Considerations on the Selection of an Optimum Vertical Multiphase Pressure Drop Prediction Model for Oil Wells

2001 ◽  
Author(s):  
Gabor Takacs
Keyword(s):  
Pressure Drop ◽  
Prediction Model ◽  
Oil Wells ◽  
Selection Of

scholarly journals Expert solution for effects of input parameters on multiphase flow correlations

2021 ◽  
Vol 9 (2) ◽  
Author(s):  
Mohamed A. Abd El-Moniem ◽  
◽  
Ahmed H. El-Banbi ◽  
Keyword(s):  
Expert System ◽  
Pressure Drop ◽  
Oil And Gas ◽  
Gas Production ◽  
Oil Wells ◽  
Gas Wells ◽  
Oil And Gas Production ◽  
Input Parameters ◽  
Bottomhole Pressure ◽  
Selection Of

Oil and gas production represents an essential source of energy. Optimization of oil and gas production systems requires accurate calculation of pressure drop in tubing and flowlines. Many empirical correlations and mechanistic models exist to calculate pressure drop in tubing and flowlines. Previous work has shown that some correlations provide more accurate results under certain flow conditions, PVT data, and well configurations than others. However, the effects of errors in input data on the selection of which correlations to use have not been investigated. This paper studies different multiphase flow correlations to determine the effects of their input parameters on (1) the accuracy of calculated pressure drop and (2) the selection of best correlation. A database consisting of 33 oil wells and 32 gas wells was selected, and a commercial software was used to build different well models. A total of 715 well models were constructed and used to investigate the effects of errors in correlations inputs on both the calculated bottomhole pressure and the selection of best correlation(s). The methodology was based on perturbing the values of the selected input parameters and calculating the new predicted bottomhole flowing pressure. Then, the effects of error in input parameters on how the calculated bottomhole pressure was different from observed data were quantified. The effect of this error in input parameters was also checked against the algorithm that selects the best correlation(s). It was found that errors in input GOR have the greatest effects for oil wells, while gas specific gravity and the tubing roughness are the most effective parameters for gas wells. The results were integrated into a rule-based expert system. A new set of data, consisting of 220 cases from 10 new oil wells and 10 new gas wells, was used to validate the expert system. The expert system was found to predict the best correlation(s) with a success rate of 80%, and it also identifies the input parameters whose error would affect the value of calculated bottomhole pressure significantly. Finally, the rules of the expert system were programmed into a VBA-Code to ease its use.

scholarly journals Resampled dimensional reduction for feature representation in machine learning

2021 ◽  
Author(s):  
Herdiantri Sufriyana ◽  
Yu Wei Wu ◽  
Emily Chia-Yu Su
Keyword(s):  
Machine Learning ◽  
Parameter Estimation ◽  
Prediction Model ◽  
Sample Size ◽  
Dimensional Reduction ◽  
Latent Variables ◽  
Feature Representation ◽  
Estimated Parameters ◽  
Representation Technique ◽  
Selection Of

Abstract We aimed to provide a resampling protocol for dimensional reduction resulting a few latent variables. The applicability focuses on but not limited for developing a machine learning prediction model in order to improve the number of sample size in relative to the number of candidate predictors. By this feature representation technique, one can improve generalization by preventing latent variables to overfit data used to conduct the dimensional reduction. However, this technique may warrant more computational capacity and time to conduct the procedure. The key stages consisted of derivation of latent variables from multiple resampling subsets, parameter estimation of latent variables in population, and selection of latent variables transformed by the estimated parameters.

scholarly journals Comments on "Researcher bias: The use of machine learning in software defect prediction"

2015 ◽  
Author(s):  
Chakkrit Tantithamthavorn ◽  
Shane McIntosh ◽  
Ahmed E Hassan ◽  
Kenichi Matsumoto
Keyword(s):  
Prediction Model ◽  
Strong Association ◽  
Model Performance ◽  
Strong Relationship ◽  
Defect Prediction ◽  
Explanatory Variables ◽  
Software Defect ◽  
The Impact ◽  
The Relationship ◽  
Selection Of

Shepperd et al. (2014) find that the reported performance of a defect prediction model shares a strong relationship with the group of researchers who construct the models. In this paper, we perform an alternative investigation of Shepperd et al. (2014)’s data. We observe that (a) researcher group shares a strong association with the dataset and metric families that are used to build a model; (b) the strong association among the explanatory variables introduces a large amount of interference when interpreting the impact of the researcher group on model performance; and (c) after mitigating the interference, we find that the researcher group has a smaller impact than the metric family. These observations lead us to conclude that the relationship between the researcher group and the performance of a defect prediction model may have more to do with the tendency of researchers to reuse experimental components (e.g., datasets and metrics). We recommend that researchers experiment with a broader selection of datasets and metrics to combat potential bias in their results.

A pressure drop prediction model for hydrate slurry based on energy dissipation under turbulent flow condition

Fuel ◽  
2021 ◽  
pp. 122188
Author(s):  
Weiqi Fu ◽  
Jing Yu ◽  
Yang Xiao ◽  
Chenglai Wang ◽  
Bingxiang Huang ◽  
...  
Keyword(s):  
Energy Dissipation ◽  
Pressure Drop ◽  
Turbulent Flow ◽  
Prediction Model ◽  
Flow Condition

scholarly journals Study on selecting of prefabricated plant site basing on BP neural network

2018 ◽  
Vol 53 ◽  
pp. 03073
Author(s):  
Yao Gang ◽  
Yang Yang ◽  
Shen Xin ◽  
Li Jun
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
High Precision ◽  
Bp Neural Network ◽  
Raw Materials ◽  
Output Factor ◽  
Plant Site ◽  
Selection Of ◽  
Transportation Facilities

In this paper, the evaluation and prediction model of prefabricated plant site was established by BP neural network, which taking nine factors into consideration, such as location, topography, land scale, transportation facilities, availability of raw materials and labour. These nine factors were taken as input factors, and the normalized global value was taken as output factor. The normalized global value was used to evaluate the performance of prefabricated plant site. In addition, the model was verified to be accurate by analysing twelve prefabricated plant site samples. Therefore, it is obvious that the model is stable in operation with high precision, and can provide effective support in the selection of prefabricated plant site.

Comparison and Selection of Different Medium on the Effect of Improving Soil Deodorization

2012 ◽  
Vol 610-613 ◽  
pp. 1328-1332
Author(s):  
Zu Xin Xu ◽  
Jian Xiu Huang ◽  
Huai Zheng Li ◽  
Wei Bing Chen ◽  
Wei Gang Wang
Keyword(s):  
Blast Furnace ◽  
Pressure Drop ◽  
Blast Furnace Slag ◽  
Removal Rate ◽  
Packed Column ◽  
Combined System ◽  
Ammonia Gas ◽  
Odor Concentration ◽  
Furnace Slag ◽  
Selection Of

Based on the investigation of odor concentration of retention tank in combined system, it aim at the removal of mixed odor and pressure drop with blast furnace slag, pebble, sand as improved medium and soil as contrast through mixed odor of ammonia gas and hydrogen sulfide made in lab-scale. The results showed that the removal rate of H2S by different medium packed column becomes stable after 12 days, and 35 days for NH3. Pressure drop of each column meets with Equation Ergum and under the same condition the order is as follows: soil>sand>pebble>blast furnace slag. And the removal rate of each medium is: soil>sand>blast furnace slag. The soil is good for removal but its pressure drop is so high that it limits flow charge, thus its removal rate is the lowest. As a result, sand and pebble as the medium for soil deodorization considering pressure drop and the effect of deodorization were chosen. It turns out that the removal rate of NH3 is higher than 65% while H2S higher than 98%.

Sign in / Sign up

Export Citation Format

Share Document