Multivariate Contamination Prediction Using Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for estimating oil-based mud (OBM) filtrate contamination in downhole fluid sampling are inadequate, especially in scenarios with low fluid density contrast, leading to inaccurate contamination levels and challenges in obtaining uncontaminated formation fluid samples.
Innovation Solution
A multivariate end-member fingerprint approach using data from multiple sensors and optical channels to fuse density and optical data, applying Principal Component Analysis (PCA) and multivariate curve resolution (MCR) algorithms to determine OBM filtrate contamination levels, regardless of density contrast, and estimate optical and density properties of both formation fluid and OBM filtrate.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional density measurement methods are used to estimate OBM filtrate contamination, then the estimation is simple and quick, but the measurement precision deteriorates significantly in low fluid density contrast scenarios
Solution Approach 1:
The patent combines multiple measurement techniques (density measurements, optical spectroscopy, and other sensor data) into a unified multivariate analysis framework. By merging these different data sources, the system achieves accurate contamination estimation in low density contrast scenarios where conventional single-method approaches fail, while maintaining operational efficiency through integrated processing.
Solution Approach 2:
The patent transforms the estimation approach by changing from relying on a single parameter (density contrast) to utilizing multiple parameters simultaneously (density, optical properties, and other fluid characteristics). This parameter expansion allows the system to maintain measurement precision across varying density contrast conditions by compensating with additional measurement dimensions.
2Measurement precision
If multiple sensors and multivariate analysis methods are used to determine contamination levels, then the measurement precision improves across all density scenarios, but the device complexity increases
Solution Approach 1:
The patent implements a multivariate analysis platform that serves multiple functions: it processes density measurements, optical spectroscopy data, and other sensor inputs through a unified Principal Component Analysis (PCA) framework. This universal approach handles both high and low density contrast scenarios with the same system architecture, avoiding the need for multiple specialized devices and reducing overall system complexity despite the enhanced capabilities.
Data Source
AI summary
Systems and methods for performing a contamination estimation of a downhole sample comprising at least a formation fluid and/or a filtrate are provided. A plurality of downhole signals are obtained from the downhole sample and one or more of the signals are conditioned. At least two of the conditioned signals or downhole signals are fused into a multivariate dataset. From optical and density properties of the formation fluid and/or of the filtrate, a multivariate calculation is performed to generate concentration profiles of the formation fluid and the filtrate.