Learning Machine Predicts Subsurface Safety Valve Closure
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Subsurface safety valves (SCSSVs) in wells can automatically close due to unsafe conditions, leading to well shut-ins and significant production delays when restarting production.
Innovation Solution
Implementing a learning machine that predicts SCSSV closures by analyzing sensor data from the well, such as flow rates, pressures, and temperatures, to notify operators and prevent unnecessary shut-ins.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If SCSSV automatically closes based on well conditions, then well safety is improved, but production continuity deteriorates
Solution Approach 1:
The learning machine performs preliminary analysis of sensor data to predict SCSSV closure events before they occur. By identifying patterns in flow rate, pressure, and temperature data that precede automatic closures, the system enables operators to take preventive actions (such as adjusting well conditions) to avoid unnecessary shut-ins, thus maintaining production continuity while preserving safety functionality.
2Reliability
If SCSSV closes in response to unsafe conditions, then safety protection is improved, but production time is lost
Solution Approach 1:
The system implements a feedback loop where the learning machine continuously monitors sensor data, compares it against learned patterns, and provides predictions to operators. This feedback enables timely intervention to prevent false closures while ensuring that genuine safety threats are addressed, thereby minimizing unnecessary production time loss while maintaining safety protection.
3Loss of time
If learning machine predicts SCSSV closure, then production delays are reduced, but system complexity increases
Solution Approach 1:
The learning machine acts as an intermediary layer between the existing SCSSV control system and operators. It processes sensor data and provides predictions without directly controlling the valve, thereby reducing production delays through early warning while adding only moderate complexity through a software-based prediction system rather than complex hardware modifications.
Data Source
AI summary
Some implementations include a method for predicting closure of a subsurface safety valve (SCSSV) configured to shut-in a well without any sensors on the SCSSV. The method may include obtaining, by a learning machine, sensor readings indicating downhole conditions in the well. The method may include predicting, by the learning machine, closure of the SCSSV based on the sensor readings indicating downhole conditions in the well. The method may include transmitting a communication predicting closure of the SCSSV.