Wellbore Event Model Training Using DTS and DAS Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in accurately determining fluid inflow locations and rates in wellbores with multiple production zones, making it difficult to manage fluid production effectively.
Innovation Solution
A method and system that utilize a combination of distributed temperature sensing (DTS) and distributed acoustic sensing (DAS) to identify events within wellbores by training event models with labeled data from both temperature and acoustic measurements, allowing for precise identification and quantification of fluid inflows, outflows, and other events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple production zones are present in a wellbore, then the total flow of fluid can be detected at the wellhead, but it becomes difficult to determine where the fluid is inflowing into the wellbore and the extent of the fluid inflow
Solution Approach 1:
The wellbore is divided into multiple monitoring segments along its length, with sensors positioned at specific intervals. Each sensor monitors a specific zone for fluid inflow events, allowing precise location identification without requiring a completely complex system overhaul. The segmentation of the monitoring function enables targeted detection in multiple production zones.
Solution Approach 2:
Acoustic sensors serve as intermediaries that detect fluid inflow events by capturing acoustic signals generated when fluid enters the wellbore. These sensors translate physical inflow events into detectable signals, enabling indirect but precise measurement of inflow locations and rates without direct intervention in the fluid flow path.
2Measurement precision
If acoustic sensors are used to detect fluid inflow events, then precise identification of inflow locations is achieved, but the system requires sophisticated signal processing and model training
Solution Approach 1:
Event models are trained in advance using labeled acoustic data from known fluid inflow events. This preliminary training phase creates ready-to-use detection algorithms that can be deployed without real-time complexity. The models learn to identify acoustic signatures of different event types beforehand, simplifying operational signal processing.
Solution Approach 2:
The system uses labeled event data from acoustic measurements to continuously improve and refine the event models. Feedback from identified events is used to retrain and enhance model accuracy over time, creating a self-improving system that reduces processing complexity while maintaining high precision.
3Productivity
If distributed temperature sensing and distributed acoustic sensing are combined, then real-time identification and quantification of fluid inflows is enabled, but data integration and model training complexity increases
Solution Approach 1:
Distributed temperature sensing (DTS) and distributed acoustic sensing (DAS) systems are merged into a unified monitoring platform. Both sensor types share common infrastructure including fiber optic cables, data acquisition systems, and processing hardware. This merging enables simultaneous temperature and acoustic monitoring while reducing overall system complexity through shared components.
Solution Approach 2:
The fiber optic cable serves multiple functions: it acts as both the transmission medium for DTS measurements and the sensing element for DAS measurements. This multi-functionality eliminates the need for separate sensor systems, reducing data integration complexity while enabling real-time identification and quantification of fluid inflows through combined thermal and acoustic data.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables real-time or near-real-time identification and quantification of fluid inflows, outflows, and other events in wellbores, facilitating better management of production and remediation actions, improving operational efficiency and reducing operational risks.
Implementation Method 1
obtaining a first set of measurements of a first signal within a wellbore
Implementation Method 2
obtaining an acoustic data set from within the wellbore
Implementation Method 3
training one or more fluid inflow models using the acoustic data set and the identification of the one or more events as inputs
Data Source
AI summary
A method of identifying events within a wellbore comprises obtaining a first set of measurements of a first signal within a wellbore, identifying one or more events within the wellbore using the first set of measurements, obtaining a second set of measurements of a second signal within the wellbore, wherein the first signal and the second signal represent different physical measurements, training one or more event models using the second set of measurements and the identification of the one or more events as inputs, and using the one or more event models to identify at least one additional event within the wellbore.