Storage Tank Volume Prediction for Low-Downtime Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for calibrating petroleum storage tanks are inefficient, costly, and prone to inaccuracies due to infrequent calibrations, which can lead to financial losses and safety risks, while current techniques require extensive downtime and are susceptible to errors from inaccurate laser positioning.
Innovation Solution
A machine learning-based predictive model that utilizes historical data and current operating parameters to estimate volumetric and structural changes in tanks, reducing the need for manual measurements and optimizing calibration frequency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional calibration methods (manual strapping, optical techniques) are used, then calibration accuracy can be achieved, but the process requires extensive tank downtime and is time-consuming (one to two days)
Solution Approach 1:
The patent replaces mechanical calibration methods (manual strapping, physical laser devices) with an acoustic wave-based system. Acoustic waves propagate through the tank to measure volume changes, eliminating the need for physical access to the tank interior and reducing calibration time from one to two days to a much shorter duration, while maintaining measurement precision.
Solution Approach 2:
The patent introduces acoustic waves as an intermediary medium to measure tank volume changes. Instead of directly measuring physical dimensions with lasers or tapes, the system uses acoustic wave travel time through the liquid to infer volume, providing a non-invasive method that minimizes tank downtime while achieving accurate calibration.
2Productivity
If laser-based calibration techniques are used to allow more frequent calibration, then calibration frequency increases, but the system is susceptible to errors from inaccurate positioning of laser devices
Solution Approach 1:
The patent replaces laser-based optical systems with acoustic wave-based measurement. Acoustic waves are less sensitive to positioning errors compared to laser devices, allowing for more frequent calibration operations without sacrificing measurement precision. The acoustic method provides robust measurements even with minor variations in sensor placement.
3Productivity
If calibration is performed infrequently to reduce downtime and costs, then operational continuity is maintained, but volume measurement accuracy deteriorates due to tank expansion
Solution Approach 1:
The patent enables periodic calibration at optimized intervals by using acoustic wave measurement. The system can perform quick acoustic measurements to detect tank expansion, allowing operators to schedule calibration only when necessary based on actual volume changes, thereby maintaining both operational continuity and measurement accuracy.
Solution Approach 2:
The patent implements a feedback mechanism where acoustic measurements continuously monitor tank volume changes. When the measured volume deviation exceeds a threshold, the system triggers a calibration event, creating a closed-loop system that maintains accuracy without requiring fixed-schedule calibrations, thus preserving operational continuity while ensuring measurement precision.
4Loss of information
If manual calibration procedures are used, then comprehensive volume data can be collected, but the extensive procedure leads to financial losses due to accumulated volume measurement errors
Solution Approach 1:
The patent replaces manual calibration procedures with automated acoustic wave-based measurement. The system automatically collects comprehensive volume data at multiple heights by analyzing acoustic travel times, eliminating manual data collection while preventing the accumulation of volume measurement errors that lead to financial losses in custody transfer operations.
Data Source
AI summary
Systems and methods are provided for predictive volumetric and structural evaluation of petroleum product containers. The system includes a computing device in communication with data input devices and implementation tools including calibration devices for measuring tank volume among other physical parameters bearing on tank volume. The computing device receives sets of historical physical parameter data for a plurality of tanks and, using machine learning (ML), generates predictive ML models for estimating volumetric parameters of tanks. The predictive model is applied by the system to historical and current data values to estimate current volumetric parameters for a given tank and, based on the results, the system performs or coordinates further operations for the given tank using an implementation tool. The further operations can include inventory management, physical calibration, maintenance and inspection as well as system evaluation and control operations.