A New Method Forecasting Physical and Chemical Properties of the Shale Based on Quantum Neural Network

Yu Xue Sun; Yuan Long Xiang; Ze Hua Wang; Li Ming Zheng

doi:10.4028/www.scientific.net/AMM.488-489.685

Paper Titles

The Dimensional Analysis and Similar Theory of Model Tests for Explosion Resisting Capacity of Tunnels
p.666

The Symmetry in the Traditional Chinese Architecture
p.669

Simulation Analysis of K Node on UHV Transmission Tubular Tower
p.676

Study on the Vortex-Induced Vibration of a Long-Span Arch Bridge
p.681

A New Method Forecasting Physical and Chemical Properties of the Shale Based on Quantum Neural Network
p.685

Three-Dimensional Finite Element Analysis on the Bearing Capacity of Bucket Foundation with Different Ratios of Diameter to Height
p.689

Experimental Study on the Flexural Impact Properties of Fiber Reinforced Lightweight Aggregate Concrete
p.696

Freeze-Thaw Resistance of Concrete Modified by Rice Hull Ash and Gangue
p.700

Effect of Axial Compression Ratio and Concrete Strength on Seismic Performance of Concrete Filled Steel Tube Beam-Column Joints
p.704

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 488-489A New Method Forecasting Physical and Chemical...

A New Method Forecasting Physical and Chemical Properties of the Shale Based on Quantum Neural Network

Abstract:

Influence factors of sidewall stability contain mechanical factors and chemical factors. Among them, the chemical factor is the internal cause of the sidewall instability. Based on the collection of the influence factors of physical and chemical properties of the shale, we decided the main factors that influence the stability through the simple correlation analysis and applied a kind of quantum neural network based on the multilayer excitation function. We established the quantum neural network forecast model of shale physical and chemical properties that can effectively improve the network convergence speed and the accuracy of prediction. The quantum neural network prediction model analysis show that human factors interference of this method is small, and the system parameters needed less, wide application, the result is reliable, can effectively reflect the shale physical and chemical properties and fabric characteristics, to provide a reliable basis for preventing sidewall instability.

You might also be interested in these eBooks

Materials Science, Civil Engineering and Architecture Science, Mechanical Engineering and Manufacturing Technology

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 488-489)

Pages:

685-688

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.488-489.685

Citation:

Cite this paper

Online since:

January 2014

Authors:

Yu Xue Sun*, Yuan Long Xiang, Ze Hua Wang, Li Ming Zheng

Keywords:

Influence Factor, Prediction, Quantum Neural Network, Shale, Sidewall Instability

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Xu Tongtai, Cui Maorong, Wang Runlian. New technology of drilling engineering sidewall stability[M]. Beijing: Petroleum industry press, 1999, 3～17.

Google Scholar

[2] Sanjay Gupta . Quantum Neural Networks . Journal of Computer and System Sciences, 2001, 63: 355~383.

Google Scholar

[3] Davld C. woodland. Borehole Instability in the western Canadian overthrust belt. SPE Drilling Engineering, March 1990: 27~33.

DOI: 10.2118/17508-pa

Google Scholar

[4] Zhang Huisheng, Wu Wei. A kind of BP algorithm of adaptive momentum factor[J]. Journal of Dalian Maritime University, 2008, 11(4): 45~47.

Google Scholar

[5] Li Fei, Zheng Baoyu, Zhao Shengmei. Quantum neural network and application[J]. Journal of Electronics & Information Technology, 2008, 26(8): 1332~1339.

DOI: 10.1109/icosp.2002.1180022

Google Scholar

[6] Wei Haikun. Neural network structure design theory and method[M]. Beijing: National defence industry press, (2005).

Google Scholar