Steel Pipe Collapse Strength Prediction With Pipe-Making Strain
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting the collapse strength of steel pipes, such as those used in submarine pipelines, fail to accurately consider the pipe-making strain during forming, leading to inaccurate predictions and potential safety risks due to underestimated or overestimated collapse resistance.
Innovation Solution
A machine learning-based method using neural networks to generate a steel pipe collapse strength prediction model that incorporates steel pipe shape, strength characteristics, and pipe-making strain, enabling precise prediction of collapse strength post-forming.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional prediction methods (NPL 1) are used that only consider steel pipe shape and strength characteristics after forming, then the prediction process is simple, but the prediction accuracy of collapse strength is insufficient
Solution Approach 1:
The patent applies preliminary action by collecting and storing pipe-making strain data during the forming process before collapse strength prediction is performed. The machine learning model is trained in advance using historical data that includes forming conditions, intermediate measurement data, and actual collapse strength results. This preliminary preparation of data and model training enables accurate prediction without requiring complex real-time measurements during the actual prediction phase.
Solution Approach 2:
The patent introduces an intermediary machine learning model that bridges the gap between simple input parameters (pipe shape, strength characteristics) and the complex output (collapse strength). The model acts as a mediator that processes the relationship between forming conditions, material properties, and final collapse strength, translating simple measurements into accurate predictions without requiring direct complex physical modeling.
2Measurement precision
If pipe-making strain during forming is not considered, then the evaluation process is straightforward, but the predicted collapse strength does not match actual measured values
Solution Approach 1:
The patent captures pipe-making strain information during the forming process as intermediate data before final prediction. By recording forming conditions and strain data in advance, the system preserves critical information that would otherwise be lost. This preliminary data collection ensures that when prediction is performed, the full history of forming conditions is available to the machine learning model, eliminating information loss while maintaining process simplicity.
3Reliability
If accurate prediction of collapse strength is achieved by considering pipe-making strain, then safety and performance are improved, but the prediction model becomes more complex
Solution Approach 1:
The patent replaces complex mechanical analysis and physical testing systems with a machine learning-based prediction model. Instead of requiring elaborate experimental setups or complex theoretical calculations to assess anti-collapse performance, the system uses trained machine learning models that process forming data and material properties to predict collapse strength with high accuracy. This substitution maintains reliability while reducing the complexity of the actual prediction implementation.
Solution Approach 2:
The patent creates a virtual copy of the steel pipe's forming history and material characteristics through data representation in the machine learning model. By copying and processing the essential features of pipe-making strain, shape, and strength characteristics in a digital format, the system achieves accurate reliability assessment without requiring physical prototypes or complex experimental apparatus, thereby reducing implementation complexity while maintaining high reliability.
Data Source
AI summary
A steel pipe collapse strength prediction model generation method, a steel pipe collapse strength prediction method, a steel pipe manufacturing characteristics determination method, and a steel pipe manufacturing method capable of highly accurately predicting the collapse strength of a steel pipe after forming or a coated steel pipe in consideration of the pipe-making strain during forming. Into a steel pipe collapse strength prediction model generated by the prediction model generation method, steel pipe manufacturing characteristics including the shape of a steel pipe to be predicted after forming, strength characteristics, and the pipe-making strain are input to predict the collapse strength after forming. Into a steel pipe collapse strength prediction model, steel pipe manufacturing characteristics including the shape of a coated steel pipe to be predicted after forming, strength characteristics, the pipe-making strain, and coating conditions are input to predict the collapse strength of the coated steel pipe.