In this research,an integrated classification method based on principal component analysis-simulated annealing genetic algorithm-fuzzy cluster means(PCA-SAGA-FCM)was proposed for the unsupervised classification of tig...In this research,an integrated classification method based on principal component analysis-simulated annealing genetic algorithm-fuzzy cluster means(PCA-SAGA-FCM)was proposed for the unsupervised classification of tight sandstone reservoirs which lack the prior information and core experiments.A variety of evaluation parameters were selected,including lithology characteristic parameters,poro-permeability quality characteristic parameters,engineering quality characteristic parameters,and pore structure characteristic parameters.The PCA was used to reduce the dimension of the evaluation pa-rameters,and the low-dimensional data was used as input.The unsupervised reservoir classification of tight sandstone reservoir was carried out by the SAGA-FCM,the characteristics of reservoir at different categories were analyzed and compared with the lithological profiles.The analysis results of numerical simulation and actual logging data show that:1)compared with FCM algorithm,SAGA-FCM has stronger stability and higher accuracy;2)the proposed method can cluster the reservoir flexibly and effectively according to the degree of membership;3)the results of reservoir integrated classification match well with the lithologic profle,which demonstrates the reliability of the classification method.展开更多
可再生能源的间歇性出力以及负荷的波动给综合能源系统(integrated energy systems,IES)引入了大量不确定性因素。提出了一种基于K-means聚类技术改进的多线性蒙特卡洛概率能流计算方法。首先,引入输入随机变量整体灵敏度系数概念,并以...可再生能源的间歇性出力以及负荷的波动给综合能源系统(integrated energy systems,IES)引入了大量不确定性因素。提出了一种基于K-means聚类技术改进的多线性蒙特卡洛概率能流计算方法。首先,引入输入随机变量整体灵敏度系数概念,并以权重系数的形式修正输入随机变量样本,改进K-means聚类效果,确保各聚类簇均具有较小的波动范围。然后,采用多线性化求解思路进行概率能流计算,即对聚类中心进行确定性能流计算,而各聚类簇中输入随机变量样本利用同一簇聚类中心处得到的状态变量和雅可比矩阵进行线性化能流求解,从而减少了迭代过程,提高计算效率。以IEEE57节点电力系统和14节点天然气网络构成的IES为算例,验证了所提方法比传统蒙特卡洛法具有更高的计算效率,相比现有多线性蒙特卡洛算法具有更高的准确性和计算效率。展开更多
准确的能源负荷预测对综合能源系统的经济调度和优化运行有着重要的影响。提出一种基于径向基函数神经网络(radial basis function neural network,RBF-NN)模型的综合能源系统电、气、热多元负荷短期预测方法。首先利用Copula理论对电...准确的能源负荷预测对综合能源系统的经济调度和优化运行有着重要的影响。提出一种基于径向基函数神经网络(radial basis function neural network,RBF-NN)模型的综合能源系统电、气、热多元负荷短期预测方法。首先利用Copula理论对电、气、热负荷进行相关性分析,建立了电、气、热负荷和温度的时间序列;接着设计RBF.NN网络模型结构,采用K.means聚类算法对隐含层节点进行优化;最后通过国内某园区综合能源系统的实际数据对模型进行验证。通过3个案例结果的比较,验证了文中提出的方法可以有效地考虑电、气、热负荷之间的耦合关系,具有较高的预测精度。展开更多
Objective： To analyze the clinical evaluation of Parkinson＇s disease （PD） patients receiving integrated Chinese and Western medicine therapy. Methods： One hundred and twenty patients were enrolled and randomly al...Objective： To analyze the clinical evaluation of Parkinson＇s disease （PD） patients receiving integrated Chinese and Western medicine therapy. Methods： One hundred and twenty patients were enrolled and randomly allocated to a control group or treatment group. Patients in the two groups received placebo and Bushen Huoxue Granule （补肾活血颗粒, BHG）, respectively. Both groups received baseline levodopa and benserazide （Madopar）. The effects of treatment were assessed monthly during the 9-month treatment. Means of evaluation included Unified PD Rating Scale （UPDRS） scores （Ⅱ and Ⅲ）, sleep scale score, 10 m turn back test （getting up time, 10 m × 2 times, and turning time）, timing motor test （TMT）-Ieft and TMT-right, which were treated as the dependent variables; and age, sex, duration of PD, Hoehn and Yahr （H-Y） stage and Madopar dosage of admitted PD patients were as the independent variables. Multiple linear regression was used to analyze these factors. Results： H-Y stage significantly affected UPDRSⅡ score, UPDRS Ⅲ score, and getting up time （P〈0.01）. Madopar dosage and H-Y stage significantly affected the 10 m × 2 times （P〈0.05 or P〈0.01）. Madopar dosage significantly affected the sleep scale score （P〈0.05）. There were also significant correlations between age and TMT-left or TMT-right （P〈0.01）, and duration of PD and TMT-right （P〈0.05）. Conclusions： The six assessed means of clinical evaluation （including UPDRS Ⅱ and UPDRS Ⅲ scores, sleep scale score, getting up time, 10 m × 2 times, and turning time） are sensitive indexes in all PD patients. H-Y stage and Madopar dosage are the major factors influencing means of clinical assessment of PD treatment.展开更多
基金funded by the National Natural Science Foundation of China(42174131)the Strategic Cooperation Technology Projects of CNPC and CUPB(ZLZX2020-03).
文摘In this research,an integrated classification method based on principal component analysis-simulated annealing genetic algorithm-fuzzy cluster means(PCA-SAGA-FCM)was proposed for the unsupervised classification of tight sandstone reservoirs which lack the prior information and core experiments.A variety of evaluation parameters were selected,including lithology characteristic parameters,poro-permeability quality characteristic parameters,engineering quality characteristic parameters,and pore structure characteristic parameters.The PCA was used to reduce the dimension of the evaluation pa-rameters,and the low-dimensional data was used as input.The unsupervised reservoir classification of tight sandstone reservoir was carried out by the SAGA-FCM,the characteristics of reservoir at different categories were analyzed and compared with the lithological profiles.The analysis results of numerical simulation and actual logging data show that:1)compared with FCM algorithm,SAGA-FCM has stronger stability and higher accuracy;2)the proposed method can cluster the reservoir flexibly and effectively according to the degree of membership;3)the results of reservoir integrated classification match well with the lithologic profle,which demonstrates the reliability of the classification method.
文摘可再生能源的间歇性出力以及负荷的波动给综合能源系统(integrated energy systems,IES)引入了大量不确定性因素。提出了一种基于K-means聚类技术改进的多线性蒙特卡洛概率能流计算方法。首先,引入输入随机变量整体灵敏度系数概念,并以权重系数的形式修正输入随机变量样本,改进K-means聚类效果,确保各聚类簇均具有较小的波动范围。然后,采用多线性化求解思路进行概率能流计算,即对聚类中心进行确定性能流计算,而各聚类簇中输入随机变量样本利用同一簇聚类中心处得到的状态变量和雅可比矩阵进行线性化能流求解,从而减少了迭代过程,提高计算效率。以IEEE57节点电力系统和14节点天然气网络构成的IES为算例,验证了所提方法比传统蒙特卡洛法具有更高的计算效率,相比现有多线性蒙特卡洛算法具有更高的准确性和计算效率。
文摘准确的能源负荷预测对综合能源系统的经济调度和优化运行有着重要的影响。提出一种基于径向基函数神经网络(radial basis function neural network,RBF-NN)模型的综合能源系统电、气、热多元负荷短期预测方法。首先利用Copula理论对电、气、热负荷进行相关性分析,建立了电、气、热负荷和温度的时间序列;接着设计RBF.NN网络模型结构,采用K.means聚类算法对隐含层节点进行优化;最后通过国内某园区综合能源系统的实际数据对模型进行验证。通过3个案例结果的比较,验证了文中提出的方法可以有效地考虑电、气、热负荷之间的耦合关系,具有较高的预测精度。
基金Supported by the National Ministry of Science and Technology "Eleventh Five-Year" Project of China(No.2006BA104A11)
文摘Objective： To analyze the clinical evaluation of Parkinson＇s disease （PD） patients receiving integrated Chinese and Western medicine therapy. Methods： One hundred and twenty patients were enrolled and randomly allocated to a control group or treatment group. Patients in the two groups received placebo and Bushen Huoxue Granule （补肾活血颗粒, BHG）, respectively. Both groups received baseline levodopa and benserazide （Madopar）. The effects of treatment were assessed monthly during the 9-month treatment. Means of evaluation included Unified PD Rating Scale （UPDRS） scores （Ⅱ and Ⅲ）, sleep scale score, 10 m turn back test （getting up time, 10 m × 2 times, and turning time）, timing motor test （TMT）-Ieft and TMT-right, which were treated as the dependent variables; and age, sex, duration of PD, Hoehn and Yahr （H-Y） stage and Madopar dosage of admitted PD patients were as the independent variables. Multiple linear regression was used to analyze these factors. Results： H-Y stage significantly affected UPDRSⅡ score, UPDRS Ⅲ score, and getting up time （P〈0.01）. Madopar dosage and H-Y stage significantly affected the 10 m × 2 times （P〈0.05 or P〈0.01）. Madopar dosage significantly affected the sleep scale score （P〈0.05）. There were also significant correlations between age and TMT-left or TMT-right （P〈0.01）, and duration of PD and TMT-right （P〈0.05）. Conclusions： The six assessed means of clinical evaluation （including UPDRS Ⅱ and UPDRS Ⅲ scores, sleep scale score, getting up time, 10 m × 2 times, and turning time） are sensitive indexes in all PD patients. H-Y stage and Madopar dosage are the major factors influencing means of clinical assessment of PD treatment.
