HIC Growth Prediction for Pipelines Using Surrogate Expert Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting hydrogen-induced crack (HIC) growth rate in metal pipelines are inefficient and unreliable, requiring excessive computing resources, leading to impractical field deployments and lack of standard methods for determining remaining lifetime of HIC-affected equipment.
Innovation Solution
A dynamic expert system is developed to predict HIC growth rate using a simulated observation database, reducing CPU and memory requirements by employing a surrogate model that replicates mechanistic models with lower resource usage, allowing for field-deployable and self-improving predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If advanced ultrasonic testing techniques are used to monitor HIC damage, then measurement precision is improved, but device complexity and cost increase significantly
Solution Approach 1:
The patent creates a virtual copy of the physical inspection system through digital twins and simulation models. Instead of requiring multiple physical advanced ultrasonic testing devices, the system uses computational models that replicate the inspection process, reducing hardware complexity while maintaining detection precision through virtual testing and analysis.
2Measurement precision
If complete advanced ultrasonic testing mapping is performed on whole pressure vessels or pipelines, then measurement precision is improved, but loss of time and computing resources increase excessively
Solution Approach 1:
The patent divides the inspection process into discrete segments or zones, allowing selective testing of high-risk areas rather than complete mapping of entire vessels or pipelines. The system segments the structure into regions requiring different levels of inspection intensity, reducing overall computing time and resource consumption while maintaining precision where it matters most.
Solution Approach 2:
The patent applies partial action by performing advanced ultrasonic testing only on critical regions or suspected HIC damage zones rather than complete mapping of entire structures. The system identifies and focuses computational resources on areas with highest probability of HIC damage, achieving sufficient measurement precision without the excessive time and resource costs of comprehensive mapping.
3Ease of operation
If historical-based techniques are used manually for HIC assessment, then ease of operation is maintained, but productivity is significantly reduced
Solution Approach 1:
The patent implements self-service through automated inspection systems that perform HIC damage assessment without requiring manual expert intervention for each measurement. The system automatically collects ultrasonic data, processes signals, identifies HIC damage, and generates reports, maintaining operational simplicity while dramatically increasing productivity through automation of repetitive inspection tasks.
Solution Approach 2:
The patent replaces manual mechanical inspection processes with automated electronic and computational systems. Instead of manual ultrasonic testing and interpretation, the system uses automated data acquisition, digital signal processing, and algorithmic analysis to assess HIC damage, preserving ease of operation through user-friendly interfaces while increasing productivity through automated high-throughput inspection capabilities.
4Reliability
If standard FFS assessment methods are used, then reliability of safety assessment is improved, but loss of time in determining remaining lifetime increases
Solution Approach 1:
The patent applies preliminary action by pre-calculating HIC growth rate curves and remaining lifetime predictions during the inspection process itself, rather than performing time-consuming separate analysis. The system pre-computes degradation models and projects future damage progression based on current measurements, providing reliable FFS assessments with accelerated timing by performing necessary calculations upfront during the inspection window.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods and systems of predicting the growth rate of hydrogen-induced cracking (HIC) in a physical asset (e.g., a pipeline, storage tank, etc.) are provided. The methodology receives a plurality of inputs regarding physical characteristics of the asset and performs parametric simulations to generate a simulated database of observations of the asset. The database is then used to train, test, and validate one or more expert systems that can then predict the growth rate and other characteristics of the asset over time. The systems herein can also generate alerts as to predicted dangerous conditions and modify inspection schedules based on such growth rate predictions.