Xu Chunbi

Application of statistical learning theory to predict corrosion rate of injecting water pipeline

Support Vector Machines (SVM) represents a new and very promising approach to pattern recognition based on small dataset. The approach is systematic and properly motivated by Statistical Learning Theory (SLT). Training involves separating the classes with a surface that maximizes the margin between them. An interesting property of this approach is that it is an approximate implementation of Structural Risk Minimization (SRM) induction principle, therefore, SVM is more generalized performance and accurate as compared to artificial neural network which embodies the Embodies Risk Minimization (ERM) principle. In this paper, according to corrosion rate complicated reflection relation with influence factors, we studied the theory and method of Support Vector Machines based the statistical learning theory and proposed a pattern recognition method based Support Vector Machine to predict corrosion rate of injecting water pipeline. The outline of the method is as follows: First, we researched the injecting water quality corrosion influence factors in given experimental zones with Gray correlation method; then we used the LibSVM software based Support Vector Machine to study the relationship of those injecting water quality corrosion influence factors, and set up the mode to predict corrosion rate of injecting water pipeline. Application and analysis of the experimental results in Shengli oilfield proved that SVM could achieve greater accuracy than the BP neural network do, which also proved that application of SVM to predict corrosion rate of injecting water pipeline, even to the other theme in petroleum engineering, is reliable, adaptable, precise and easy to operate.

The Way of Appraising the Active Degree of Gas Reservoir Considering the Production Performance of Water Invasion Gas Reservoir

The water of body multiple factors calculated by static state and dynamical methods are the simplest ways to distinguish the active degree of water driver gas reservoir recently. However, the active degree of water driver gas reservoir is different in different production stage due to the influence of water body porosity and permeability, the formation communication of water body and gas reservoir, the production position, the well pattern deploying, and the gas well mode, etc. This paper develop a new way to distinguish the active degree of water driver gas reservoir which consider the production performance of water invasion gas reservoir, such as water body porosity and permeability, the formation communication of water body and gas reservoir, the production position, etc.

Prediction Model of Sulfur Precipitation in Gas Well with High H2S Content

For the gas well with high H2S content,the process of sulfur deposition including the sulfur dissolution, precipitation, migration and deposition is a quite complex process. Relative to the solubility of sulfur under certain temperature and the pressure, the sulfur will be separated out when the content of sulfur in high sour gas is surpassed. Based on the theories of mass conservation, momentum conservation, energy conservation, and the transfer of heat in the radial directions of well bore, we established the prediction model of the sulfur precipitation in the high H2S content gas well by using Roberts thermal empirical equation. In view of the examples, the sulfur separation at different levels of production is calculated and discussed by using the self-programming computer.

The Application of Proper Value Method in Non-shut-in Well Testing for High Pressure Gas Well

According to average value and characteristic points and lines of typical curve for dual media, the proper value analysis method was applied here, deviating mathematical expressions of exact resolution for the dual-porosity characteristic parameters such as interporosity flow coefficient and storage ratio in non-shut-in well test analysis of high pressure gas well And taking examples to illustrate the calculation method.