Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
operation
Join our industry experts to discover how you can deliver safer, more consistent, and higher-performing operations by connecting the right experts to the right job, going beyond remote operations. Learn how Schlumberger's Performance Live digitally connected service can reduce HSE exposure, service delivery incidents, and CO2e emissions while measurably improving your field operations efficiency.
In this SPE Tech Talk, we explore the impact of combining data analytics, automation, sensors, and AI on drilling operations and efficiency. In this SPE Tech Talk with SLB, we discuss RheoProfiler, semi-automated equipment that provides drilling fluid property measurements designed to increase the efficiency of the fluid engineer. In this SPE Tech Talk, we discuss ongoing concerns with measuring and controlling injection, and production rates. SLB joins this SPE Tech Talk to discuss what drilling automation and advisory are and the options available for operators to enable drilling automation for any rig. Don't miss this SPE Tech Talk with SLB and Rockwell Automation as they discuss the latest developments in technology which enable remote operations an Don't miss this SPE Tech Talk with SLB and Rockwell Automation as they discuss the latest developments in technology which enable remote operations an SLB and Microsoft have co-developed a secure, open, and fully managed cloud-based data platform solution.
Join us for this webinar, where we take a deeper look at the practical aspects of implementing a digital twin, review real-life examples, and discuss the challenges and benefits involved. A digital twin provides a virtual representation of a physical object using data from the physical object to perform various what-if analyses in real-time, even before the scenarios have happened. In the oil and gas industry, this translates to enhanced safety, predictive scenario modeling for complex operations, better learning and knowledge retention, improved productivity, and overall enhanced operational efficiency. Digital twin technology provides oil and gas companies a powerful platform to assimilate and analyze vast amounts of production data. Digital twins can be used for predictive maintenance operations, smart HSE, optimizing drilling plans, simulation of production imbalances or equipment reliability issues, and rapid scenario modeling for global economic conditions--all of which can greatly improve efficiencies and reduce carbon footprints while increasing ROI.
- Facilities Design, Construction and Operation (1.00)
- Data Science & Engineering Analytics > Information Management and Systems (1.00)
- Health, Safety, Environment & Sustainability > Sustainability/Social Responsibility > Sustainable development (0.64)
- Health, Safety, Environment & Sustainability > Environment > Climate change (0.64)
To start the process of digital transformation in the oil production operations carried out in the Ecuadorian Oriente Basin, the methodology proposed was based on "MIT Sloan School of Management" and established for all the processes of innovation and product creation, called RWW, "Real, Win and Worth". Real case studies in Ecuador will be discussed including not only production engineering analysis but also production operations in the field with a major focus on asset surveillance. Both activities require time-consuming tasks such as field trips and well-by-well analysis, showing the transformation in the way we operate leveraging the use of data, promoting remote operations, and automating the workflows used within the production engineering department. The starting point of this implementation was the well surveillance workflow, carried out at the field level because there was no mature SCADA system. Thus, the Edge was implemented with capabilities based on Internet of Things (IoT) technology to connect the different elements of the production chain. Currently, more than 400 pieces of equipment have been connected to a unified platform, including electro-submersible pumping equipment (ESP), wells with Beam Pumping (BM), injector wells, injection pumps, high-pressure injection equipment, multiphase flow meters and others, which allowed to the mature field to integrate data, perform real-time analysis and remotely control any equipment that is connected.
- Information Technology > Sensing and Signal Processing (0.97)
- Information Technology > Communications > Networks > Sensor Networks (0.60)
- Information Technology > Architecture > Real Time Systems (0.60)
- Information Technology > Communications > Web (0.50)
Several methods and techniques exist for avoiding gas in ESPs, including inverted shrouds, passive separators, mechanical gas separators, and tandem gas separators. Most share the limitations of limited flow capabilities and reduced performance at higher total flow rates. The many variables associated with complex two-phase flow behavior, internal and external pressure variations, separation methods, velocity and viscosity of fluids, effect of the pump bolted above, inherent erosion issues, and single vs. tandem designs add to the challenge of basic mechanical gas-separator operation. In 2016, a program was initiated that featured investment in both experienced personnel and advanced testing technology to unravel the aforementioned challenges and improve understanding of the operation of downhole mechanical gas separation.
All are playful nicknames for the oil and gas icon known as a pumpjack. To the uninformed, the pumpjack is a thing-a-ma-jig that has something to do with oil, probably "fracking" because that's what drilling rigs do, right? But as an industry-educated and well-informed reader of JPT, you know this is inaccurate. By whatever name you call it, you know that the pumpjack is the visible manifestation of an invisible physics equation, a mechanism buried deep underground that lifts reservoir fluids to the surface. You also know it is one type of artificial lift available in a stable of systems with equally curious and technical names like progressive cavity, plunger, jet, gas lift, and electrical submersible pump (ESP).
- Oceania > Australia > Western Australia > North West Shelf > Carnarvon Basin > Dampier Basin > WA-209-P > Stag Field (0.99)
- Oceania > Australia > Western Australia > North West Shelf > Carnarvon Basin > Dampier Basin > WA-15-L > Stag Field (0.99)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- (26 more...)
- Reservoir Description and Dynamics > Unconventional and Complex Reservoirs > Shale oil (0.70)
- Reservoir Description and Dynamics > Unconventional and Complex Reservoirs > Shale gas (0.70)
- Health, Safety, Environment & Sustainability > Sustainability/Social Responsibility > Sustainable development (0.69)
- (5 more...)
In the past 25 years, the artificial lift industry has seen incredible changes, making hydrocarbon production smarter and more efficient. This conversation showcases the technological progress such as materials, digital tools, and automation and the strategic leadership that has guided the industry to new heights. Join us as we dive into the world of artificial lift and discover the innovation and expertise shaping the future of energy. Stephenson: Numerous individuals impacted my early career, the most noteworthy being Herald Winkler, who was in the first class of SPE's Legends of Artificial Lift awarded in 2014. I traveled to my first ATCE in New Orleans as a first-year petroleum engineering student. I distinctly remember walking the exhibit floor and seeing this little guy get mobbed by people asking him questions. I asked one of my fellow students, 'Who is that guy? Tom Cruise?' I then learned that Wink was one of the pioneers of gas-lift technology and wrote the first definitive book on the subject. At that moment, I realized that artificial lift might offer a viable career path for me. Eventually, I got to know him personally, first as a student and then as an artificial lift professional. One of the most impactful conversations I had with him was one in which he told me, 'I am not a gas-lift expert.
- North America > United States > Texas (0.94)
- North America > United States > Louisiana > Orleans Parish > New Orleans (0.24)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (24 more...)
Filling borehole image gaps with a partial convolution neural network
Jiang, Lei (University of Science and Technology of China, University of Science and Technology of China) | Si, Xu (University of Science and Technology of China, University of Science and Technology of China) | Wu, Xinming (University of Science and Technology of China, University of Science and Technology of China)
ABSTRACT Borehole images are measured by logging tools in a well, providing a microresistivity map of the rock properties surrounding the borehole. These images contain valuable information related to changes in mineralogy, porosity, and fluid content, making them essential for petrophysical analysis. However, due to the special design of borehole imaging tools, vertical strips of gaps occur in borehole images. We develop an effective approach to fill these gaps using a convolutional neural network with partial convolution layers. To overcome the challenge of missing training labels, we introduce a self-supervised learning strategy. Specifically, we replicate the gaps found in borehole images by randomly creating vertical blank strips that mask out certain known areas in the original images. We then use the original images as label data to train the network to recover the known areas masked out by the defined gaps. To ensure that the missing data do not impact the training process, we incorporate partial convolutions that exclude the null-data areas from convolutional computations during forward and backward propagation of updating the network parameters. Our network, trained in this way, can then be used to reasonably fill the gaps originally appearing in the borehole images and obtain full images without any noticeable artifacts. Through the analysis of multiple real examples, we determine the effectiveness of our method by comparing it with three alternative approaches. Our method outperforms the others significantly, as demonstrated by various quantitative evaluation metrics. The filled full-bore images obtained through our approach enable enhanced texture analysis and automated feature recognition.
- Phanerozoic > Cenozoic > Neogene > Miocene (0.47)
- Phanerozoic > Cenozoic > Neogene > Pliocene (0.47)
- Geology > Geological Subdiscipline (0.86)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock > Mudrock (0.69)
- Geophysics > Seismic Surveying > Borehole Seismic Surveying (1.00)
- Geophysics > Borehole Geophysics (1.00)
- North America > United States > Wyoming > Uinta Basin (0.99)
- North America > United States > Utah > Uintah Basin > Natural Buttes Field > Wasatch Formation (0.99)
- North America > United States > Utah > Uinta Basin (0.99)
- North America > United States > Colorado > Uinta Basin (0.99)
Can deep learning compensate for sparse shots in the imaging domain? A potential alternative for reducing the acquisition cost of seismic data
Dong, Xintong (Jilin University) | Lu, Shaoping (Sun Yat-Sen University, Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Sun Yat-Sen University) | Lin, Jun (Jilin University) | Zhang, Shukui (Sun Yat-Sen University, Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Sun Yat-Sen University) | Ren, Kai (Sun Yat-Sen University, Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Sun Yat-Sen University) | Cheng, Ming (Jilin University)
ABSTRACT Dense shots can improve the fold of subsurface imaging points, which is essential for the resolution of imaging results. However, dense shots significantly increase the cost of data acquisition, which is one of the major bottlenecks faced by seismic exploration. To address this issue, we speculate whether it is possible to construct an effective method to optimize the image made by stacking sparse shots and then generate an imaging result similar to the image made by stacking dense shots. In other words, we explore the possibility of using an optimization method to replace the dense shots in migration imaging, which would likely reduce the acquisition cost of seismic data. Deep learning can establish a nonlinear and complex mapping relationship by using data-driven strategies. Inspired by this, we use the convolutional neural network to establish a novel mapping relationship from the sparse-shot image to the dense-shot image by constructing a suitable training data set and designing a self-guided attention network architecture. We refer to this mapping relationship as shot compensation. We use the 2D Sigsbee2b model and the 3D SEG advanced modeling model to demonstrate the potential application of shot compensation in reducing the acquisition cost of seismic data. Moreover, a real 2D marine seismic data set is used to evaluate the effectiveness of shot compensation. Experimental results on synthetic and real data indicate that this shot compensation method can improve the quality of sparse-shot images and that the improved imaging results are similar to their corresponding dense-shot images.
- Asia > China (0.46)
- North America > United States > Illinois > Madison County (0.24)
MT2DInv-Unet: A 2D magnetotelluric inversion method based on deep-learning technology
Pan, Kejia (Shenzhen Research Institute of Central South University, Central South University) | Ling, Weiwei (Central South University, Jiangxi College of Applied Technology) | Zhang, Jiajing (Jiangxi College of Applied Technology, Ministry of Natural Resources) | Zhong, Xin (Jiangxi College of Applied Technology, Ministry of Natural Resources) | Ren, Zhengyong (Central South University) | Hu, Shuanggui (China University of Mining and Technology) | He, Dongdong (The Chinese University of Hong Kong) | Tang, Jingtian (Central South University)
ABSTRACT Traditional gradient-based inversion methods usually suffer from the problems of falling into local minima and relying heavily on initial guesses. Deep-learning methods have received increasing attention due to their excellent nonlinear fitting ability. However, given the recent application of deep-learning methods in the field of magnetotelluric (MT) inversion, there are currently challenges associated with achieving high inversion resolution and extracting sufficient features. We develop a neural network model (called MT2DInv-Unet) based on the deformable convolution for 2D MT inversion to approximate the nonlinear mapping from the MT response data to the resistivity model. The deformable convolution is achieved by adding an offset to each sample point of the conventional convolution operation, which extracts hidden relationships and allows the flexible adjustment of the size and shape of the feature region. Meanwhile, we design the network structure with multiscale residual blocks, which effectively extract the multiscale features of the MT response data. This design not only enhances the network performance but also alleviates issues such as vanishing gradients and network degradation. The results of synthetic models indicate that our network inversion method has stable convergence, good robustness, and generalization performance, and it performs better than the fully convolutional neural network and U-Net network. Finally, the inversion results of field data show that MT2DInv-Unet can effectively obtain a reliable underground resistivity structure and has a good application prospect in MT inversion.
- Research Report > New Finding (0.93)
- Research Report > Experimental Study (0.68)