Numerical model and program development of horizontal directional drilling for non-excavation technology

Wan, Jifang; Jiang, Shan; Yan, Xiangwu; Li, Jingcui; Li, Guotao

doi:10.1007/s12665-021-09842-w

Cited by 2 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This technology is characterized by high construction efficiency (daily drilling depth: about 15-30 m) and low environmental impact. In addition, it is free from topographic influence, thus the drilling construction can be arranged directly along the tunnel axis [1][2][3]. This technology, combined with integrated logs and the images and videos of the cores and panoramic views of boreholes, allows for acquiring most of the geological information required for conventional adit explorations, precisely investigating the lithological changes of surrounding rocks, the density of joint fissures, and the distribution of fault fracture zone, and accurately classifying tunnels' surrounding rocks [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Borehole TV Imaging Technology for Horizontal Directional Drilling Based on an Optimization Algorithm for Structural Planes

Yang,

Cai,

Wang

et al. 2023

Advances in Civil Engineering

View full text Add to dashboard Cite

The horizontal directional drilling technology combined with the borehole TV imaging technology can be used to obtain most of the geological information in conventional adit exploration. This combination has little impact on the environment and is free from topographic constraints, thus contributing to green exploration. However, conventional algorithms for structural planes fail to accurately extract information on the attitudes of incomplete structural planes in boreholes of any azimuth. Moreover, existing borehole TV devices are mostly cable-based and, thus, difficult to put in place in horizontal drilling. They are prone to get stuck in the collapse section of boreholes, thus damaging the devices. Given these challenges, this study develops an optimization algorithm for structural planes: (1) first, information on multiple points in the 2D unfolded view is fitted using a sinusoidal function curve, three arbitrary points are constructed using the fitted curve, and the normal vector of the plane determined by the three points is calculated; (2) the normal vector in the geodetic coordinate system is obtained after two rotations of the spatial coordinate system based on the theory of transformation of Cartesian coordinate system; (3) finally, the dip angle and dip direction of a structural plane are calculated using the normal vector in the geodetic coordinate system. By making the best use of the information on multiple points in the 2D unfolded view, the optimization algorithm can overcome the defect that is difficult for conventional two-point methods to locate the highest and lowest points of discontinuous structural planes. Therefore, the optimization algorithm applies to calculating the attitudes of structural planes in boreholes of any azimuth. Based on this optimization algorithm, this study successfully develops a cable-free, storage-based TV device for boreholes of any azimuth. This device was employed for laboratory experiments on 20 complete structural planes and 32 incomplete structural planes. As indicated by the experiment results, the optimization algorithm proposed in this study is applicable to many types of structural planes, with a dip direction error of less than 10° and a dip angle error of less than 5°, thus meeting the production requirements.

show abstract

Section: Introductionmentioning

confidence: 99%

Borehole TV Imaging Technology for Horizontal Directional Drilling Based on an Optimization Algorithm for Structural Planes

Yang,

Cai,

Wang

et al. 2023

Advances in Civil Engineering

View full text Add to dashboard Cite

show abstract

Production Forecasting Based on Attribute-Augmented Spatiotemporal Graph Convolutional Network for a Typical Carbonate Reservoir in the Middle East

Gao

Wei

Zhao³

et al. 2022

Energies

View full text Add to dashboard Cite

Production forecasting plays an important role in development plans during the entire period of petroleum exploration and development. Artificial intelligence has been extensively investigated in recent years because of its capacity to extensively analyze and interpret complex data. With the emergence of spatiotemporal models that can integrate graph convolutional networks (GCN) and recurrent neural networks (RNN), it is now possible to achieve multi-well production prediction by considering the impact of interactions between producers and historical production data simultaneously. Moreover, an accurate prediction not only depends on historical production data but also on the influence of neighboring injectors’ historical gas injection rate (GIR). Therefore, based on the assumption that introducing GIR can enhance prediction accuracy, this paper proposes a deep learning-based hybrid production forecasting model that is aimed at considering both the spatiotemporal characteristics of producers and the GIR of neighboring injectors. Specifically, we integrated spatiotemporal characteristics and GIR into an attribute-augmented spatiotemporal graph convolutional network (AST-GCN) and gated recurrent units (GRU) neural network to extract intricate temporal correlations from historical data. The method proposed in this paper has been successfully applied in a well pattern (including five producers and seven gas injectors) in a low-permeability carbonate reservoir in the Middle East. In single well production forecasting, the error of AST-GCN is 63.2%, 37.3%, and 16.1% lower in MedAE, MAE, and RMSE compared with GRU and 62.9%, 44.6%, and 28.9% lower compared with RNS. Similarly, the accuracy of AST-GCN is 15.9% and 35.8% higher than GRU and RNS in single well prediction. In well-pattern production forecasting, the error of AST-GCN is 41.2%, 64.2%, and 75.2% lower in RMSE, MAE, and MedAE compared with RNS, while the accuracy of AST-GCN is 29.3% higher. After different degrees of Gaussian noise are added to the actual data, the average change in AST-GCN is 3.3%, 0.4%, and 1.2% in MedAE, MAE, and RMSE, which indicates the robustness of the proposed model. The results show that the proposed model can consider the production data, gas injection data, and spatial correlation at the same time, which performs well in oil production forecasts.

show abstract

Numerical model and program development of horizontal directional drilling for non-excavation technology

Cited by 2 publications

References 19 publications

Borehole TV Imaging Technology for Horizontal Directional Drilling Based on an Optimization Algorithm for Structural Planes

Borehole TV Imaging Technology for Horizontal Directional Drilling Based on an Optimization Algorithm for Structural Planes

Production Forecasting Based on Attribute-Augmented Spatiotemporal Graph Convolutional Network for a Typical Carbonate Reservoir in the Middle East

Contact Info

Product

Resources

About