Downhole Casing Perforation Measurement from Acoustic Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual inspection of tubulars for perforations is time-consuming and prone to errors due to complex, noisy 3D acoustic images, making it difficult for human operators and existing image processing software to accurately identify and measure features like cracks and perforations.
Innovation Solution
A method and system using a Perforation Segmentation Model, such as UNet or UNet++, to automatically identify and calculate geometric properties of perforations in downhole casings from ultrasound images, involving convolution and thresholding to create perforation masks and contours.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual inspection is used to identify perforations in ultrasound images, then human operators can detect features, but the process is time-consuming and prone to error
Solution Approach 1:
The patent replaces the manual mechanical inspection process with an automated computer-based system that uses machine learning models to analyze ultrasound images. The system automatically identifies perforations, calculates geometric properties, and generates reports without human intervention in the measurement process, thereby eliminating time consumption and human error while maintaining high detection accuracy.
2Extent of automation
If existing image processing software is used, then automated processing is possible, but the software cannot accurately identify perforations due to image complexity and noise
Solution Approach 1:
The patent transforms the ultrasound image data from its original complex format into a processed representation suitable for machine learning analysis. The system applies specific preprocessing steps and uses trained neural network models that have learned to recognize perforation patterns despite image noise and complexity, achieving both high automation and accurate measurement.
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between the raw ultrasound images and the final perforation measurements. This intermediary component processes the complex, noisy images through learned patterns and relationships, enabling accurate automated detection that neither raw images nor simple processing algorithms could achieve alone.
3Measurement precision
If digital calipers are used to measure perforation dimensions, then operators can estimate diameter and area, but the measurements are prone to judgment error and vary between operators
Solution Approach 1:
The patent replaces the manual digital caliper measurement process with an automated computer vision system that calculates geometric properties directly from the ultrasound images. The system automatically determines perforation dimensions, area, and other geometric characteristics without human measurement, eliminating operator judgment errors and inter-operator variability while providing consistent, precise measurements.
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 fast and accurate identification and measurement of perforations, reducing human error and increasing efficiency by providing automated geometric measurements.
Implementation Method 1
acoustic imaging is used to log tubulars
Implementation Method 2
Reflections from these features are subtly different from the surrounding area
Data Source
AI summary
A method and instruction memory for processing acoustic images of a downhole casing to determine perforations of the tubular. The images may be acquired by an acoustic logging tool deployed into cased well. A Machine Learning model is trained to recognize regions of the acoustic images that are perforations or not, in order to calculate geometric properties of the perforation and overall casing. Renderings of the imaged casing may be overlaid with contours and properties of perforations to improve perforation, fracturing and producing operations.