Surrogate Model for Pipe Corrosion Rate Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing corrosion prediction models for pipelines, particularly those relying on computational fluid dynamics (CFD), face challenges due to high computational costs, making them inefficient for real-time applications and large design spaces.
Innovation Solution
A computer-implemented method using a surrogate model trained with data samples from physics-based simulations to estimate the maximum near-wall velocity in pipe sections, which is then fed into an electrochemical model to predict corrosion rates, thereby decoupling fluid flow simulation from electrochemical modeling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If physics-based CFD simulation is used for corrosion prediction, then measurement precision and reliability are improved, but productivity deteriorates due to high computational cost
Solution Approach 1:
The patent creates a surrogate model that copies the input-output behavior of the complex CFD-based corrosion model. Instead of running expensive CFD simulations for each prediction, the surrogate model (trained on CFD data) provides rapid predictions that replicate the accurate corrosion rate calculations, thus achieving both speed and accuracy.
Solution Approach 2:
The patent performs preliminary CFD simulations to generate training data for the surrogate model. By pre-computing corrosion rates for various input conditions and storing these results in a training dataset, the system prepares advance knowledge that enables fast predictions without requiring real-time CFD computations.
2Adaptability or versatility
If CFD-based modeling is applied to cover broad corrosion scenarios, then adaptability is improved, but use of energy worsens due to high computational requirements
Solution Approach 1:
The system pre-computes corrosion rates for a comprehensive range of conditions using CFD simulations and stores these results in a training dataset. This preliminary action covers broad corrosion scenarios in advance, enabling the surrogate model to handle diverse inputs without requiring expensive real-time CFD computations.
Solution Approach 2:
The surrogate model learns to copy the complex CFD-based corrosion prediction behavior across multiple scenarios. By training on diverse CFD simulation data representing different corrosion conditions, the model achieves broad adaptability while consuming minimal energy during actual predictions.
Data Source
AI summary
A computer-implemented approach has been developed to estimate corrosion rate (100) in a section of a pipe transmitting a corrosive substance. A trained surrogate model (60) is provided to output an estimated value of maximum near-wall velocity (70) of the substance in the pipe section. The estimated value of maximum near-wall velocity (70) is then fed into a computerized electrochemical model (80), together with electrochemical parameters (90) associated with the corrosive substance, which electrochemical model then determines an estimated corrosion rate (100) imposed on the pipe section by the corrosive substance. The surrogate model is trained using results of a full physics-based simulation. Once it has been trained, the surrogate model can generate the estimated value of maximum near-wall velocity (70) much faster than the full physics-based simulation can.