Application of BP Neural Network Based on Petrophysical Big Data Mining

Based on the big data mining method of petrophysical data, this paper studies the method and application of BP neural network to establish nonlinear interpretation model in distributed cloud computing environment. The nonlinear mapping relationship between the relative objective logging response and actual formation component is established by extracting the data mining result model, which overcomes existing deficiencies of the conventional logging interpretation procedure based on the homogeneity theory, linear hypothesis and the use of statistical experience simplifying model and parameters. The results show that network prediction model has been improved and has superior reference value for solving practical problems of interpretation under complex geological conditions.

Download Full-text

Research on Closed-Loop Safety Production System of Hot Oil Pipeline Based on Big Data Mining

ASME 2019 Asia Pacific Pipeline Conference ◽

10.1115/appc2019-7609 ◽

2019 ◽

Author(s):

Yu Tao ◽

Li Chuanxian ◽

Liu Lijun ◽

Chen Hongjun ◽

Guo Peng ◽

...

Keyword(s):

Neural Network ◽

Data Mining ◽

Big Data ◽

Prediction Model ◽

Bp Neural Network ◽

Closed Loop ◽

Long Distance ◽

Oil Pipeline ◽

Big Data Mining ◽

Actual Production

Abstract The process of long-distance hot oil pipeline is complicated, and its safety and optimization are contradictory. In actual production and operation, the theoretical calculation model of oil temperature along the pipeline has some problems, such as large error and complex application. This research relies on actual production data and uses big data mining algorithms such as BP neural network, ARMA, seq2seq to establish oil temperature prediction model. The prediction result is less than 0.5 C, which solves the problem of accurate prediction of dynamic oil temperature during pipeline operation. Combined with pigging, the friction prediction model of standard pipeline section is established by BP neural network, and then the economic pigging period of 80 days is given; and after the friction database is established, the historical friction data are analyzed by using the Gauss formula, and 95% of the friction is set as the threshold data to effectively monitor the variation of the friction due to the long period of waxing in pipelines. The closed loop operation system of hot oil pipeline safety and optimization was formed to guide the daily process adjustment and production arrangement of pipeline with energy saving up to 92.4%. The prediction model and research results based on production big data have good adaptability and generalization, which lays a foundation for future intelligent control of pipelines.

Download Full-text

A Big Data Mining Approach of PSO-Based BP Neural Network for Financial Risk Management With IoT

IEEE Access ◽

10.1109/access.2019.2948949 ◽

2019 ◽

Vol 7 ◽

pp. 154035-154043 ◽

Cited By ~ 6

Author(s):

Hangjun Zhou ◽

Guang Sun ◽

Sha Fu ◽

Jing Liu ◽

Xingxing Zhou ◽

...

Keyword(s):

Neural Network ◽

Data Mining ◽

Risk Management ◽

Big Data ◽

Bp Neural Network ◽

Financial Risk ◽

Financial Risk Management ◽

Big Data Mining ◽

Data Mining Approach

Download Full-text

Research on the big data mining algorithm based on modified neural network and structure optimized genetic algorithm

2016 International Conference on Communication and Electronics Systems (ICCES) ◽

10.1109/cesys.2016.7889911 ◽

2016 ◽

Cited By ~ 1

Author(s):

Yi Liang ◽

Xiangyun Cai ◽

Zilun Xiong

Keyword(s):

Neural Network ◽

Data Mining ◽

Genetic Algorithm ◽

Big Data ◽

Data Mining Algorithm ◽

Big Data Mining ◽

Mining Algorithm

Download Full-text

Productivity estimation of cutter suction dredger operation through data mining and learning from real-time big data

Engineering Construction & Architectural Management ◽

10.1108/ecam-05-2020-0357 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Jiake Fu ◽

Huijing Tian ◽

Lingguang Song ◽

Mingchao Li ◽

Shuo Bai ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Data Mining ◽

Big Data ◽

Bp Neural Network ◽

Coefficient Of Determination ◽

Support Vector ◽

Content Type ◽

Optimal Coefficient ◽

Productivity Estimation

PurposeThis paper presents a new approach of productivity estimation of cutter suction dredger operation through data mining and learning from real-time big data.Design/methodology/approachThe paper used big data, data mining and machine learning techniques to extract features of cutter suction dredgers (CSD) for predicting its productivity. ElasticNet-SVR (Elastic Net-Support Vector Machine) method is used to filter the original monitoring data. Along with the actual working conditions of CSD, 15 features were selected. Then, a box plot was used to clean the corresponding data by filtering out outliers. Finally, four algorithms, namely SVR (Support Vector Regression), XGBoost (Extreme Gradient Boosting), LSTM (Long-Short Term Memory Network) and BP (Back Propagation) Neural Network, were used for modeling and testing.FindingsThe paper provided a comprehensive forecasting framework for productivity estimation including feature selection, data processing and model evaluation. The optimal coefficient of determination (R2) of four algorithms were all above 80.0%, indicating that the features selected were representative. Finally, the BP neural network model coupled with the SVR model was selected as the final model.Originality/valueMachine-learning algorithm incorporating domain expert judgments was used to select predictive features. The final optimal coefficient of determination (R2) of the coupled model of BP neural network and SVR is 87.6%, indicating that the method proposed in this paper is effective for CSD productivity estimation.

Download Full-text

Research on the Method of Warfare Simulation Data Analysis Based on BP Neural Network and RoughSet

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.765-767.498 ◽

2013 ◽

Vol 765-767 ◽

pp. 498-503

Author(s):

Jun Heng ◽

Yun Fei Tian ◽

Peng Yan

Keyword(s):

Neural Network ◽

Data Mining ◽

Rough Set ◽

Bp Neural Network ◽

Rough Set Theory ◽

Reference Value ◽

Simulation Data ◽

Bp Network ◽

The Neural Network ◽

Rule Set

Preliminary exploration on simulation data mining with BP network and rough set method is made in the paper. Data mining method based on rough set theory and BP neural network is put up. Firstly, we reduce the redundant attributes in the decision-making table with rough set method, and then the noise is filtered by BP neural network. Finally, rule set is generated by rough set from the reduction decision table. This method not only avoids the complexity of the rules extracted from training the neural network, but also improves the classification accuracy effectively. At last, the mining data by the experimental data of the troops marching warfare simulation system and the result with the actual reference value is obtained.

Download Full-text