Design of an Image Segmentation System Based on Hierarchical Density-Based Spatial Clustering of Applications with Noise for Off-Road Unmanned Ground Vehicles
Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
Cited by 2 publications
References 15 publications
Automatic Determination of Cuttings and Cavings Properties for Hole Cleaning and Wellbore Stability Assessment Using a Laser-Based Sensor
This work describes an accurate method for the automatic, real-time characterization of cuttings and cavings, including their volume, size distribution, and shape/morphology. This method integrates high-resolution images and 3D data (points in 3D space), collected in real-time using an integrated laser-based sensor previously tested in the field. Additionally, we analyze the effect of the morphological characteristics of cuttings/cavings on the volume correction factor, which is a function of the void space, when these are stacked up. The proposed method encompasses (1) the identification of individual cuttings/cavings in the data (segmentation), (2) the extraction of their morphological characteristics, and (3) the estimation of their bulk volume, as well as their effective volume (without the interstitial void space) when these are stacked. To achieve these outputs, our method incorporates (1) optimized image pre-processing methods, (2) state-of-the-art computer vision techniques, (3) ellipse-fitting algorithms, and (4) numerical integration of the 3D data. We validated the proposed method at laboratory scale simulating challenging field conditions. These conditions included poor mud/solids separation and stacked cuttings. The assessment of the hole cleaning efficiency and wellbore stability is key to preventing undesirable non-productive time (NPT) events in drilling operations, such as stuck pipe events. The conventional method for such an assessment involves low-frequency sampling of cuttings/cavings from collector trays at the rig shale shakers, as well as their manual characterization by a human. This person infers volume, size distribution, and morphological characteristics of the returning stream. This approach results in a biased and often late evaluation of hole cleaning and wellbore stability issues, thereby missing out on opportunities to prevent NPT. Our method enables an accurate real-time characterization of cuttings/cavings, even in challenging conditions such as wet solids conditions and stacking-up. Additionally, we observed that, when the cuttings/cavings are stacked, the required correction to the initial volume estimation (derived from the integration of the 3D data) depends on their morphological characteristics, as well as the level of stacking. Since our proposed method covers these aspects, it can also provide an accurate measurement of the solids return volume, serving as basis for a timely and accurate evaluation of hole cleaning sufficiency and wellbore stability. This work is the first to propose a holistic, automatic, and real-time characterization of cuttings/cavings, including their volume, size distribution, and shape/morphology. Furthermore, it is the first to integrate 3D data with high-resolution images to pursue this objective. The method proposed in this paper can be used for the real-time assessment of hole cleaning sufficiency and wellbore stability, and, consequently, for the prediction, prevention, and better management of NPT-producing events.
Automatic Determination of Cuttings and Cavings Properties for Hole Cleaning and Wellbore Stability Assessment Using a Laser-Based Sensor
This work describes an accurate method for the automatic, real-time characterization of cuttings and cavings, including their volume, size distribution, and shape/morphology. This method integrates high-resolution images and 3D data (points in 3D space), collected in real-time using an integrated laser-based sensor previously tested in the field. Additionally, we analyze the effect of the morphological characteristics of cuttings/cavings on the volume correction factor, which is a function of the void space, when these are stacked up. The proposed method encompasses (1) the identification of individual cuttings/cavings in the data (segmentation), (2) the extraction of their morphological characteristics, and (3) the estimation of their bulk volume, as well as their effective volume (without the interstitial void space) when these are stacked. To achieve these outputs, our method incorporates (1) optimized image pre-processing methods, (2) state-of-the-art computer vision techniques, (3) ellipse-fitting algorithms, and (4) numerical integration of the 3D data. We validated the proposed method at laboratory scale simulating challenging field conditions. These conditions included poor mud/solids separation and stacked cuttings. The assessment of the hole cleaning efficiency and wellbore stability is key to preventing undesirable non-productive time (NPT) events in drilling operations, such as stuck pipe events. The conventional method for such an assessment involves low-frequency sampling of cuttings/cavings from collector trays at the rig shale shakers, as well as their manual characterization by a human. This person infers volume, size distribution, and morphological characteristics of the returning stream. This approach results in a biased and often late evaluation of hole cleaning and wellbore stability issues, thereby missing out on opportunities to prevent NPT. Our method enables an accurate real-time characterization of cuttings/cavings, even in challenging conditions such as wet solids conditions and stacking-up. Additionally, we observed that, when the cuttings/cavings are stacked, the required correction to the initial volume estimation (derived from the integration of the 3D data) depends on their morphological characteristics, as well as the level of stacking. Since our proposed method covers these aspects, it can also provide an accurate measurement of the solids return volume, serving as basis for a timely and accurate evaluation of hole cleaning sufficiency and wellbore stability. This work is the first to propose a holistic, automatic, and real-time characterization of cuttings/cavings, including their volume, size distribution, and shape/morphology. Furthermore, it is the first to integrate 3D data with high-resolution images to pursue this objective. The method proposed in this paper can be used for the real-time assessment of hole cleaning sufficiency and wellbore stability, and, consequently, for the prediction, prevention, and better management of NPT-producing events.
Automatic Determination of Cuttings and Cavings Properties for Hole Cleaning and Wellbore Stability Assessment Using a Laser-Based Sensor
Summary This work describes an accurate method for the automatic, real-time characterization of cuttings and cavings, including their volume, size distribution, and shape/morphology. This method integrates high-resolution images and 3D data (points in 3D space), collected in real time using an integrated laser-based sensor previously tested in the field. In addition, we analyze the effect of the morphological characteristics of cuttings/cavings on the estimated void space between them when they are stacked. The proposed method encompasses (1) the identification of individual cuttings/cavings in the data (segmentation), (2) the extraction of their morphological characteristics, and (3) the estimation of their bulk volume, as well as their effective volume (without the interstitial void space) when these are stacked. To achieve these outputs, our method incorporates (1) optimized image preprocessing methods, (2) state-of-the-art computer vision techniques, (3) ellipse-fitting algorithms, and (4) numerical integration of the 3D data. We validated the proposed method at laboratory scale, simulating challenging field conditions that included poor mud/solids separation and stacked cuttings. The assessment of the hole cleaning sufficiency and wellbore stability is key to preventing undesirable nonproductive time (NPT) events in drilling operations, such as stuck pipe events. The conventional method for such an assessment involves low-frequency sampling of cuttings/cavings from collector trays at the rig shale shakers, as well as their manual characterization by a human. This person infers volume, size distribution, and morphological characteristics of the returning solids stream. This approach results in a biased and often late evaluation of hole cleaning and wellbore stability issues, thereby missing out on opportunities to prevent NPT. Our method enables an accurate real-time characterization of cuttings/cavings, even in challenging conditions such as wet and stacked solids. Additionally, we observed that, when the cuttings/cavings are stacked, the required correction to the initial volume estimation (derived from the integration of the 3D data) depends on their morphological characteristics, as well as the level of stacking. Because our proposed method covers these aspects, it can also provide an accurate measurement of the solids’ volume, serving as the basis for a timely and accurate evaluation of hole cleaning sufficiency and wellbore stability. This work is the first to propose a holistic, automatic, and real-time characterization of cuttings/cavings, including their volume, size distribution, and shape/morphology. Furthermore, it is the first to integrate 3D data with high-resolution images to pursue this objective. The method proposed in this paper can be used for the real-time assessment of hole cleaning sufficiency and wellbore stability, and, consequently, for the prediction, prevention, and better management of NPT-producing events.
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.
Contact Info
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Product
Resources
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.
