Towards Managing Uncertain Geo-Information for Drilling Disasters Using Event Tracking Sensitivity Analysis
In sub-surface drilling rigs, one key critical crisis is unwanted influx into the borehole as a result of increasing the influx rate while drilling deeper into a high-pressure gas formation. Although established risk assessments in drilling rigs provide a high degree of protection, uncertainty arise...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/9/4292 |
| _version_ | 1827742548800569344 |
|---|---|
| author | Siamak Tavakoli Stefan Poslad Rudolf Fruhwirth Martin Winter Herwig Zeiner |
| author_facet | Siamak Tavakoli Stefan Poslad Rudolf Fruhwirth Martin Winter Herwig Zeiner |
| author_sort | Siamak Tavakoli |
| collection | DOAJ |
| description | In sub-surface drilling rigs, one key critical crisis is unwanted influx into the borehole as a result of increasing the influx rate while drilling deeper into a high-pressure gas formation. Although established risk assessments in drilling rigs provide a high degree of protection, uncertainty arises due to the behavior of the formation being drilled into, which may cause crucial situations at the rig. To overcome such uncertainties, real-time sensor measurements are used to predict, and thus prevent, such crises. In addition, new understandings of the effective events were derived from raw data. In order to avoid the computational overhead of input feature analysis that hinders time-critical prediction, EventTracker sensitivity analysis, an incremental method that can support dimensionality reduction, was applied to real-world data from 1600 features per each of the 4 wells as input and 6 time series per each of the 4 wells as output. The resulting significant input series were then introduced to two classification methods: Random Forest Classifier and Neural Networks. Performance of the EventTracker method was understood correlated with a conventional manual method that incorporated expert knowledge. More importantly, the outcome of a Neural Network Classifier was improved by reducing the number of inputs according to the results of the EventTracker feature selection. Most important of all, the generation of results of the EventTracker method took fractions of milliseconds that left plenty of time before the next bunch of data samples. |
| first_indexed | 2024-03-11T04:06:45Z |
| format | Article |
| id | doaj.art-4e619430c3a74c3cac31e4250b274cae |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T04:06:45Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4e619430c3a74c3cac31e4250b274cae2023-11-17T23:42:21ZengMDPI AGSensors1424-82202023-04-01239429210.3390/s23094292Towards Managing Uncertain Geo-Information for Drilling Disasters Using Event Tracking Sensitivity AnalysisSiamak Tavakoli0Stefan Poslad1Rudolf Fruhwirth2Martin Winter3Herwig Zeiner4Computer Science Department, Maharishi International University, Fairfield, IA 52557, USASchool of Electronic Engineering and Computer Science, Queen Mary University of London, London E1 4NS, UKThonhauser Data Engineering GmbH, 8700 Leoben, AustriaJOANNEUM RESEARCH Forschungsgesellschaft mbH, 8010 Graz, AustriaJOANNEUM RESEARCH Forschungsgesellschaft mbH, 8010 Graz, AustriaIn sub-surface drilling rigs, one key critical crisis is unwanted influx into the borehole as a result of increasing the influx rate while drilling deeper into a high-pressure gas formation. Although established risk assessments in drilling rigs provide a high degree of protection, uncertainty arises due to the behavior of the formation being drilled into, which may cause crucial situations at the rig. To overcome such uncertainties, real-time sensor measurements are used to predict, and thus prevent, such crises. In addition, new understandings of the effective events were derived from raw data. In order to avoid the computational overhead of input feature analysis that hinders time-critical prediction, EventTracker sensitivity analysis, an incremental method that can support dimensionality reduction, was applied to real-world data from 1600 features per each of the 4 wells as input and 6 time series per each of the 4 wells as output. The resulting significant input series were then introduced to two classification methods: Random Forest Classifier and Neural Networks. Performance of the EventTracker method was understood correlated with a conventional manual method that incorporated expert knowledge. More importantly, the outcome of a Neural Network Classifier was improved by reducing the number of inputs according to the results of the EventTracker feature selection. Most important of all, the generation of results of the EventTracker method took fractions of milliseconds that left plenty of time before the next bunch of data samples.https://www.mdpi.com/1424-8220/23/9/4292drilling disasterfeature selectionforward selectionsensitivity analysisrandom forest classifierneural networks |
| spellingShingle | Siamak Tavakoli Stefan Poslad Rudolf Fruhwirth Martin Winter Herwig Zeiner Towards Managing Uncertain Geo-Information for Drilling Disasters Using Event Tracking Sensitivity Analysis Sensors drilling disaster feature selection forward selection sensitivity analysis random forest classifier neural networks |
| title | Towards Managing Uncertain Geo-Information for Drilling Disasters Using Event Tracking Sensitivity Analysis |
| title_full | Towards Managing Uncertain Geo-Information for Drilling Disasters Using Event Tracking Sensitivity Analysis |
| title_fullStr | Towards Managing Uncertain Geo-Information for Drilling Disasters Using Event Tracking Sensitivity Analysis |
| title_full_unstemmed | Towards Managing Uncertain Geo-Information for Drilling Disasters Using Event Tracking Sensitivity Analysis |
| title_short | Towards Managing Uncertain Geo-Information for Drilling Disasters Using Event Tracking Sensitivity Analysis |
| title_sort | towards managing uncertain geo information for drilling disasters using event tracking sensitivity analysis |
| topic | drilling disaster feature selection forward selection sensitivity analysis random forest classifier neural networks |
| url | https://www.mdpi.com/1424-8220/23/9/4292 |
| work_keys_str_mv | AT siamaktavakoli towardsmanaginguncertaingeoinformationfordrillingdisastersusingeventtrackingsensitivityanalysis AT stefanposlad towardsmanaginguncertaingeoinformationfordrillingdisastersusingeventtrackingsensitivityanalysis AT rudolffruhwirth towardsmanaginguncertaingeoinformationfordrillingdisastersusingeventtrackingsensitivityanalysis AT martinwinter towardsmanaginguncertaingeoinformationfordrillingdisastersusingeventtrackingsensitivityanalysis AT herwigzeiner towardsmanaginguncertaingeoinformationfordrillingdisastersusingeventtrackingsensitivityanalysis |