Machine Learning/Artificial Intelligence Driven Computer Vision for Cuttings Analysis Under Drilling and Completions

2021 ◽  
Author(s):  
Chafaa Badis ◽  
Welton Souza ◽  
Mohammad Abadullah Yasir ◽  
Perminder Sabharwal

Abstract The shape and size of formation cuttings passing through a shaker screen can provide valuable insights about any potential downhole problems. Large size cuttings or carvings may indicate the presence of an abnormal pressure zone and hole size may be enlarged which may lead to NPT events (stuck pipe, loss circulation, etc.), asset loss or HSE incidents. We proposed a new method of real-time automated analysis of cuttings in the shale shaker enabling faster reaction to mitigate risks associated with drilling operations. The solution uses a camera on the shaker screen, capturing the cuttings images and applying computer vision and convolutional neural networks algorithms to identify and classify individual cuttings shape, size and type combined with wireline data to raise alarms on specific conditions and prescribe actions to mitigate the problem. The solution showed a remarkably high confidence in identifying the cutting types and size and in detecting potential problems at their early stage enabling the drilling engineers to take the corrective actions at the onset of an event.

2014 ◽  
Vol 493 ◽  
pp. 80-85 ◽  
Author(s):  
C.L Siow ◽  
Jaswar ◽  
Efi Afrizal

Computational Fluid Dynamics (CFD) software is often used to study fluid flow and structures motion in fluids. The CFD normally requires large size of arrays and computer memory and then caused long execution time. However, Innovation of computer hardware such as multi-cores processor provides an alternative solution to improve this programming performance. This paper discussed loop parallelize multi-cores processor for optimization of sequential looping CFD code. This loop parallelize CFD was achieved by applying multi-tasking or multi-threading code into the original CFD code which was developed by one of the authors. The CFD code was developed based on Reynolds Average Navier-Stokes (RANS) method. The new CFD code program was developed using Microsoft Visual Basic (VB) programming language. In the early stage, the whole CFD code was constructed in a sequential flow before it is modified to parallel flow by using VBs multi-threading library. In the comparison, fluid flow around the hull of round-shaped FPSO was selected to compare the performance of both the programming codes. Besides, executed results of this self-developed code such as pressure distribution around the hull were also presented in this paper.


1940 ◽  
Vol s2-81 (324) ◽  
pp. 479-520
Author(s):  
ELIZABETH A. FRASER ◽  
RACHEL M. RENTON

1. A short account is given of the breeding habits of Heterandria formosa in an aquarium. 2. The ovary and the mature ovum are briefly described, the noteworthy feature of the ripe ovum being the small quantity of yolk. 3. Degeneration of ova is found to be a common occurrence in unfertilized females, and to a less extent in those full of developing embryos. 4. The method for ensuring the fertilization of the egg within the follicle is portrayed. Over the area where the spermatozoa have entered the cells of the ovarian epithelium and those of the follicle form a solid plug which eventually disrupts to enable the fully developed embryo to escape into the cavity of the ovary. 5. It is characteristic of early development that the egg is encircled by a unilaminar ectoderm before there is any visible differentiation into endoderm and mesoderm. 6. Owing to the scarcity of yolk only a few periblast cells arise and no syncytial layer is formed. 7. The primitive-germ cells are visible at an early stage within the apparently undifferentiated mesendoderm cells. 8. A striking feature is the large size of the pericardium and its growth upwards as a pericardium hood which completely surrounds the head region of the embryo. Over the walls runs a network of blood-vessels from which the maternal capillaries become eventually separated by only an attenuated layer of protoplasm. Both respiration and nutrition are effected through the follicle. 9. A remarkable specialization is the development of a urinary bladder which expands into a thin-walled vesicle of enormous dimensions, finally occupying almost the entire area formerly filled by the pericardium and the yolk-granules. 10. The development of Heterandria is compared with that of other viviparous fishes. 11. The significance of the unusual features in early and late development is discussed and some comparisons are made with the conditions in higher vertebrates.


2017 ◽  
Vol 11 (1) ◽  
pp. 413-419 ◽  
Author(s):  
Narjiss Akerzoul ◽  
Saliha Chbicheb ◽  
Wafaa El Wady

Introduction: Odontomas are considered as benign tumors of odontogenic tissue origin and are more over non-aggressive. They can also be categorized as hamartomas and are a result of developmental malformation of odontogenic tissues. As the name suggests, they are composed of mature tooth substances. They possess limited and slow growth potential and are well differentiated. They can be ectodermal, mesodermal or mixed in origin. Mixed variety may be further divided into compound or complex depending upon their radio-graphical resemblance to the tooth. Compound odontomes are reported to be twice more common than complex odontomes. Among them, complex odontomes are asymptomatic unless they cause bony expansion of the jaws. Case Report: This paper aims to report and discuss a case of complex odontoma with unusually large size leading to gross facial asymmetry. Further this paper will highlight the important information the general dental practitioner must possess to diagnose such lesions at an early stage. Conclusion: Odontomas are benign odontogenic tumors with unusually large size leading to gross facial asymmetry. The general dental practitioners must possess the knowledge and important information to diagnose such lesions at an early stage.


2021 ◽  
Vol 7 (4) ◽  
pp. 46-63
Author(s):  
Dr. Faleh H. M. Almahdawi ◽  
Dr. Kareem A. Alwan ◽  
Ahmed K. H. Alhusseini

Prediction of formation pore pressure gradient is a very important factor in designingdrilling well program and it help to avoid many problems during drilling operations such as lostcirculation, kick, blowout and other problems.In this study, abnormal formation pressure is classified into two types; abnormal highpressure (HP) and abnormal low pressure (LP), therefore any pressure that is either above orbelow the hydrostatic pressure is referred to as an abnormal formation pressure.This study concerns with abnormal formation pressure distribution and their effect ondrilling operations in middle & south Iraqi oil fields. Abnormal formation pressure maps aredrawn depending upon drilling evidence and problems.Three formations are considered as abnormal formations in the region of study, theseformations geologically existed in Tertiary age and they from shallower to deeper are: LowerFars, Dammam and Umm Er Radhuma, Formations. The maps of this study referred to eitherhigh formations pressure such as (Lower Fars and Umm Er Radhuma) or the low formationspressure such as (Dammam) in middle and south of Iraq. Finally these maps also suggested andshowed the area, where no field is drill until now, which may behave as high, low and normalformation pressure for every formation understudy.


2015 ◽  
Vol 36 (7) ◽  
pp. 1095-1123 ◽  
Author(s):  
Lixin Cai

Purpose – The purpose of this paper is to enhance understanding low pay dynamics of Australian employees, with a focus on the determination of low pay duration. Design/methodology/approach – The study draws on a representative longitudinal survey of Australian households to provide empirical findings from both descriptive analysis and econometric modelling. Findings – The results show that workers who have entered low pay from higher pay also have a higher hazard rate of transitioning to higher pay; and those who have entered low pay from non-employment are more likely to return to non-employment. Union members, public sector jobs and working in medium to large size firms tend to increase the hazard rate of transitioning to higher pay, while immigrants from non-English speaking countries and workers with health problems have a lower hazard rate of moving into higher pay. There is some evidence that the longer a worker is on low pay, the less likely he or she is to transition to higher pay. Originality/value – This study addresses an information gap regarding the determination of low pay duration. The findings help identify workers who are at high risk of staying on low pay or transitioning into non-employment and are therefore informative for developing targeted policy to help the low paid maintain employment and/or move up the earnings ladder. The results also suggest that policy intervention should take place at an early stage of a low pay spell.


2021 ◽  
Author(s):  
Taekwang Ha ◽  
Jun Ma ◽  
Jørgen Blindheim ◽  
Torgeir Welo ◽  
Geir Ringen ◽  
...  

Bending processes have various advantages, such as less processing time, lower number of tooling parts, and cost compared to other manufacturing processes. However, one of the disadvantages of a bending process is the inevitable springback problem, which entails geometrical inaccuracy. Many researchers have made attempts to effectively measure springback in-line to control product quality and compensate for variability. While measurement tools and machines are available to measure springback, they might not be able to accommodate large products due to the size limit of measurement devices. Nevertheless, sensor-based monitoring is becoming critical to control product quality and to move towards Industry 4.0. In this paper, an in-situ springback monitoring technique for bending of large-size profiles is proposed to overcome the measurement restrictions for such profiles. A computer vision technique with the circular Hough transform was used to evaluate springback. The marked points on a profile were used to track the deformation of the workpiece. However, a weakness with image processing is to recognize the points from the complex background. Instead of employing global search for the points in an image frame, the marked points were detected by locally setting regions based on forming parameters such as a bending angle and stretching level. Springback was calculated by the change of position of those points. The results of springback monitoring were validated with the physically measured data from experiments. Based on this measurement technique, the feasibility of a computer vision-based springback monitoring in large-size profile bending is discussed in detail.


Author(s):  
Ayush Gupta

-In the current scenario of the data world, the data holds significant information if processed correctly. The data can be in the form of images which can prove to be a boon in deriving the useful insights from it in order to get the knowledge of things at an early stage itself. But the matter of concern is deriving the information from the images will be a tedious task for human beings and would incur a heavy cost and time. So, an easy and cheaper technique is to teach a machine efficiently to do the task for us. The concept of using Machines to do human tasks is known as Machine Learning. In this paper, I present various literature reviews regarding image processing in Machine learning and how image processing has helped in identifying the issues at early stages so that they can be resolved easily without causing much harm. Also, image processing has been a helpful tool in computer vision.


2009 ◽  
Vol 44 (4) ◽  
pp. 314-322 ◽  
Author(s):  
Tracy C. Leskey ◽  
Brent D. Short ◽  
Starker E. Wright ◽  
Mark W. Brown

Adult brown stink bugs, Euschistus servus (Say), were caged individually on limbs with apple fruit of 6 cultivars in research orchards in West Virginia. Studies were performed to describe specific characteristics of damage that could be used for field and/or laboratory diagnosis of stink bug injury to apple fruit at harvest. These characteristics were separated into surface and subsurface features. On the apple surface, 3 prevailing types of stink bug injury were observed in the field: (1) a discolored dot, i.e., stink bug feeding puncture; (2) a discolored dot with a depression in the fruit; and (3) a discolored dot with a discolored depression in the fruit. Subsurface characters were related to the extent of damage observed on the fruit skin. Common subsurface damage ranged from a stylet sheath to corky tissue of variable color, shape, and size that sometimes was not contiguous with the skin. Laboratory evaluations under a dissecting microscope revealed that the size of the stink bug feeding puncture was ~0.17 mm diam. This character was the only consistent, definitive symptom of stink bug injury present among all observed damage. Due to variability in other surface and subsurface characters, and potential problems with visual apparency of injury in the field, evaluations of suspected stink bug damage should be performed with 40X magnification in the laboratory to confirm the presence of stink bug feeding punctures.


Sign in / Sign up

Export Citation Format

Share Document