Distributed Pressure Sensing via Fiber-Optic DAS and DTS Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional pressure gauges used in petroleum and geothermal applications are limited by frequent calibration needs, low tolerance in harsh environments, hysteresis errors, and the inability to provide distributed pressure measurements, making real-time distributed pressure measurement in high-pressure well-scale conditions challenging.
Innovation Solution
A machine learning system and method that uses fiber-optic Distributed Acoustic Sensor (DAS) and Distributed Temperature Sensor (DTS) data to predict pressure along optical fiber cables, specifically employing low-frequency DAS data combined with DTS data to train and process pressure predictions in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional pressure gauges are used for pressure measurement, then the measurement solution is cost-effective, but the gauges suffer from frequent calibration needs, low tolerance in harsh environments, hysteresis errors, and only provide pressure at discrete gauge locations
Solution Approach 1:
The patent replaces traditional mechanical pressure gauges with an optical-based distributed sensing system using fiber optic cables that can measure pressure, temperature, and vibration simultaneously along the entire wellbore without mechanical moving parts, eliminating calibration needs and improving reliability in harsh environments
Solution Approach 2:
The fiber optic cable serves multiple functions simultaneously: it acts as the sensing element for pressure measurement, temperature measurement, and vibration detection, while also serving as the data transmission medium, replacing multiple separate devices with a single multi-functional system
2Loss of information
If traditional pressure gauges are used, then the system is simple, but the gauges can only provide pressure at discrete gauge locations (single-point sensing)
Solution Approach 1:
The patent divides the wellbore into numerous discrete measurement points along the fiber optic cable, transforming a single-point sensing system into a distributed sensing system that provides continuous pressure, temperature, and vibration data at multiple locations simultaneously, eliminating information loss about pressure distribution
Solution Approach 2:
The patent transitions from zero-dimensional (single-point) pressure measurement to one-dimensional distributed measurement along the wellbore length, adding spatial dimensionality to the measurement system and enabling comprehensive pressure distribution mapping
3Measurement precision
If high-frequency DAS components are used for pressure measurement, then the system can capture dynamic events, but the accuracy for pressure prediction is reduced compared to low-frequency DAS data
Solution Approach 1:
The patent changes the frequency parameter of DAS data from high-frequency to low-frequency components for pressure prediction, optimizing the frequency range to maximize pressure measurement accuracy while using machine learning to selectively capture relevant dynamic event information
Data Source
AI summary
A machine learning system and method are provided for using fiber-optic Distributed Acoustic Sensor (DAS) and Distributed Temperature Sensor (DTS) data to predict pressure along one or more optical fiber cables. DAS and DTS data are used to train a model to predict pressure based on the DAS and DTS data corresponding to optical signals carried on the fiber cable(s). The trained model is then used to process acquired DAS and DTS data corresponding to optical signals carried on the fiber cable(s) to the predict pressure distributed along the cable(s).