Integration of Neural Networks and Wellbore Stability, a Modern Approach to Recognize Drilling Problems Through Computer Vision

2021 ◽  
Author(s):  
Luis Alejandro Rocha Vargas ◽  
Carlos Andres Izurieta
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Data Augmentation ◽  
Wellbore Stability ◽  
Causal Mechanism ◽  
Modern Approach ◽  
Wellbore Instability ◽  
Multiple Parameters ◽  
Drilling Operations ◽  
Multiple Data Sets

Abstract Cavings are a valuable source of information when drilling operations are being performed, and multiple parameters can contribute to producing cavings which indicate that failure has occurred or is about to occur downhole. This study will describe a project which is an integrated study of Machine Learning, Computer Vision, Geology, and Photography so that the recognition of cavings in the shaker is possible and how to link the cavings morphology with causal mechanisms related to wellbore instability problems. This study aims to develop a model which can extract caving features such as Shape, Edge Definition, Color, and Size. One of the core aspects of this study was to develop a structured image database of cavings from the Norwegian Continental Shelf which contains important feature information and the application of different algorithms used for automation enabled several opportunities to analyze and identify causal mechanism related to wellbore instability problems in real-time. As a result of that, the drilling operations would experience an improvement in terms of a faster decision-making process to solve operative problems related to wellbore stability which will lead to optimization not only in time and resources but also in safer drilling operations. Different algorithms and artificial intelligence tools were used to investigate the best approach to correctly detect and derive meaningful information about the shape, color size and edge from cavings like supervised learning, unsupervised learning, neural networks and computer vision. A key part of this study was image augmentation which plays a significant role for the detection of the cavings and their features. Multiple data sets can be created, and by using data augmentation, this will enable recognition of more complex patterns that will have on-rig applicability. Also, this new approach can deliver multiple outcomes besides failure mechanism identification such as volume of rocks being drilled, transport of cutting, type of formation being drilled.

scholarly journals Detection of citrus leaf diseases using a deep learning technique

2021 ◽  
Vol 11 (2) ◽  
pp. 1719
Author(s):  
Ahmed R. Luaibi ◽  
Tariq M. Salman ◽  
Abbas Hussein Miry
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Data Augmentation ◽  
Original Data ◽  
Training Images ◽  
Learning Technique ◽  
Data Points ◽  
Citrus Leaves

The food security major threats are the diseases affected in plants such as citrus so that the identification in an earlier time is very important. Convenient malady recognition can assist the client with responding immediately and sketch for some guarded activities. This recognition can be completed without a human by utilizing plant leaf pictures. There are many methods employed for the classification and detection in machine learning (ML) models, but the combination of increasing advances in computer vision appears the deep learning (DL) area research to achieve a great potential in terms of increasing accuracy. In this paper, two ways of conventional neural networks are used named Alex Net and Res Net models with and without data augmentation involves the process of creating new data points by manipulating the original data. This process increases the number of training images in DL without the need to add new photos, it will appropriate in the case of small datasets. A self-dataset of 200 images of diseases and healthy citrus leaves are collected. The trained models with data augmentation give the best results with 95.83% and 97.92% for Res Net and Alex Net respectively.

scholarly journals A Systematic Review on Data Scarcity Problem in Deep Learning: Solution and Applications

2022 ◽  
Author(s):  
Ms. Aayushi Bansal ◽  
Dr. Rewa Sharma ◽  
Dr. Mamta Kathuria
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Language Processing ◽  
Data Augmentation ◽  
Medical Science ◽  
Real Life ◽  
Survey Paper ◽  
Augmentation Techniques ◽  
Comprehensive Survey

Recent advancements in deep learning architecture have increased its utility in real-life applications. Deep learning models require a large amount of data to train the model. In many application domains, there is a limited set of data available for training neural networks as collecting new data is either not feasible or requires more resources such as in marketing, computer vision, and medical science. These models require a large amount of data to avoid the problem of overfitting. One of the data space solutions to the problem of limited data is data augmentation. The purpose of this study focuses on various data augmentation techniques that can be used to further improve the accuracy of a neural network. This saves the cost and time consumption required to collect new data for the training of deep neural networks by augmenting available data. This also regularizes the model and improves its capability of generalization. The need for large datasets in different fields such as computer vision, natural language processing, security and healthcare is also covered in this survey paper. The goal of this paper is to provide a comprehensive survey of recent advancements in data augmentation techniques and their application in various domains.

Application of Artificial Intelligence To Predict Time-DependentMud-Weight Windows in Real Time

SPE Journal ◽  
2021 ◽  
pp. 1-21
Author(s):  
Dung T. Phan ◽  
Chao Liu ◽  
Murtadha J. AlTammar ◽  
Yanhui Han ◽  
Younane N. Abousleiman
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Analytical Solution ◽  
Real Time ◽  
Analytical Solutions ◽  
Wellbore Stability ◽  
Time Dependent ◽  
Processing Unit ◽  
Inference System ◽  
Drilling Operations

Summary Selection of a safe mud weight is crucial in drilling operations to reduce costly wellbore-instability problems. Advanced physics models and their analytical solutions for mud-weight-window computation are available but still demanding in terms of central-processing-unit (CPU) time. This paper presents an artificial-intelligence (AI) solution for predicting time-dependent safe mud-weight windows and very refined polar charts in real time. The AI agents are trained and tested on data generated from a time-dependent coupled analytical solution (poroelastic) because numerical solutions are prohibitively slow. Different AI techniques, including linear regression, decision tree, random forest, extra trees, adaptive neuro fuzzy inference system (ANFIS), and neural networks are evaluated to select the most suitable one. The results show that neural networks have the best performances and are capable of predicting time-dependentmud-weight windows and polar charts as accurately as the analytical solution, with 1/1,000 of the computer time needed, making them very applicable to real-time drilling operations. The trained neural networks achieve a mean squared error (MSE) of 0.0352 and a coefficient of determination (R2) of 0.9984 for collapse mud weights, and an MSE of 0.0072 and an R2 of 0.9998 for fracturing mud weights on test data sets. The neural networks are statistically guaranteed to predict mud weights that are within 5% and 10% of the analytical solutions with probability up to 0.986 and 0.997, respectively, for collapse mud weights, and up to 0.9992 and 0.9998, respectively, for fracturing mud weights. Their time performances are significantly faster and less demanding in computing capacity than the analytical solution, consistently showing three-orders-of-magnitude speedups in computational speed tests. The AI solution is integrated into a deployed wellbore-stability analyzer, which is used to demonstrate the AI’s performances and advantages through three case studies.

scholarly journals An Assessment of the Causes of Wellbore Instability and Stuck Pipe Occurrences in an Offshore Field, Niger Delta, Nigeria

2020 ◽  
Vol 1 (1) ◽  
Keyword(s):  
Cation Exchange ◽  
Niger Delta ◽  
Drilling Fluid ◽  
Wellbore Stability ◽  
Swelling Potential ◽  
Offshore Drilling ◽  
Wellbore Instability ◽  
Clay Swelling ◽  
Drilling Operations ◽  
Cationic Exchange

Wellbore instability and consequential stuck pipe issues are a common challenge associated with offshore drilling. Usually, the effect of wellbore instability is an increase in nonproductive time, possible loss of tools and costly drilling operations. Hence, there is a need for wellbore stability analyses before and during drilling operations. In “Agaza Field”, offshore Niger Delta, wellbore instability problems were encountered at various depths between 3,696-4,270 ft.; 5,000-5,425 ft. and 7,600-8000 ft. intervals. Sixty-five ditch-cutting samples and composite log plots obtained from both wells were and analyzed to determine the clay swelling potential and the cationic exchange between the formation and the drilling fluid as well as causes of formation instability. Agaza-1 well showed evidence of tight hole at intervals between 4,200 and 7,600 ft. In Agaza-2, there were indications of wellbore stresses from 1,908 ft. to 2,030 ft. However, deeper than 4,225ft depth, high fluctuation of pore pressure coincided with wellbore instability between 4,810 ft. and 5,200 ft. The principal clay minerals present within the formations are Illite, Smectite and Smectite/Illite interlayered types. Result of the cation exchange analysis showed that high concentration of calcium and sodium in the shale is responsible for high dissociation of the constituent minerals hence making the shales unstable. Analysis has shown that samples at some intervals from both wells are associated with high swelling potential while average cation exchange value is 40 meq/100g. Therefore, the primary cause of wellbore instability and stuck pipe within the studied intervals are attributed to high swelling and reactivity over time due to fluidformation interaction. Keywords: Clay cationic exchange, Clay swelling potential, Offshore drilling challenges, Reactive shales. African

Optimize Internal Phase Salinity to Improve Wellbore Stability and Mitigate Lost Circulation

2021 ◽  
Author(s):  
Jianguo Zhang ◽  
Alan Rodgerson ◽  
Stephen Edwards
Keyword(s):  
Water Activity ◽  
Wellbore Stability ◽  
Chemical Effect ◽  
Wellbore Instability ◽  
Lost Circulation ◽  
Main Challenge ◽  
Internal Phase ◽  
Naturally Fractured ◽  
Drilling Operations ◽  
Shale Formation

Abstract Wellbore instability and lost circulation are two major sources of non-productive time (NPT) in drilling operations worldwide. Non-aqueous fluid (NAF) is often chosen to mitigate this and minimize the chemical effect on wellbore instability in reactive shales. However, it may inadvertently increase the risk of losses. A simple method to optimize internal phase salinity (IPS) of NAF is presented to improve wellbore stability and mitigate the increased possibility of losses. Field cases are used to demonstrate the effects of salinity on wellbore instability and losses, and the application of the proposed method. IPS is optimized by managing bidirectional water movement between the NAF and shale formation via semi-permeable membrane. Typically, higher shale dehydration is designed for shallow reactive shale formation with high water content. Whereas, low or no dehydration is desired for deep naturally fractured or faulted formation by balancing osmotic pressure with hydrostatic pressure difference between mud pressure and pore pressure. The simple approach to managing this is as follows: The water activity profile for the shale formation (aw,shale) is developed based on geomechanical and geothermal information The water activity of drilling fluid (aw,mud) is defined through considering IPS and thermal effects The IPS of NAF is manipulated to manage whether shale dehydration is a requirement or should be avoided If the main challenge is wellbore instability in a chemically reactive shale, then the IPS should be higher than the equivalent salinity of shale formation (or aw,shale > aw, mud) If the main challenge is losses into non-reactive, competent but naturally fractured or faulted shale, then IPS should be at near balance with the formation equivalent salinity (or aw, shale ≈ aw, mud) It is important that salt (e.g. calcium chloride – CaCl2) addition during drilling operations is done judiciously. The real time monitoring of salinity variations, CaCl2 addition, water evaporation, electric stability (ES), cuttings/cavings etc. will help determine if extra salt is required. The myth of the negative effects of IPS on wellbore instability and lost circulation is dispelled by analyzing the field data. The traditional Chinese philosophy: "following Nature is the only criteria to judge if something is right" can be applied in this instance of IPS optimization. A simple and intuitive method to manage IPS is proposed to improve drilling performance.

The machine training in problems of satellite images’s processing

Metrologiya ◽  
2020 ◽  
pp. 15-37
Author(s):  
L. P. Bass ◽  
Yu. A. Plastinin ◽  
I. Yu. Skryabysheva
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Computer Vision ◽  
Satellite Images ◽  
Vision Systems ◽  
Earth Remote Sensing ◽  
Practical Applications ◽  
Convolution Neural Networks ◽  
Computer Vision Systems ◽  
Trained Neural Network

Use of the technical (computer) vision systems for Earth remote sensing is considered. An overview of software and hardware used in computer vision systems for processing satellite images is submitted. Algorithmic methods of the data processing with use of the trained neural network are described. Examples of the algorithmic processing of satellite images by means of artificial convolution neural networks are given. Ways of accuracy increase of satellite images recognition are defined. Practical applications of convolution neural networks onboard microsatellites for Earth remote sensing are presented.

Deep neural networks trained with heavier data augmentation learn features closer to representations in hIT

2018 ◽  
Author(s):  
Alex Hernández-García ◽  
Johannes Mehrer ◽  
Nikolaus Kriegeskorte ◽  
Peter König ◽  
Tim C. Kietzmann
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

Algorithms for segmentation and recognition of objects on medical images based on chiarlet transformation and neural networks

2020 ◽  
pp. 35-45
Author(s):  
Y.A. Hamad ◽  
K.V. Simonov ◽  
A.S. Kents
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Computer Vision ◽  
Edge Detection ◽  
Medical Images ◽  
Classification Algorithms ◽  
Visual Data ◽  
Recognition Of Objects

The paper considers general approaches to image processing, analysis of visual data and computer vision. The main methods for detecting features and edges associated with these approaches are presented. A brief description of modern edge detection and classification algorithms suitable for isolating and characterizing the type of pathology in the lungs in medical images is also given.

scholarly journals Data augmentation for computed tomography angiography via synthetic image generation and neural domain adaptation

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Malte Seemann ◽  
Lennart Bargsten ◽  
Alexander Schlaefer
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Deep Learning ◽  
Medical Imaging ◽  
Computed Tomography Angiography ◽  
Data Augmentation ◽  
Domain Adaptation ◽  
Synthetic Image ◽  
Wide Range ◽  
The Impact

AbstractDeep learning methods produce promising results when applied to a wide range of medical imaging tasks, including segmentation of artery lumen in computed tomography angiography (CTA) data. However, to perform sufficiently, neural networks have to be trained on large amounts of high quality annotated data. In the realm of medical imaging, annotations are not only quite scarce but also often not entirely reliable. To tackle both challenges, we developed a two-step approach for generating realistic synthetic CTA data for the purpose of data augmentation. In the first step moderately realistic images are generated in a purely numerical fashion. In the second step these images are improved by applying neural domain adaptation. We evaluated the impact of synthetic data on lumen segmentation via convolutional neural networks (CNNs) by comparing resulting performances. Improvements of up to 5% in terms of Dice coefficient and 20% for Hausdorff distance represent a proof of concept that the proposed augmentation procedure can be used to enhance deep learning-based segmentation for artery lumen in CTA images.

Sign in / Sign up

Export Citation Format

Share Document