Higher Order Channels for Drilling Event Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Time-series data in the oil and gas industry, particularly in drilling and hydraulic fracturing, is often processed inconsistently, leading to inaccurate and incomplete analysis due to reliance on manual methods that fail to identify hidden features and higher order channels, resulting in reduced accuracy and speed of analysis.
Innovation Solution
Automated methods and systems that process well data from various sensors to generate higher order channels, such as rate of change of pressure values, to identify breakdown pressure, diverter events, and offset pressure responses, using heuristic approaches rather than complex machine learning techniques, allowing for more accurate and efficient analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis methods are used to process time-series data, then the analysis can be performed with simple tools, but the accuracy and completeness of identifying events and parameters are reduced
Solution Approach 1:
The patent introduces higher order channels as intermediary data structures that bridge the gap between raw time-series data and event identification. These channels compute derived metrics (rate of change, moving averages, statistical deviations) that serve as mediators to reveal hidden features and patterns not directly visible in the original data, thereby improving measurement precision without requiring complex machine learning systems.
Solution Approach 2:
The patent segments the data processing task into multiple stages: first computing higher order channels from raw data, then using these channels to identify specific events (breakdown pressure, diverter events, offset pressure responses). This segmentation allows the system to break down the complex analysis into manageable steps, improving accuracy while keeping each processing stage relatively simple.
2Productivity
If manual processing methods are used, then the system complexity is low, but the speed and consistency of data analysis are reduced
Solution Approach 1:
The system implements self-service through automated computation of higher order channels that continuously process time-series data without human intervention. The automated event identification algorithms scan through the computed channels to detect patterns and flag events, enabling the system to serve itself in analyzing data at high speed and with consistent criteria, thereby improving productivity while managing complexity through automation rather than human effort.
Solution Approach 2:
The patent applies preliminary action by pre-computing higher order channels (rate of change, moving averages, statistical metrics) before actual event identification occurs. This preliminary processing prepares the data in advance, allowing the subsequent event detection to proceed quickly and consistently by simply comparing against predefined criteria, thus improving analysis speed without proportionally increasing overall system complexity.
3Loss of information
If only native time-series channels are analyzed, then the processing is straightforward, but hidden features and higher order patterns are missed
Solution Approach 1:
The patent applies dimensionality change by transforming the one-dimensional time-series data into multiple dimensions through higher order channels. Instead of analyzing only the raw pressure values over time, the system creates additional dimensions representing rate of change, moving averages, and statistical deviations. This multi-dimensional view reveals hidden features and patterns that exist in different data dimensions, reducing information loss while keeping the processing approach systematic and manageable.
Data Source
AI summary
A well completion processing system to identify breakdown pressure, diverter events and offset pressure, in time sequenced fracture data, and use the identification of the same in the modification or adjustment of parameters associated with completion, as well as the display of information in a graphical form, such as an interface. In various examples, the processing system employs higher order channels in the processing of the same.