Log interpretation and evaluation of tight sandstone reservoir in Chang 8 Member of Longdong West area, Ordos Basin, China, are facing great challenges due to the co-development of normal oil pay and resistivity low-contrast oil pay. To better guide the exploration and development of oil resources in this area, the reservoir characteristics and control mechanism of resistivity low-contrast oil pay were studied. Firstly, the reservoirs were divided into resistivity low-contrast oil pay (RLP) and normal oil pay (NP) based on the relative value of the apparent resistivity increase rate. Then, the difference of reservoir characteristics between RLP and NP is analyzed by comparing a series of experimental data and real logging data in those two reservoir types. Finally, the control mechanism of RLP was studied from reservoir micro-factors and regional macro-factors, respectively. It is found that the chlorite and illite are the most abundant clay minerals in RLP and NP, respectively. Compared with NP reservoir, the average porosity of RLP is better, but the pore space is mainly composed of micropores, which lead to smaller average pore throat radius and poor pore structure. The high irreducible water saturation and high formation water salinity reduced the reservoir resistivity from micro-aspect. Besides, the difference of hydrocarbon expulsion capacity of source rock and the regional difference of formation water salinity controlled the distribution of RLP and NP. Comprehensive consideration of the reservoir micro-factors and regional macro-factors is important to carry out effective logging interpretation and evaluation.

Resistivity low-contrast oil pays are a kind of unconventional oil resource with no obvious difference in physical and electrical properties from water layers, which makes it difficult to be identified based on the characteristics of the geophysical well logging response. In this study, the support vector machine (SVM) technology was used to interpret the resistivity low-contrast oil pays in Chang 8 tight sandstone reservoir of Huanxian area, Ordos Basin. First, the input data sequences of logging curves were selected by analyzing the relationship between reservoir fluid types and logging data. Then, the SVM classification model for fluid identification and SVR regression model for reservoir parameter prediction were constructed. Finally, these two models were applied to interpret the resistivity low-contrast oil pays in the study area. The application results show that the fluid recognition accuracy of the SVM classification model is higher than that of the logging cross plot method, back propagation neural network method and radial basis function neural network method. The calculation accuracy of permeability and water saturation predicted by the SVR regression model is higher than that based on the experimental fitting model, which indicates that it is feasible to carry out logging interpretation and evaluation of the resistivity low-contrast oil pays by the SVM method. The research results not only provide an important reference and basis for the review of old wells but also provide technical support for the exploration and development of new strata.

In order to improve the logging interpretation accuracy for complex oil and water layers developed in tight sandstone reservoirs, this study takes the Chang 8 member of the Yanchang Formation in the Huanxian area as the research object, and two new fluid identification methods were constructed based on nuclear magnetic resonance (NMR) logging and array acoustic logging. Firstly, the reservoir characteristics of physical properties and conductivity were studied in the research area, and the limitations of conventional logging methods in identifying complex oil and water layers were clarified. Then, the sensitive parameters for identifying different pore fluids were established by analyzing the relationship between NMR logging and array acoustic logging with different pore fluids. On this basis, the fluid identification plate, composed of movable fluid apparent diffusion coefficient and effective porosity difference (D_a-Δφ_e) by NMR logging data of D9TWE3 observation mode, and the other fluid identification plate, composed of apparent bulk modulus of pore fluid and elastic parameter sensitive factor (K_f-Fac), were constructed, respectively. Finally, these two fluid identification methods were used for reservoir interpretation of actual logging data. This study shows that the two new fluid identification methods constructed by NMR logging and array acoustic logging can effectively eliminate the interference of rock skeleton on logging interpretation, which make them more effective in identifying complex oil and water layers than the conventional logging method. Additionally, the two methods have their own advantages and disadvantages when used separately for interpreting complex oil and water layers, and the comprehensive interpretation of the two methods provides a technical development direction for further improving the accuracy of logging the interpretation of complex oil and water layers.

This study focus on saturation evaluation of Chang 8 tight sandstone reservoir in Longdong West area of Ordos Basin, China. An improved saturation calculation method was proposed based on the equivalent rock capillary bundle theory. Firstly, according to characteristics of reservoir pore structure and rock conductivity, the conductive space of reservoir rock is equivalent to the parallel conductive of micro capillary bundle representing the micro pores and the coarse capillary bundle representing the macro pores. Then, the variable cementation index(m) saturation model was deduced by using Poiseuille flow equation and Darcy's law. During the calculation of model parameters, the T₂ spectrum data of nuclear magnetic resonance (NMR) was used to calculate the equivalent radius of reservoir micro pores and macro pores, which ensured the ability of model popularization and application. Finally, the proposed saturation calculation method is applied to reservoir evaluation of the study area, and compared with the classical Archie saturation model. The application effect shows that the calculated saturation from the proposed variable m model is much closer to the sealed coring data than that from classical Archie model, and the average relative error of saturation calculated by the variable m model is within 7%, which proves that the proposed saturation calculation method is applicable and effective.

The coal component content is an important parameter during the coal resources exploration and exploitation. Previous logging curve regression and single neural network methods have the disadvantages of low accuracy and weak generalization ability in calculating coal component content. In this study, a gray relational analysis-hybrid neural network (GRA-HNN) method is developed by combining GRA and HNN to predict coal component content in logging data. First, the correlation degree between different conventional logging data and coal components is calculated using the GRA method, and logging curves with a correlation degree of ≥0.7 are selected as the input training data set. Then, a back propagation neural network, support vector machine neural network, and radial basis function neural network of different coal components are constructed based on the selected optimal input logging data, and the weighted average strategy is used to form an HNN prediction model. Finally, the GRA-HNN method is used to predict the coal component content of coalbed methane production wells in the Panji mining area. The application results indicate that the coal component content predicted by the GRA-HNN method has the highest accuracy compared with the logging curve regression method and its single neural network model, with a maximum average relative error of 13.4%. In addition, the accuracy of coal component content predicted by some single intelligent models is not always higher than the logging curve regression method, indicating that the neural network model is not necessarily suitable for all coal component content predictions. Our GRA-HNN method not only optimizes the prediction performance of a single neural network model by selecting effective input parameters but also comprehensively considers the prediction effect of several neural network models, which strengthens the generalization ability of neural network model and increases the log interpretation accuracy of coal component content.

Low resistivity contrast oil reservoirs are subtle reservoirs that have no obvious difference in physical and electrical properties from water layers. It is difficult to identify based on the characteristics of the geophysical well logging response. Especially in tight sandstone reservoirs with low porosity and low permeability, the log interpretation effect of low resistivity contrast oil layers is worse. In recent years, data mining technology has been increasingly applied in oil exploration and development, especially for some complex reservoirs with unclear logging response characteristics, and how to use data mining technology to effectively solve some complex problems is of great significance in oilfields. Therefore, support vector machine (SVM) technology was applied to interpret the low resistivity contrast oil layer in this paper. First, the input data sequences of logging curves were selected by analyzing the relationship between reservoir fluid types and logging data. Then, the SVM classification model for fluid identification and SVR regression model for reservoir parameter prediction were constructed. Finally, the two models were applied to the logging interpretation of the Chang 8 tight sandstone reservoir of the Yanchang Formation in the Huanxian area, Ordos Basin. The application results show that the fluid recognition accuracy of the SVM classification model is higher than that of the logging cross plot method and BP neural network method. The calculation accuracy of permeability and water saturation predicted by the SVR regression model is higher than that based on the experimental fitting model, which indicates that it is feasible to carry out logging interpretation and evaluation of the low resistivity contrast oil layer by the SVM method. The research results not only provide an important reference and basis for the review of old wells but also provide technical support for the exploration and development of new strata.