Stress Intensity Factors for Pressurized Pipes with an Internal Crack: The Prediction Model Based on an Artificial Neural Network
During pipeline operation, internal cracks may occur. The severity around the crack tip can be quantified by the stress intensity factor (<i>K</i><sub>I</sub>), which is a linear–elastic fracture mechanics parameter. For pressurized pipes featuring infinitely long internal su...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/20/11446 |
_version_ | 1797574830774550528 |
---|---|
author | Patchanida Seenuan Nitikorn Noraphaiphipaksa Chaosuan Kanchanomai |
author_facet | Patchanida Seenuan Nitikorn Noraphaiphipaksa Chaosuan Kanchanomai |
author_sort | Patchanida Seenuan |
collection | DOAJ |
description | During pipeline operation, internal cracks may occur. The severity around the crack tip can be quantified by the stress intensity factor (<i>K</i><sub>I</sub>), which is a linear–elastic fracture mechanics parameter. For pressurized pipes featuring infinitely long internal surface cracks, <i>K</i><sub>I</sub> can be interpolated from a function considering pressure, geometry, and crack size, as presented in API 579-1/ASME FFS-1. To enhance <i>K</i><sub>I</sub> prediction accuracy, an artificial neural network (ANN) model was developed for such pressurized pipes. Predictions from the ANN model and API 579-1/ASME FFS-1 were compared with precise finite element analysis (FEA). The ANN model with an eight-neuron sub-layer outperformed others, displaying the lowest mean squared error (MSE) and minimal validation discrepancies. Nonlinear validation data improved both MSE and testing performance compared to uniform validation. The ANN model accurately predicted normalized <i>K</i><sub>I</sub>, with differences of 2.2% or lower when compared to FEA results. Conversely, API 579-1/ASME FFS-1′s bilinear interpolation predicted inaccurately, exhibiting disparities of up to 4.3% within the linear zone and 24% within the nonlinearity zone. Additionally, the ANN model effectively forecasted the critical crack size (<i>a</i><sub>C</sub>), differing by 0.59% from FEA, while API 579-1/ASME FFS-1′s bilinear interpolation underestimated <i>a</i><sub>C</sub> by 4.13%. In summary, the developed ANN model offers accurate forecasts of normalized <i>K</i><sub>I</sub> and critical crack size for pressurized pipes, providing valuable insights for structural assessments in critical engineering applications. |
first_indexed | 2024-03-10T21:28:38Z |
format | Article |
id | doaj.art-b3cd9db9ff5041edba64cdb856949709 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T21:28:38Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-b3cd9db9ff5041edba64cdb8569497092023-11-19T15:32:18ZengMDPI AGApplied Sciences2076-34172023-10-0113201144610.3390/app132011446Stress Intensity Factors for Pressurized Pipes with an Internal Crack: The Prediction Model Based on an Artificial Neural NetworkPatchanida Seenuan0Nitikorn Noraphaiphipaksa1Chaosuan Kanchanomai2Department of Mechanical Engineering, Faculty of Engineering, Thammasat School of Engineering, Thammasat University, Pathumthani 12120, ThailandDepartment of Mechanical Engineering, Faculty of Engineering, Thammasat School of Engineering, Thammasat University, Pathumthani 12120, ThailandDepartment of Mechanical Engineering, Faculty of Engineering, Thammasat School of Engineering, Thammasat University, Pathumthani 12120, ThailandDuring pipeline operation, internal cracks may occur. The severity around the crack tip can be quantified by the stress intensity factor (<i>K</i><sub>I</sub>), which is a linear–elastic fracture mechanics parameter. For pressurized pipes featuring infinitely long internal surface cracks, <i>K</i><sub>I</sub> can be interpolated from a function considering pressure, geometry, and crack size, as presented in API 579-1/ASME FFS-1. To enhance <i>K</i><sub>I</sub> prediction accuracy, an artificial neural network (ANN) model was developed for such pressurized pipes. Predictions from the ANN model and API 579-1/ASME FFS-1 were compared with precise finite element analysis (FEA). The ANN model with an eight-neuron sub-layer outperformed others, displaying the lowest mean squared error (MSE) and minimal validation discrepancies. Nonlinear validation data improved both MSE and testing performance compared to uniform validation. The ANN model accurately predicted normalized <i>K</i><sub>I</sub>, with differences of 2.2% or lower when compared to FEA results. Conversely, API 579-1/ASME FFS-1′s bilinear interpolation predicted inaccurately, exhibiting disparities of up to 4.3% within the linear zone and 24% within the nonlinearity zone. Additionally, the ANN model effectively forecasted the critical crack size (<i>a</i><sub>C</sub>), differing by 0.59% from FEA, while API 579-1/ASME FFS-1′s bilinear interpolation underestimated <i>a</i><sub>C</sub> by 4.13%. In summary, the developed ANN model offers accurate forecasts of normalized <i>K</i><sub>I</sub> and critical crack size for pressurized pipes, providing valuable insights for structural assessments in critical engineering applications.https://www.mdpi.com/2076-3417/13/20/11446artificial intelligenceartificial neural networkstress intensity factorcrackpipe |
spellingShingle | Patchanida Seenuan Nitikorn Noraphaiphipaksa Chaosuan Kanchanomai Stress Intensity Factors for Pressurized Pipes with an Internal Crack: The Prediction Model Based on an Artificial Neural Network Applied Sciences artificial intelligence artificial neural network stress intensity factor crack pipe |
title | Stress Intensity Factors for Pressurized Pipes with an Internal Crack: The Prediction Model Based on an Artificial Neural Network |
title_full | Stress Intensity Factors for Pressurized Pipes with an Internal Crack: The Prediction Model Based on an Artificial Neural Network |
title_fullStr | Stress Intensity Factors for Pressurized Pipes with an Internal Crack: The Prediction Model Based on an Artificial Neural Network |
title_full_unstemmed | Stress Intensity Factors for Pressurized Pipes with an Internal Crack: The Prediction Model Based on an Artificial Neural Network |
title_short | Stress Intensity Factors for Pressurized Pipes with an Internal Crack: The Prediction Model Based on an Artificial Neural Network |
title_sort | stress intensity factors for pressurized pipes with an internal crack the prediction model based on an artificial neural network |
topic | artificial intelligence artificial neural network stress intensity factor crack pipe |
url | https://www.mdpi.com/2076-3417/13/20/11446 |
work_keys_str_mv | AT patchanidaseenuan stressintensityfactorsforpressurizedpipeswithaninternalcrackthepredictionmodelbasedonanartificialneuralnetwork AT nitikornnoraphaiphipaksa stressintensityfactorsforpressurizedpipeswithaninternalcrackthepredictionmodelbasedonanartificialneuralnetwork AT chaosuankanchanomai stressintensityfactorsforpressurizedpipeswithaninternalcrackthepredictionmodelbasedonanartificialneuralnetwork |