Oil Saturation Log Prediction Using Neural Network in New Steamflood Area

2020 ◽  
Author(s):  
A. Syahputra
Keyword(s):  
Neural Network ◽  
Water Saturation ◽  
Prediction Method ◽  
Neural Model ◽  
Training Model ◽  
Acquisition Time ◽  
Oil Saturation ◽  
Full Field ◽  
Remaining Oil ◽  
Observation Wells

Surveillance is very important in managing a steamflood project. On the current surveillance plan, Temperature and steam ID logs are acquired on observation wells at least every year while CO log (oil saturation log or SO log) every 3 years. Based on those surveillance logs, a dynamic full field reservoir model is updated quarterly. Typically, a high depletion rate happens in a new steamflood area as a function of drainage activities and steamflood injection. Due to different acquisition time, there is a possibility of misalignment or information gaps between remaining oil maps (ie: net pay, average oil saturation or hydrocarbon pore thickness map) with steam chest map, for example a case of high remaining oil on high steam saturation interval. The methodology that is used to predict oil saturation log is neural network. In this neural network method, open hole observation wells logs (static reservoir log) such as vshale, porosity, water saturation effective, and pay non pay interval), dynamic reservoir logs as temperature, steam saturation, oil saturation, and acquisition time are used as input. A study case of a new steamflood area with 16 patterns of single reservoir target used 6 active observation wells and 15 complete logs sets (temperature, steam ID, and CO log), 19 incomplete logs sets (only temperature and steam ID) since 2014 to 2019. Those data were divided as follows ~80% of completed log set data for neural network training model and ~20% of completed log set data for testing the model. As the result of neural model testing, R2 is score 0.86 with RMS 5% oil saturation. In this testing step, oil saturation log prediction is compared to actual data. Only minor data that shows different oil saturation value and overall shape of oil saturation logs are match. This neural network model is then used for oil saturation log prediction in 19 incomplete log set. The oil saturation log prediction method can fill the gap of data to better describe the depletion process in a new steamflood area. This method also helps to align steam map and remaining oil to support reservoir management in a steamflood project.

Energy Consumption Forecasting Using United Grey System–Bayesian Regularization Neural Network Model

2012 ◽  
Vol 524-527 ◽  
pp. 3087-3092 ◽  
Author(s):  
Xiao Hui Hu ◽  
Lv Jun Zhan ◽  
Yun Xue ◽  
Gui Xi Liu ◽  
Zhe Fan
Keyword(s):  
Neural Network ◽  
Energy Consumption ◽  
Regularization Parameter ◽  
Prediction Method ◽  
Neural Model ◽  
Bayesian Regularization ◽  
Grey System ◽  
Bayesian Regularization Neural Network ◽  
Energy Consumption Prediction

The energy consumption of the enterprise is subject to various factors. To solve the problem, a new grey-neural model is proposed which effectively combines the grey system and Bayesian-regularization neural network and avoids the disadvantages of each other. The case study indicates that the prediction method is not only reasonable in theory but also owns good application value in the energy consumption prediction. Meanwhile, results also exhibit that G-BRNN model has the automated regularization parameter selection capability and may ensure the excellent adaptability and robustness.

scholarly journals Study on the relationship between the water cutting rate and the remaining oil saturation of the reservoir by using the index percolating saturation formula with variable coefficients

2020 ◽  
Vol 10 (8) ◽  
pp. 3649-3661
Author(s):  
Meiling Zhang ◽  
Jiayi Fan ◽  
Yongchao Zhang ◽  
Yinxin Liu
Keyword(s):  
Relative Permeability ◽  
Water Saturation ◽  
Variable Coefficients ◽  
Absolute Permeability ◽  
Oil Saturation ◽  
Rock Samples ◽  
Remaining Oil ◽  
Cutting Rate ◽  
Water Cutting ◽  
The Relationship

Abstract The water cutting rate is recorded dynamically during the production process of a well. If the remaining oil saturation of the reservoir can be deduced based on the water cutting rate, it will give guidance to improve the reservoir recovery and can save expensive drilling costs. In the oil–water two-phase seepage experiment on core samples, the oil and water relative permeability reflects the relationship between the water cutting rate and water saturation, that is, percolating saturation formula. The relative permeability test data of 17 rock samples from six seal coring wells in Daqing Changyuan were used to optimize and construct the coefficients of the index percolating saturation formula that vary with the pore structure parameters of reservoirs, to form an index percolating saturation formula with variable coefficients that is more consistent with the regional geological characteristics of the reservoir. Based on this, the formula of water saturation calculated by the water cutting rate is deduced. And the high-precision formula for calculating the irreducible water saturation and residual oil saturation by effective porosity, absolute permeability, and shale content is given. The derivative formula of water saturation on the water cutting rate was established, and the parameters of 17 rock samples were calculated. It was found that the variation velocity of water saturation of each sample with the water cutting rate presented a “U” shape, which was consistent with the actual characteristics that the variation velocity of the water saturation in the early, middle, and late stages of oilfield development first decreased, then stabilized, and finally increased rapidly. The research results were applied to the prediction of remaining oil saturation in the research area, and the water saturation about six producing wells was calculated by using their present water cutting rates, and the remaining oil distribution profile was predicted effectively. The analysis of four layers of two newly drilled infill wells and reasonable oil recovery suggestions were given to achieve good results.

scholarly journals Analysis of Sports Performance Prediction Model Based on GA-BP Neural Network Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Jinjuan Wang
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Performance Prediction ◽  
Bp Neural Network ◽  
Prediction Method ◽  
Training Model ◽  
Sports Performance ◽  
Advantages And Disadvantages ◽  
Network Algorithm ◽  
Neural Network Algorithm

There are many factors that affect athletes’ sports performance in sports competitions. The traditional sports performance prediction method is difficult to obtain more accurate sports performance prediction results and corresponding data analysis in a short time, which is not conducive for coaches to formulate targeted and scientific training sprint plans for athletes’ problems. Therefore, based on GA-BP neural network algorithm, this paper constructs a sports performance prediction model and carries out experiments and analysis. The experimental results show that GA-BP neural network algorithm has a faster convergence speed than BP neural network and can achieve the expected error accuracy in a shorter time, which overcomes the problems of the BP neural network. At the same time, different from the previous models, GA-BP neural network algorithm can get the athlete training model according to the relationship between quality training indicators and special sports training results, which can more intuitively show the advantages and disadvantages of athletes. In the final sports performance prediction results, GA-BP neural network prediction results have higher accuracy, better stability, better prediction effect, and higher application value than BP neural network.

scholarly journals Comprehensive correction method of airtight coring saturation based on core classification

2021 ◽  
Vol 25 (6 Part A) ◽  
pp. 4153-4160
Author(s):  
Junjie Dong ◽  
Rui Deng
Keyword(s):  
Water Saturation ◽  
Correction Method ◽  
Comprehensive Analysis ◽  
Production Well ◽  
Oil Saturation ◽  
The Core ◽  
Split Method ◽  
Remaining Oil ◽  
Oil Water ◽  
Core Classification

The indoor comprehensive analysis of core saturation of airtight coring wells is an important part of well logging interpretation. According to the saturation data, the geological reserves can be accurately calculated, and the remaining oil saturation and water-flooded zone in the later stage of the production well can be accurately evaluated. Due to the influence of many factors in the coring process and the experiment process, the sum of the core oil and water saturation is usually not equal to 100%. At present, conventional airtight coring correction method is generally to analyze the oil-water saturation, and then correct the data of the same factors that affect the results. This article combines two methods for saturation correction of XX oilfield in China. For cores with consistent missing factors, mathematical statistics are used to correct the saturation. When most of the rock pores have irreducible water and remaining oil, the phase percolation split method is used for the correction after the experimental analysis. By comparing with the logging interpretation results and the results of adjacent wells, the feasibility of the comprehensive correction method can be verified.

scholarly journals Rolling Bearing Fault Prediction Method Based on QPSO-BP Neural Network and Dempster–Shafer Evidence Theory

Energies ◽  
2020 ◽  
Vol 13 (5) ◽  
pp. 1094 ◽  
Author(s):  
Lanjun Wan ◽  
Hongyang Li ◽  
Yiwei Chen ◽  
Changyun Li
Keyword(s):  
Neural Network ◽  
Working Conditions ◽  
Bp Neural Network ◽  
Evidence Theory ◽  
Prediction Method ◽  
Rolling Bearing ◽  
Fault Prediction ◽  
Fault Classification ◽  
Bearing Fault ◽  
Hidden Layer

To effectively predict the rolling bearing fault under different working conditions, a rolling bearing fault prediction method based on quantum particle swarm optimization (QPSO) backpropagation (BP) neural network and Dempster–Shafer evidence theory is proposed. First, the original vibration signals of rolling bearing are decomposed by three-layer wavelet packet, and the eigenvectors of different states of rolling bearing are constructed as input data of BP neural network. Second, the optimal number of hidden-layer nodes of BP neural network is automatically found by the dichotomy method to improve the efficiency of selecting the number of hidden-layer nodes. Third, the initial weights and thresholds of BP neural network are optimized by QPSO algorithm, which can improve the convergence speed and classification accuracy of BP neural network. Finally, the fault classification results of multiple QPSO-BP neural networks are fused by Dempster–Shafer evidence theory, and the final rolling bearing fault prediction model is obtained. The experiments demonstrate that different types of rolling bearing fault can be effectively and efficiently predicted under various working conditions.

Financial market trend analysis based on autoregressive conditional heteroscedasticity model and BP neural network prediction

2021 ◽  
pp. 002072092098849
Author(s):  
Xinzhe Yin ◽  
Jinghua Li
Keyword(s):  
Neural Network ◽  
Trend Analysis ◽  
Financial Market ◽  
Prediction Method ◽  
Good Effect ◽  
Trend Prediction ◽  
Bp Network ◽  
Conditional Heteroscedasticity ◽  
Bp Model ◽  
Autoregressive Conditional Heteroscedasticity

Many experts and scholars at home and abroad have studied this topic in depth, laying a solid foundation for the research of financial market prediction. At present, the mainstream prediction method is to use neural network and autoregressive conditional heteroscedasticity to build models, which is a more scientific way, and also verified the feasibility of the way in many studies. In order to improve the accuracy of financial market trend prediction, this paper studies in detail the neural network system represented by BP and the autoregressive conditional heterogeneous variance model represented by GARCH. Analyze its structure and algorithm, combine the advantages of both, create a GARCH-BP model, and transform its combination structure and optimize the algorithm according to the uniqueness of the financial market, so as to meet the market as much as possible Characteristics. The novelty of this paper is the construction of the autoregressive conditional heteroscedasticity model, which lays the foundation for the prediction of financial market trends through the construction of the model. However, there are some shortcomings in this article. The overall overview of the financial market is not very clear, and the prediction of the BP network is not so comprehensive. Finally, through the actual data statistics of market transactions, the effectiveness of the GARCH-BP model was tested, analyzed and researched. The final results show that model has a good effect on the prediction and trend analysis of market, and its accuracy and availability greatly improved compared with the previous conventional approach, which is worth further study and extensive research It is believed that the financial market prediction model will become one of the mainstream tools in the industry after its later improvement.

Full-field X-ray diffraction microscopy using polymeric compound refractive lenses

2014 ◽  
Vol 47 (6) ◽  
pp. 1882-1888 ◽  
Author(s):  
J. Hilhorst ◽  
F. Marschall ◽  
T. N. Tran Thi ◽  
A. Last ◽  
T. U. Schülli
Keyword(s):  
Imaging Techniques ◽  
Light And Electron Microscopy ◽  
Added Value ◽  
Acquisition Time ◽  
Imaging Method ◽  
X Ray Diffraction ◽  
Polymeric Compound ◽  
Full Field ◽  
X Ray ◽  
Diffraction Imaging

Diffraction imaging is the science of imaging samples under diffraction conditions. Diffraction imaging techniques are well established in visible light and electron microscopy, and have also been widely employed in X-ray science in the form of X-ray topography. Over the past two decades, interest in X-ray diffraction imaging has taken flight and resulted in a wide variety of methods. This article discusses a new full-field imaging method, which uses polymer compound refractive lenses as a microscope objective to capture a diffracted X-ray beam coming from a large illuminated area on a sample. This produces an image of the diffracting parts of the sample on a camera. It is shown that this technique has added value in the field, owing to its high imaging speed, while being competitive in resolution and level of detail of obtained information. Using a model sample, it is shown that lattice tilts and strain in single crystals can be resolved simultaneously down to 10−3° and Δa/a= 10−5, respectively, with submicrometre resolution over an area of 100 × 100 µm and a total image acquisition time of less than 60 s.

Sign in / Sign up

Export Citation Format

Share Document