Drilling Operation Anomaly Detection With Activity-Based Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional drilling anomaly systems suffer from low interpretability, lack of real-time anomaly identification, and subjective review of drilling parameters, leading to inaccurate and delayed detection of operational anomalies in subterranean drilling processes.
Innovation Solution
A feature extraction model is used to partition time-series drilling data into activities like pre-connection, connection, and rotary drilling, extracting features such as maximum velocity and acceleration, and determining anomalies based on a probability density function and an adjustable threshold, providing real-time anomaly detection and visualizations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional key performance indicators or aggregate measures are used to measure drilling operation processes, then the system can provide overall performance metrics, but the interpretability and ability to provide constructive feedback for improvement is reduced
Solution Approach 1:
The patent segments drilling operations into distinct activity types (e.g., drilling, tripping, connecting) and analyzes each segment separately using activity-specific parameters. This segmentation allows the system to provide precise anomaly detection for each operation type while maintaining manageable complexity through modular analysis approaches.
Solution Approach 2:
The system dynamically changes parameters based on the identified activity type. Different parameters are monitored and evaluated according to the specific drilling activity being performed, allowing precise measurement tailored to each operation phase while keeping the overall system structure flexible and adaptable.
2Loss of time
If conventional systems aggregate drilling operation data over time for review, then comprehensive historical analysis is possible, but real-time anomaly identification capability is lost
Solution Approach 1:
The system dynamically adapts its analysis in real-time by continuously identifying the current activity type and adjusting monitoring parameters accordingly. This dynamic approach enables real-time anomaly detection with precision tailored to each specific drilling activity, rather than using static aggregate thresholds.
Solution Approach 2:
The system provides immediate feedback by continuously monitoring drilling parameters in real-time and alerting operators to anomalies as they occur. This real-time feedback loop maintains measurement precision by evaluating parameters against activity-specific norms rather than historical aggregates, enabling timely corrective actions.
3Ease of operation
If manual selective review of drilling parameters is conducted by field personnel, then subjective judgment can be applied, but accuracy is reduced due to inability to capture complex interplay of variables
Solution Approach 1:
The system acts as an intermediary between raw drilling data and operator decision-making. It automatically processes complex parameter interrelationships and activity classifications, presenting simplified anomaly information to operators. This maintains ease of operation while dramatically improving accuracy by removing human cognitive limitations in analyzing complex variable interactions.
4Loss of information
If conventional systems use average or statistical values for key performance indicators, then aggregate performance can be measured, but the values become too vague or complex for field personnel to interpret and develop improvement plans
Solution Approach 1:
The system segments performance data by activity type and presents segmented metrics rather than overall averages. This segmentation makes information more interpretable by showing performance in the context of specific drilling activities, enabling operators to identify and address efficiency issues in particular operation phases.
Solution Approach 2:
The system changes the form of presented information based on activity type, displaying parameter values and anomalies in activity-specific contexts. This adaptive presentation maintains information interpretability by showing relevant parameters in meaningful contexts while supporting productivity improvements through actionable, context-specific insights.
Data Source
AI summary
The present disclosure relates to systems, methods, and non-transitory computer-readable media for dynamically utilizing, in potentially real time, anomaly pattern detection to optimize operational processes relating to well construction or subterranean drilling. For example, the disclosed systems use time-series data combined with rig states to automatically detect and split similar operations. Subsequently, the disclosed systems identify operation anomalies from a field-data collection utilizing an automated anomaly detection workflow. The automated anomaly detection workflow can identify operation anomalies at a more granular level by determining which process behavior contributes to the operation anomaly (e.g., according to corresponding process probabilities for a given operation). In addition, the disclosed systems can present graphical representations of operation anomalies, process behaviors (procedural curves), and/or corresponding process probabilities in an intuitive, user-friendly manner.