Learn More
A B-spline kernel combined with RBF is developed, a mixed kernel is obtained. By analyzing the structure of the logging signal characteristics, the method is used to automatically identify the water-flooded status of oil-saturated stratum. The experimental results show that the mixed kernel has high recognition accuracy with the advantages of the short(More)
To address training of process neural networks based on the orthogonal basis expansion, a double chains quantum genetic algorithm based on the probability amplitudes of quantum bits is proposed. In this method, the probability amplitudes of each qubit are regarded as two paratactic genes, each chromosome contains two gene chains, and each of gene chains(More)
Depth correction of logging curves is an important part of the logging research, matching curve is the key to the depth correction. This paper presents an effective method for depth correction of logging curves based on LTS Hausdorff distance. In this method, after determining standard curve segment, the position of best contrast curve segment is calculated(More)
For training of process neural networks based on the orthogonal basis expansion, it is difficult to converge for BP algorithm as more parameters. Aiming at the issue, this paper proposes a solution based on quantum genetic algorithm with double chains. Firstly, the number of genes is determined by the number of weight parameters, quantum chromosomes are(More)
According to the characteristics of post evaluation for the productive capacity construction project of oilfield and the actual situation of oilfield, detailed analyzed the evaluation index, the relationship and the impact to the Comprehensive Post Evaluation of the post evaluation for the productive capacity construction project of oilfield, proposed the(More)
Focusing on the users is more interested in the sequential patterns that accord with the well completion business process habit overall in the web access mode of well completion mobile platform. This paper proposed a weighted sequential pattern mining algorithm based on the well completion business process. With analyzing the business process models and web(More)
According to the characteristics of the model number is relatively small, similarity, complexity is not high in the small professional model library, and the existing 3D model retrieval method can not effectively improve the efficiency. This paper puts forward the retrieval algorithms based on normal plane, extract normal vector of each triangular facet in(More)
With the massive explosion of social multimedia community, social images have become very popular in our daily life. The image-associated labels are a valuable resource for automatic image annotation, but they tend to be unreliable. In this paper, we exploit the problem of image annotation from real-world community contributed images and their associated(More)