Poster Open Access

Combining Physics-Based and Data-Driven Modeling for Pressure Prediction in Well Construction

Oney Erge; Eric van Oort


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/5bdcb0ed-b547-49cd-beb9-08c40b46f378/SciPy2020_poster.pdf"
      }, 
      "checksum": "md5:5bc9c2dc964c594d9cab8368b19cd0ff", 
      "bucket": "5bdcb0ed-b547-49cd-beb9-08c40b46f378", 
      "key": "SciPy2020_poster.pdf", 
      "type": "pdf", 
      "size": 1042491
    }
  ], 
  "owners": [
    109103
  ], 
  "doi": "10.5281/zenodo.3906912", 
  "stats": {
    "version_unique_downloads": 146.0, 
    "unique_views": 170.0, 
    "views": 179.0, 
    "version_views": 179.0, 
    "unique_downloads": 146.0, 
    "version_unique_views": 170.0, 
    "volume": 166798560.0, 
    "version_downloads": 160.0, 
    "downloads": 160.0, 
    "version_volume": 166798560.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3906912", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3906911", 
    "bucket": "https://zenodo.org/api/files/5bdcb0ed-b547-49cd-beb9-08c40b46f378", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3906911.svg", 
    "html": "https://zenodo.org/record/3906912", 
    "latest_html": "https://zenodo.org/record/3906912", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3906912.svg", 
    "latest": "https://zenodo.org/api/records/3906912"
  }, 
  "conceptdoi": "10.5281/zenodo.3906911", 
  "created": "2020-06-24T20:58:50.258895+00:00", 
  "updated": "2020-06-24T22:18:23.024224+00:00", 
  "conceptrecid": "3906911", 
  "revision": 2, 
  "id": 3906912, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3906912", 
    "description": "<p>This poster introduces&nbsp;a novel framework to combine&nbsp;the physics-based and data-driven modeling, aiming to attain the best features of both approaches for well construction. Gaussian processes, neural networks and deep learning models are trained and executed together with a physics model that is directly derived using the first principles. Then the results are combined through a decision-making algorithm, a hidden Markov model. The approach is tested within the scope of wellbore hydraulics on a dataset from an actual drilling operation. The results suggest the proposed approach has a good potential to allow safer, optimized drilling operations.</p>", 
    "language": "eng", 
    "title": "Combining Physics-Based and Data-Driven Modeling for Pressure Prediction in Well Construction", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3906911"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3906912"
          }
        }
      ]
    }, 
    "keywords": [
      "Deep Learning, Machine Learning, Combining Physics-Based Modeling and Data-Driven Modeling, Hydraulics Modeling, Frictional Pressure Loss Modeling."
    ], 
    "publication_date": "2020-06-24", 
    "creators": [
      {
        "orcid": "0000-0002-2687-9135", 
        "affiliation": "The University of Texas", 
        "name": "Oney Erge"
      }, 
      {
        "affiliation": "The University of Texas", 
        "name": "Eric van Oort"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "poster", 
      "title": "Poster"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3906911", 
        "relation": "isVersionOf"
      }
    ]
  }
}
179
160
views
downloads
All versions This version
Views 179179
Downloads 160160
Data volume 166.8 MB166.8 MB
Unique views 170170
Unique downloads 146146

Share

Cite as