵保持不变,在缓存(cache)中重用稀疏矩阵,可避免每次执行SpMV均从主存加载A,从而缓解SpMV访存受限问题,提升MPK性能.但缓存数据重用会导致相邻SpMV操作之间的数据依赖,现有MPK优化多针对单次SpMV调用,或在实现数据重用时引入过多额外开销.提出了缓存感知的MPK(cache-awareMPK,Ca-MPK),基于稀疏矩阵的依赖图,设计了体系结构感知的递归划分方法,将依赖图划分为适合缓存大小的子图/子矩阵,通过构建分割子图解耦数据依赖,根据特定顺序在子矩阵上调度执行SpMV,实现缓存数据重用.测试结果表明,Ca-MPK相对于Intel OneMKL库和最新MPK实现,平均性能提升分别多达约1.57倍和1.40倍.
文摘鲁棒优化作为应对风电等新能源出力不确定性的重要工具,广泛应用于微电网优化调度中。传统的不确定集不够紧凑,无法准确刻画风电不确定性,同时不确定集包围的数据中可能存在部分异常值,导致调度结果过于保守。针对上述问题,提出了一种基于数据驱动不确定集的微电网两阶段鲁棒优化调度方法。首先,通过风电历史数据构建条件正态Copula(conditional normal copula,CNC)模型,再将日前风电预测值输入CNC模型生成次日风电功率样本。然后,通过支持向量聚类(support vector clustering,SVC)和维度分解构建考虑风电时间相关性的数据驱动不确定集。该不确定集可更为准确地刻画风电不确定性,并将风电数据中的异常值排除在外,从而在降低鲁棒优化保守性的同时具备异常值抵抗性。其次,提出了基于上述不确定集的两阶段鲁棒优化调度模型,并采用列约束生成(column and constraint generation,C&CG)算法求解。最后通过仿真证明了相较传统不确定集,本文构建的不确定集保守性更低,同时对风电数据异常值具有良好的抵抗性。
