Predictive Drilling Reports Using Active and Historic Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional drilling operations lack predictive capabilities, relying on reactionary decision-making due to a lack of concise and accessible future forecasting in drilling reports, leading to inefficiencies and lost time.
Innovation Solution
Implementing a system that uses active and historic data from similar wells to generate predictive drilling reports through machine-learning models, comparing time series datasets and key drilling factors to forecast future drilling conditions and potential issues, enabling proactive risk mitigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional drilling reports are generated using manual and automated processes to summarize previous drilling activity, then a summary of past performance is provided, but the reports include little or no information on future drilling conditions, leading to reactionary decision-making and lost time
Solution Approach 1:
The system performs preliminary analysis by comparing active drilling data with historical data from similar wells to predict future drilling conditions before they occur. This allows drilling teams to prepare in advance for potential issues such as stuck pipe, losses, or wellbore instability, rather than reacting after problems arise. The predictive reporting generates forecasts of future drilling parameters and potential complications, enabling proactive decision-making and preparation of mitigation strategies ahead of time.
2Reliability
If predictive drilling reports are generated by comparing active drilling data with extensive historical data from multiple reference wells, then actionable insights into future events are provided, but the data processing and analysis complexity increases
Solution Approach 1:
The system creates simplified representations of complex drilling scenarios by generating predictive reports that copy the structure and format of conventional drilling reports, but populate them with predicted future values instead of past data. This allows the complex predictive analytics to be presented in a familiar, easy-to-understand format that mirrors standard industry reporting, reducing the perceived complexity for users while maintaining the power of sophisticated data comparison across multiple reference wells.
Solution Approach 2:
The system introduces an intermediary predictive reporting layer between raw historical data and decision-makers. Instead of requiring users to directly analyze complex datasets from multiple reference wells, the intermediary system processes this data through comparative analysis and presents synthesized predictions in an accessible format. This intermediary layer handles the complexity of data integration, normalization, and comparison across different wells and conditions, shielding users from the underlying computational complexity while delivering actionable insights.
Data Source
AI summary
A method comprises receiving active data of a number of time series datasets for different attributes of an active drilling operation of an active well, for a previous time period having a defined length of time and retrieving historic data, that corresponds to the active data, of the number of attributes for offset drilling operations of a number of selected reference wells. The method includes selecting a subset of the historic data that satisfies a relevancy threshold based on relevancy to the active data, wherein the selecting is based on similarities between the number of time series datasets in the active data and the historic data. The method includes creating a predictive composite logging, for a future time period, that includes a number of predictive times series datasets for at least a portion of the different attributes based on the selected subset of the historic data.