Research on reconstruction of transverse wave time difference curve based on neural network

Journals

Title：
Research on reconstruction of transverse wave time difference curve based on neural network
Author：
Jicheng Yan
Author Affiliation：
Research Institute of Exploration and Development of Daqing Oilfield Company Ltd, Daqing, China
Received：Oct.22, 2022
Accepted：Nov.19, 2022
Published：Dec.6, 2022

Abstract

Yilong-Pingchang Region is a transfer block of Daqing Oilfield, and is an important field for increasing reserve and production, and with development of shale in Lianggaoshan, Daanzhai and other strata, it is a key target for unconventional exploration and development. “Seven-character” evaluation and calculation of rock characteristic parameters are essential links in evaluation of shale oil and gas reservoir strata. Data on transverse wave time difference plays a very important significance in evaluation of unconventional reservoir strata, however, since the well-logging cost using array acoustic wave is relatively high, most of the old wells in the research area failed to have transverse wave time difference curve logging, thus causing a series of troubles for “seven-characteristic” evaluation, re-examination of old wells and fracturing transformation. In this paper, K.Mod module of Techlog software was used, to make optimal selection of the well-logging parameters sensitive to transverse wave time difference by extracting existing data on transverse wave time difference, and construct calculation method of transverse wave time difference based on neural network method, which has a relatively good effect upon verification, and plays a very important significance to evaluation of reservoir strata in the research area.

Keywords

Yilong-Pingchang, array acoustic wave, neural network, transverse wave time difference, curve reconstruction.

References

[1] Zhang Yabin, Qu Yibin, Chen Zhongyun. Application of Neural-network Technology in Reconstructing Logging Curves [J]. Journal of Oil and Gas Technology, 2011, 33(3): 89-94.

[2] Wang Jun, Cao Junxing, You Jiachun. Reconstruction of logging traces based on GRU neural network [J]. Oil Geophysical Prospecting, 2020, 55(3): 510-520.

[3] Yang Zhili, Zhou Lu, Peng Wenli, Zheng Jinyun. Application of BP neural network technology in acoustic wave well-logging curves [J]. Journal of Southwest Petroleum University (Science & Technology Edition), 2008,30(1): 63-66.

[4] Wu Zaixin, Wang Kai, Hu Chibing, Lv Hongbo. Neural Network Approach to Freeform Curve Reconstruction [J]. Science Technology and Engineering, 2006, 18(6): 2900-2902.

[5] Zhu Chao, Gao Xianzhi, Yang Dexiang, Cui Junfeng. Application of Acoustic Wave Curve Reconstruction in Prediction of Volcanic Rock Reservoir [J]. Journal of Oil and Gas Technology, 2010, 32(3): 258-262.

[6] Li Jing, Luan Shuang, You Minghui. Introduction to Principle of Artificial Neural Network [J]. Modern Education Science, 2010, 32(3): 258-262.

[7] Lin Jinglong, Nie Jing, Yu Chunsheng. Micropore Structure Type Prediction of Reservoirs Based on BP Neural Network [J]. World Well Logging Technology, 2009, 171(3): 33-36.