An Optimal Design Algorithm for Proppant Placement in Slickwater Fracturing

2021 ◽  
Author(s):  
HaiYang Wang ◽  
Desheng Zhou ◽  
Jinze Xu ◽  
Shun Liu ◽  
Erhu Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Optimal Design ◽  
Prediction Model ◽  
Influencing Factors ◽  
Bp Neural Network ◽  
Unconventional Reservoirs ◽  
Hydraulic Fractures ◽  
Oil Well ◽  
Design Algorithm ◽  
Slickwater Fracturing

Abstract Slickwater fracturing technology is one of the significant stimulation measures for the development of unconventional reservoirs. An effective proppant placement in hydraulic fractures is the key to increase the oil production of unconventional reservoirs. However, previous studies on optimizing proppant placement are mainly focused on CFD numerical simulation and related laboratory experiments, and an optimization design method that comprehensively consider multiple influencing factors has not been established. The objective of this study is to establish an optimal design algorithm for proppant placement based on the construction characteristics of slickwater fracturing combined with Back Propagation (BP) neural network. In this paper, a proppant placement simulation experimental device was built to analyze proppant placement form data. We established a BP neural network model that considers multiple influencing factors and used the proppant placement form data to train and calibrate the model, which the proppant placement form prediction model is finally obtained. Using the proppant placement form prediction model, we designed an algorithm that can quickly select the three groups of construction schemes with the best proppant-filling ratio based on the massive construction schemes. The results indicate that the prediction results of the algorithm for proppant placement form are consistent with the CFD simulation results and experimental results, and the numerical error of the balanced height and the distance between the front edge of the proppant sandbank and the fracture entrance is within 5%. After using this algorithm to optimize the design of the fracturing construction scheme for the C8 oil well in Changqing Oilfield, the stimulation performance of the C8 oil well after fracturing is 2.7 times that of the adjacent well. The optimal design algorithm for proppant placement established in this paper is an effective, accurate, and intelligent optimization algorithm. This algorithm will provide a novel method for hydraulic fracturing construction design in oilfields.

Prediction for Percentage of Vehicle Entering Expressway Rest Area Based on BP Neural Network

2012 ◽  
Vol 178-181 ◽  
pp. 1956-1960
Author(s):  
Xiao Yan Shen ◽  
Hao Xue Liu ◽  
Jia Liu
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Influencing Factors ◽  
High Precision ◽  
Bp Neural Network ◽  
High Speed ◽  
High Speed Railway ◽  
Neural Network Prediction ◽  
Network Prediction ◽  
Influence Degree

In order to scientifically decide the percentage of vehicle entering expressway rest area, based on analyzing the influencing factors relating to the percent of mainline traffic stopping, a BP neural network prediction model for it was put forward. Finally, The Xinzheng Rest Area (XRA) was taken as an example for verifying the feasibility of the prediction model and determining the influence degree of the Shijiazhuang-Wuhan high-speed railway on the percentage of mainline vehicles entering XRA. The result shows that the model had a high precision and reliability.

Prediction Model of Passenger Waiting Time in High-Speed Rail Hub Based on Bp Neural Network

2013 ◽  
Vol 321-324 ◽  
pp. 1903-1906 ◽  
Author(s):  
Yu Long Pei ◽  
Kan Zhou ◽  
Ting Peng
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Influencing Factors ◽  
Waiting Time ◽  
Bp Neural Network ◽  
High Speed ◽  
Influencing Factor ◽  
Educational Background ◽  
High Speed Rail ◽  
Trip Distance

In order to explore the characteristics of passenger waiting time in high-speed rail hub, this paper analyzed the influencing factors of passenger waiting time, based on the survey of passenger waiting time in high-speed rail hub. And the main influencing factors were screened out using variance analysis. Then the prediction model of passenger waiting time based on BP neural network was established, the parameters of the model were calibrated and the validity was verified. The results show that, travel time in urban area, trip distance, familiarity toward the hub, educational background of passengers, and the type of transportation is the main influencing factor of passenger waiting time in high-speed rail hub, and the average relative error is only 9.2% using the proposed prediction model of passenger waiting time based on BP neural network.

scholarly journals Research on Prediction Model of Hotels’ Development Scale Based on BP Artificial Neural Network Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Nan Zhao ◽  
Sang-Bing Tsai
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Prediction Model ◽  
Influencing Factors ◽  
Bp Neural Network ◽  
Tourism Development ◽  
Development Economic ◽  
Bp Artificial Neural Network ◽  
Relationship Analysis ◽  
Artificial Neural

Due to the lack of macro and systematic data, the target cost of high-star hotel project cannot meet the characteristics and needs of the hotel project itself. Therefore, the establishment of star hotel development scale prediction is urgent. In the scale development strategy, based on the previous studies, combined with the development characteristics of regional high-star hotels in a city, this paper constructs the index system of influencing factors of the development scale of high-star hotels and extracts the main influencing factors of hotel development scale by principal component analysis and partial relationship analysis, which are mainly urban development, economic development, tourism development, tourism development exhibition industry development, business development, and transportation development. The BP artificial neural network prediction method is used to establish a prediction model for the development scale of high-star hotels, by adopting the above key extraction factors as input of BP neural network. Through the input and output of the scale influence index data, the development scale of star hotels is accurately predicted. The simulation results verify the effectiveness and reliability of the star hotel development scale prediction strategy based on BP neural network, in terms of accuracy and model superiority.

Research on Stamping Spring-Back Prediction for Car Body Panel Based on BP Neural Network

2010 ◽  
Vol 97-101 ◽  
pp. 250-254 ◽  
Author(s):  
Xin Jian Zhou
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Bp Neural Network ◽  
Front Panel ◽  
Spring Back ◽  
Test Analysis ◽  
Car Body ◽  
Neural Network Prediction ◽  
Mould Design ◽  
Bp Neural Network Model

On the basis of orthogonal test analysis of variance, BP neural network is used to forecast quantitatively the stamping spring-back of front panel of a car body, namely the engine hood, under the conditions of different stamping parameters. Firstly, BP neural network prediction model is established and sample training is done in Matlab. Then, the spring-back prediction using BP neural network and the result of spring-back simulation using Dynaform is compared to verify the precision and stability of the prediction model. Lastly, modification is made to the BP neural network according to practical stamping parameters and an efficient BP neural network model is established. Using this model, stamping spring-back prediction for the front panel of a car body is made. The spring-back prediction could then be used for spring-back compensation in the mould design of the front panel.

Prediction of Sand Thickness Using Seismic Attributes Based on BP-Neural Network

2012 ◽  
Vol 524-527 ◽  
pp. 180-183
Author(s):  
Feng Gao
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Bp Neural Network ◽  
Seismic Attributes ◽  
Bp Network ◽  
Sand Body ◽  
Precise Prediction ◽  
Energy Maximum ◽  
Bp Model ◽  
Rms Amplitude

Total energy, maximum peak amplitude and RMS amplitude are sensitive to sand body, and they are non-linear relations with sand thickness. In this study, a three-layer BP neural network is employed to build the prediction model. Nine samples were analyzed by three-layer BP network. The relationships were produced by BP network between sand thickness and the three seismic attributes. The precise prediction results indicate that the three-layer BP network based modeling is a practically very useful tool in prediction sand thickness. The BP model provided better accuracy in prediction than other methods.

Sign in / Sign up

Export Citation Format

Share Document