LabVIEW设计中压力传感器的RBF神经网络温度补偿

在石油平台注水压力监测系统设计中 ,采用LabVIEW虚拟仪器平台 ,嵌入逼近能力强和收敛速度快的RBF神经网络 ,以人工环境实验数据为样本进行训练 ,实现了压力传感器的智能网络温度补偿。结果显示 ,此方法能够在压力、温度变化较大的恶劣环境下 ,获得很高的补偿精度。     

区域似大地水准面确定的最小二乘支持向量机方法

支持向量机(SVM)是近年来发展起来的机器学习的新方法,它较好地解决小样本、非线性、高维数、局部极小点等实际问题.文中研究支持向量机的拓展算法--最小二乘支持向量机(LSSVM),并将其应用于确定大面积复杂似大地水准面.通过工程实例并与神经网络模型和二次曲面多项式拟合模型相比较,验证确定区域似大地水准面的LSSVM方法的有效性.     

虚拟样机技术在地质工程机械领域的应用研究

基于对国内地质工程机械的研发现状的考虑，根据虚拟样机技术的特点，讨论了在地质工程机械领域实施虚拟样机技术的必要件，并提出了建立地质工程机械虚拟样机的策略。联合PRO／E、ANSYS及ADAMS建立了气动潜孔锤的虚拟样机模型，对气动潜孔锤虚拟样机进行了仿真，阐明了虚拟样机技术在地质工程机械领域的应用前景。     

Cloning and characterization of glyceraldehyde-3-phosphate dehydrogenase encoding gene inGracilaria/Gracilariopsis lemaneiformis

Glyceraldehyde-3-phosphate dehydrogenase （GAPDH） plays important roles in various cellular processes. A cytosolic GAPDH encoding gene （gpd） of Gracilaria/Gracilariopsis lemaneiformis was cloned and characterized. Deduced amino acid sequence of the enzyme of G. lemaneiformis had high homology with those of seven red algae. The 5＇-untranslated regions of the GAPDHs encoding genes of these red algae varied greatly. GAPDHs of these red algae shared the highly conserved glyceraldehyde 3-phosphate dehydrogenase active site ASCTTNCL. However, such active site of Cyanidium caldarium was different from those of the other six algae at the last two residues （CL to LF）, thus the spatial structure of its GAPDH active center may be different from those of the other six. Phylogenetic analysis indicated that GAPDH of G. lemaneiformis might have undergone an evolution similar to those of Porphyra yezoensis, Chondrus crispus, and Gracilaria verrucosa. C. caldarium had a closer evolutionary relationship with Cyanidioschyzon merolae than with Cyanidium sp. Virtual Northern blot analysis revealed that gpd of G. lemaneiformis expressed constitutively, which suggested that it might be house-keeping and could be adapted as an inner control in gene expression analysis of G. lemaneiformis.     

非线性支持向量机在油气预测中的应用

油气预测的传统方法通常是基于经验风险最小化准则,但在有限样本情况下,预测效果并不理想.研究引入基于结构化风险最小化准则的非线性支持向量机方法,通过对推广误差界的最小化达到最大的泛化能力和全局最优,时于小样本数据,该方法具有可靠的预测能力.在对四川观音场构造面新统上部碳酸盐岩储层数据处理中.通过实例试算,结果表明该方法有效可靠,预测精度高,与已知结果吻合较好.     

一种基于核学习的储集层渗透率预测新方法

基于核学习的支持向量机,是一种采用结构风险最小化原则代替传统经验风险最小化原则的新型统计学习方法,具有完备的理论基础。这里提出了核学习技术在储集层非均质特性描述中渗透率参数预测的新用途。在复杂地层中,基于支持向量机的智能和自适应模式识别能力而建立了常规测井多参数信息输入的渗透率预测模型,然后对实际油田储集层渗透率进行了预测。与常规线性回归模型预测结果相对比,所提出的方法更易于使用,很少受不确定因素的影响,并具有较强的信息整合能力以及更高的预测准确性和可信度。     

三种非线性回归逐时气温预报比较订正

选取ECMWF和T639的2013年1月至2014年12月的数值预报场构造预报因子,基于神经网络、支持向量机和构造函数的非线性方法,预报地面逐时气温。试验结果显示,在单个方法预报误差较大时,3种方法的偏差订正集成方法更利于减小误差,通过偏差订正,3种非线性方法预报效果良好,平均绝对误差减小了0.5 ℃。在近1年独立样本的预报检验中,集成方法、神经网络、支持向量机和构造函数预报的平均绝对误差分别为1.5 ℃、1.7 ℃、1．8 ℃和1．4 ℃,总体上构造函数预报更为准确。     

Site characterization model using least‐square support vector machine and relevance vector machine based on corrected SPT data (Nc)

Statistical learning algorithms provide a viable framework for geotechnical engineering modeling. This paper describes two statistical learning algorithms applied for site characterization modeling based on standard penetration test (SPT) data. More than 2700 field SPT values (N) have been collected from 766 boreholes spread over an area of 220 sqkm area in Bangalore. To get N corrected value (N_c), N values have been corrected (N_c) for different parameters such as overburden stress, size of borehole, type of sampler, length of connecting rod, etc. In three‐dimensional site characterization model, the function N_c=N_c (X, Y, Z), where X, Y and Z are the coordinates of a point corresponding to N_c value, is to be approximated in which N_c value at any half‐space point in Bangalore can be determined. The first algorithm uses least‐square support vector machine (LSSVM), which is related to a ridge regression type of support vector machine. The second algorithm uses relevance vector machine (RVM), which combines the strengths of kernel‐based methods and Bayesian theory to establish the relationships between a set of input vectors and a desired output. The paper also presents the comparative study between the developed LSSVM and RVM model for site characterization. Copyright © 2009 John Wiley & Sons, Ltd.     

高光谱影像概率分类向量机分类方法研究

从分析基于支持向量机和相关向量机的高光谱影像分类方法的优势和不足出发,将基于概率分类向量机的方法用于高光谱影像分类试验。在贝叶斯理论框架下,概率分类向量机为基函数权值引入截断Gauss先验概率分布,使得不同类别的基函数权值具有不同符号的先验分布,并利用EM算法进行参数推断,得到足够稀疏的概率模型,弥补了相关向量机选取错误类别的样本作为相关向量的不足,从而有效地提高了模型的分类精度和稳定性。OMIS和PHI影像分类试验表明,概率分类向量机能够很好地应用在高光谱影像分类。