Foreign object intrusion is a great threat to high-speed railway safety operations. Accurate foreign object intrusion detection is particularly important. As a result of the lack of intruding foreign object samples during the operational period, artificially generated ones will greatly benefit the development of the detection methods. In this paper, we propose a novel method to generate railway intruding object images based on an improved conditional deep convolutional generative adversarial network (C-DCGAN). It consists of a generator and multi-scale discriminators. Loss function is also improved so as to generate samples with a high quality and authenticity. The generator is extracted in order to generate foreign object images from input semantic labels. We synthesize the generated objects to the railway scene. To make the generated objects more similar to real objects, on scale in different positions of a railway scene, a scale estimation algorithm based on the gauge constant is proposed. The experimental results on the railway intruding object dataset show that the proposed C-DCGAN model outperforms several state-of-the-art methods and achieves a higher quality (the pixel-wise accuracy, mean intersection-over-union (mIoU), and mean average precision (mAP) are 80.46%, 0.65, and 0.69, respectively) and diversity (the Fréchet-Inception Distance (FID) score is 26.87) of generated samples. The mIoU of the real-generated pedestrian pairs reaches 0.85, and indicates a higher scale of accuracy for the generated intruding objects in the railway scene.
The Sichuan Basin is the major target for shale gas exploration in China because of its rich gas stored in unexploited black shale with multiple bed series. National Shale Gas Exploitation Areas have been established since 2012, the proved geological shale gas reserves is 9210×108 m3 and 90.25×108m3 annually output has been achieved by the end of 2017. The operating Sichuan Basin shale gas area located in the major compression tectonic experienced multiple geological structure movements in Earth history, showing characteristics of high steep structure with faults greatly developed. It's proven that the key factors in exploiting these targets are well acknowledged by the efforts to land and expose the lateral within the sweet zone. To successfully place lateral in reservoirs from geological perspective must overcome challenges of high uncertainty structure identification to make soft landing and maximize horizontal exposure in the sweet zone. While it comes to shale gas reservoir, to pave the way for fracture operation and achieve good well completion, the drilling requires a relative gentle well path, keeping well path inclination with limitation, which requires to make azimuth turning to achieve this. To ensure the optimum placement of the well in sweet zone, the integration of rotary steerable drilling system (RSS) with borehole images measurements in real-time have been implemented with the employment of well placement technique. The borehole image portrays structural profile while drilling whilst the rotary steerable drilling system provides accurate trajectory control. With the help of borehole image and proactive log correlation, the trajectory can be landed precisely into desired best quality reservoir, although the formation dip and actual target depth become much different with geological prognosis. During the lateral section, the trajectory was also controlled effectively in the high-quality reservoir despite of structural variation and reservoir property change. Through use of Fit-For-Purpose solution it effectively improves drilling efficiency and positively impacts well production. These achievements subsequently help to optimize wells deployment plan and wells with longer lateral horizontal section were planned for greater predictable production rate.
Being the world's third largest shale gas producer after the US and Canada, China delivered an output of 9 billion cubic meters (bcm) in 2017. China has the world's largest technically recoverable reserves of shale gas, of which US Energy Information Administration (EIA) estimates at 31.6 tcm, 68% higher than shale reserves in the US. Unlike the US who started to explore shale gas in the 1980s, China only completed the first shale gas well in 2011. Development of shale gas resources is expected to play a vital role in China's enthusiastically planned transition to a low-carbon energy future. On September 14th, 2016, Chinese National Energy Board released Shale Gas Development Plan 2016-2020. In the plan, shale gas production goal was set at 30 bcm for 2020. With an average shale gas production of 20MCM per well per year, it is estimated that a minimum of 1500 horizontal wells with 1000m lateral length are needed by the year of 2020. The question arises whether what kind of drilling performance is needed to meet the aggressive development target. In less than a decade, Petro China, its subsidiaries and contractors have made significant breakthroughs in shale gas exploration, not only in capacity, but also drilling techniques. The paper captures the success and lessons that the drillers had gained in the last 7 years in terms of drilling performance. It is well known that China shale gas reserves are in geologically challenging areas. The challenges consisted of hard formations with kicks, losses, frequent stuck pipe and over pressure formation. The problems were amplified by high geological formation dip, faults, and stratigraphic uncertainties. In this harsh drilling environment, rate of penetration was slow, trajectory control is difficult, mud weight and circulating pressure are high, downhole torsional vibration, drilling torque and stick&slip are high, rig equipment and downhole tools fail prematurely, and non-productive time is excessive. Over the years, the team had demonstrated that with systematic, scientific and engineering drilling approaches, a considerable improvement in drilling performance can be achieved. To deliver and execute the optimized drilling approaches, high intregration and synergy between each drilling segment are required. These approaches are nothing new in the drilling world, these are optimization in Well Plan, Mud Properties, Rig Capacity & Drilling Parameters, Bottome Hole Aseembly (BHA) selection and design, best Drilling Practice and Drilling Operation Efficiency. These are all part of a formula to success; the key is to rightly balance each one of them. The team sucessfully reduce average well days from 120 to 30 in one particular field. Along the way, the team also identify a few more components to the formula of success, with that, the short-term goal shall be further reducing the well days to 25 days, and less than 20 days in long term.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.