An exact statistical fit and auto-correction system for neutron log data has been set up with the use of image network statistics, network weighted analysis ( algorithm) and fit. 利用图象网络统计、拟合、加权分析技术,提出中子测井资料环境影响校正分析方法和处理模式,建立起精细的统计、拟合自动分析校正系统。
First, the original sequence of log data preprocessed are converted into a set of maximal forward references. Second, using the algorithm similar to the Apriori to discover frequent access patterns. 首先把经过预处理后的日志数据转换为最大前向引用的集合,然后使用Apriori算法挖掘出频繁访问模式。
According to a great deal of coring, rock-electric experiment, well testing and log data, this paper provides a set of quantitative method by means of mathematical statistics. 方法:依据取心、岩电实验、试油及测井资料,采用数理统计方法,制定了一套定量划分高矿化度地层水淹层级别的方法。
As to the 343 training set data according to the principle with 7 LOG space, a neural network topology with two hidden layers with a few neurons and the efficient and robust quasi-Newton method are applied to establish neural network model in this paper. 针对7点LOG空间分布方案的343个训练样本,提出了采用2个隐层和少节点网络结构的方案,并用拟牛顿法训练神经网络模型。
The purpose of well log interpretation is using various tools and technologies comprehensively to tap the strata information which is involved in logging data, to set up the relations between logging data and geological objective and to describe the geological characters of the targets. 测井解释的目的在于综合利用各种技术手段,充分挖掘测井资料所包含的地层信息,建立测井数据向地质目标的映射关系,描述目的层的地质特征。
By using the core analysis data of key wells to standardize log data, the log interpretation model fitting for calculating the porosity, permeability parameters is set up, and its liability is tested. 利用关键井的岩心分析数据来标定测井资料,建立了孔隙度、渗透率等参数的解释模型,并验证了其可靠性,提高了测井解释精度,为油气田的生产提供了可靠的依据。
In the experiments, we use the click-through log data from a commercial search engine, extract rank-related features and set up datasets. 在实验中,我们使用某商业搜索引擎的查询点击数据,抽取影响网页排序的特征集合,构造实验所需的数据集。
RCAS randomly selects subset of unlabeled data to expand the negative sample set and make use of log data and feedback result to expand the positive sample set, which solves the problem of small sample problem and asymmetry problem. 并从未标记数据中随机抽取子集扩充负例样本集合,利用日志数据和相关反馈结果扩充正例样本集合。从而解决了小样本和不对称问题。