Wellbore Object Imaging With Adaptive Vision Under Harsh Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current drilling and pumping operations in oil and gas exploration face challenges in effectively monitoring wellbore objects due to harsh environmental conditions and remote locations, leading to inefficient and error-prone manual inspections, which often result in undetected conditions or events.
Innovation Solution
An automated object imaging and detection system using a vision system with digital cameras, sensors, and deep neural networks (DNN) to analyze images of wellbore objects, enabling real-time identification of object features like shape, size, and type, and dynamically adjusting image settings based on detected anomalies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual observation by rig-based personnel is used to inspect wellbore objects, then flexibility and adaptability to various conditions are maintained, but the monitoring is intermittent, costly, and error-prone leading to undetected conditions
Solution Approach 1:
The system enables self-service monitoring where the automated imaging system continuously captures and analyzes wellbore objects without requiring constant human intervention. The system serves itself by automatically detecting, classifying, and reporting wellbore objects, eliminating the need for continuous manual inspection while maintaining high detection accuracy and operational efficiency.
2Measurement precision
If automated imaging systems are deployed at MMSM locations, then continuous monitoring and detection accuracy are improved, but harsh environmental conditions (steam, rain, variable lighting, fog) interfere with obtaining usable images
Solution Approach 1:
The system dynamically adjusts imaging parameters such as exposure time, gain, and illumination intensity in response to changing environmental conditions. The automated exposure control and adaptive lighting systems modify capture settings in real-time to compensate for steam, rain, fog, and variable lighting, ensuring consistent image quality despite harsh environmental factors at MMSM locations.
3Ease of operation
If imaging is performed at separation screens, then object flow can be monitored, but vibration and fluid saturation cause image distortion and overlapping debris reduces data usefulness
Solution Approach 1:
The system creates multiple image copies and uses image processing algorithms to reconstruct clear images from distorted captures. By capturing multiple frames and processing them through deconvolution and noise reduction algorithms, the system produces accurate representations of wellbore objects even when initial images are distorted by vibration and fluid saturation at the separation screen location.
4Speed
If computing analysis is performed close to MMSM due to poor data transmission rates, then data processing speed is maintained, but the system complexity and infrastructure requirements increase
Solution Approach 1:
The system segments processing tasks by performing initial image capture and preprocessing at the edge device near the MMSM, then selectively transmitting only essential data or processed results to remote servers. This segmentation allows critical real-time analysis to occur locally with minimal infrastructure, while complex analytical tasks can be distributed to remote computing resources when bandwidth permits, optimizing both speed and complexity management.
Data Source
AI summary
A method including selecting image data of a mechanical mud separation machines (“MMSM”) to detect objects in an object flow and other operational conditions at the MMSM. The image data may be processed by a Deep Neural Network to identify objects in the object flow, operational parameters of the MMSM, and environmental conditions. Additional image data may be selected for additional processing based on the results of the analysis.