Hydraulic Simulation Event Detection for Real-Time Drilling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing drilling operations lack effective methods to predict the onset of negative events in real-time, such as hole cleaning, lost circulation, and bit wear, which can lead to significant operational disruptions and costly delays.

Innovation Solution

A system and method utilizing real-time data modeling and hydraulic simulations to analyze sensor data from downhole and surface sensors, applying event probability models to predict the likelihood and timing of drilling events, allowing for proactive adjustments to drilling parameters and fluid compositions to mitigate these events.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If real-time sensor data is collected and analyzed using event probability models, then the ability to predict drilling events is improved, but the system complexity increases

Engineering Contradiction:

Improveevent prediction accuracyVSAvoiddata processing system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the complex drilling operation monitoring into distinct event types (hole cleaning, lost circulation, bit wear, etc.), each with specific parameters and probability models. This allows the overall complex system to be divided into manageable modular components, where each event type is analyzed independently using tailored models and sensor subsets.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an event probability model as an intermediary layer between raw sensor data and drilling operation decisions. This intermediary processes sensor inputs through weighted calculations and hydraulic simulations to produce interpretable event probabilities and time-to-event estimates, simplifying the interface between data collection and operational response.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Difficulty of detecting and measuring

If hydraulic simulations and event probability models are applied to sensor data, then the detection capability of drilling issues is improved, but the computational requirements increase

Engineering Contradiction:

Improvedrilling event detection capabilityVSAvoidcomputational energy consumption

Core Design Contradiction:

Difficulty of detecting and measuringVSUse of energy by moving object

Solution Approach 1:

The system applies partial action by selecting and weighting only the most relevant parameters for each specific event type rather than processing all available sensor data equally. For example, hole cleaning detection focuses on cuttings concentration and flow rate parameters, while lost circulation detection emphasizes pressure and flow relationships, reducing unnecessary computational overhead.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent dynamically adjusts parameter weights and thresholds based on drilling conditions and event probabilities. The system modifies which parameters are monitored and how they are weighted according to the current drilling state, optimizing computational resources by focusing analysis on the most critical parameters for each situation rather than maintaining constant high-level monitoring of all parameters.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If weighted probability calculations with time trends are performed for each event parameter, then the precision of event timing prediction is improved, but the data processing time increases

Engineering Contradiction:

Improveevent timing prediction precisionVSAvoiddata processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary calculations by pre-establishing event probability models, parameter weightings, and hydraulic simulation frameworks before actual drilling events occur. These models are developed and validated in advance, allowing the real-time system to execute only the necessary data substitution and probability calculation steps when monitoring actual drilling operations, rather than building models from scratch during critical moments.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12435612B2Event detection using hydraulic simulations

Publication Date: 2025.10.07 HALLIBURTON ENERGY SERVICES INC

AI summary

Determining the likelihood of an event occurring during a drilling operation can utilize various input parameters collected from one or more sensors located downhole or at a surface location of the borehole undergoing the drilling operation. The collected input parameters can be weighted according to user parameters and then calculated over time to determine a trend in the input parameters. The trend can be analyzed against one or more probability models, such as using a machine learning process, to determine a potential for the event to occur and an estimated time interval over which the event may occur. The results of this analysis can be used by users or drilling systems to implement corrective actions to reduce or avoid the potential for the event occurring.