ANN Prediction Model of Concrete Fatigue Life Based on GRW-DBA Data Augmentation
In order to improve the prediction accuracy of the machine learning model for concrete fatigue life using small datasets, a group calculation and random weight dynamic time warping barycentric averaging (GRW-DBA) data augmentation method is proposed. First, 27 sets of real experimental data were aug...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/2/1227 |
_version_ | 1797446379315920896 |
---|---|
author | Jinna Shi Wenxiu Zhang Yanru Zhao |
author_facet | Jinna Shi Wenxiu Zhang Yanru Zhao |
author_sort | Jinna Shi |
collection | DOAJ |
description | In order to improve the prediction accuracy of the machine learning model for concrete fatigue life using small datasets, a group calculation and random weight dynamic time warping barycentric averaging (GRW-DBA) data augmentation method is proposed. First, 27 sets of real experimental data were augmented by 10 times, 20 times, 50 times, 100 times, 200 times, 500 times, and 1000 times, respectively, using the GRW-DBA method, and the optimal factor was determined by comparing the model’s training time and prediction accuracy under different augmentation multiples. Then, a concrete fatigue life prediction model was established based on artificial neural network (ANN), and the hyperparameters of the model were determined through experiments. Finally, comparisons were made with data augmentation methods such as generative adversarial network (GAN) and regression prediction models such as support vector machine (SVM), and the generalization of the method was verified using another fatigue life dataset collected on the Internet. The result shows that the GRW-DBA algorithm can significantly improve the prediction accuracy of the ANN model when using small datasets (the R<sup>2</sup> index increased by 20.1% compared with the blank control, reaching 98.6%), and this accuracy improvement is also verified in different data distributions. Finally, a graphical user interface is created based on the developed model to facilitate application in engineering. |
first_indexed | 2024-03-09T13:40:40Z |
format | Article |
id | doaj.art-be02dcc24c5e4035816d868595ca0eca |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T13:40:40Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-be02dcc24c5e4035816d868595ca0eca2023-11-30T21:07:59ZengMDPI AGApplied Sciences2076-34172023-01-01132122710.3390/app13021227ANN Prediction Model of Concrete Fatigue Life Based on GRW-DBA Data AugmentationJinna Shi0Wenxiu Zhang1Yanru Zhao2School of Civil Engineering, Inner Mongolia University of Technology, Hohhot 010051, ChinaSchool of Civil Engineering, Inner Mongolia University of Technology, Hohhot 010051, ChinaSchool of Civil Engineering, Inner Mongolia University of Technology, Hohhot 010051, ChinaIn order to improve the prediction accuracy of the machine learning model for concrete fatigue life using small datasets, a group calculation and random weight dynamic time warping barycentric averaging (GRW-DBA) data augmentation method is proposed. First, 27 sets of real experimental data were augmented by 10 times, 20 times, 50 times, 100 times, 200 times, 500 times, and 1000 times, respectively, using the GRW-DBA method, and the optimal factor was determined by comparing the model’s training time and prediction accuracy under different augmentation multiples. Then, a concrete fatigue life prediction model was established based on artificial neural network (ANN), and the hyperparameters of the model were determined through experiments. Finally, comparisons were made with data augmentation methods such as generative adversarial network (GAN) and regression prediction models such as support vector machine (SVM), and the generalization of the method was verified using another fatigue life dataset collected on the Internet. The result shows that the GRW-DBA algorithm can significantly improve the prediction accuracy of the ANN model when using small datasets (the R<sup>2</sup> index increased by 20.1% compared with the blank control, reaching 98.6%), and this accuracy improvement is also verified in different data distributions. Finally, a graphical user interface is created based on the developed model to facilitate application in engineering.https://www.mdpi.com/2076-3417/13/2/1227artificial neural networkdata augmentationfatigue lifepredictive modelsmall datasets |
spellingShingle | Jinna Shi Wenxiu Zhang Yanru Zhao ANN Prediction Model of Concrete Fatigue Life Based on GRW-DBA Data Augmentation Applied Sciences artificial neural network data augmentation fatigue life predictive model small datasets |
title | ANN Prediction Model of Concrete Fatigue Life Based on GRW-DBA Data Augmentation |
title_full | ANN Prediction Model of Concrete Fatigue Life Based on GRW-DBA Data Augmentation |
title_fullStr | ANN Prediction Model of Concrete Fatigue Life Based on GRW-DBA Data Augmentation |
title_full_unstemmed | ANN Prediction Model of Concrete Fatigue Life Based on GRW-DBA Data Augmentation |
title_short | ANN Prediction Model of Concrete Fatigue Life Based on GRW-DBA Data Augmentation |
title_sort | ann prediction model of concrete fatigue life based on grw dba data augmentation |
topic | artificial neural network data augmentation fatigue life predictive model small datasets |
url | https://www.mdpi.com/2076-3417/13/2/1227 |
work_keys_str_mv | AT jinnashi annpredictionmodelofconcretefatiguelifebasedongrwdbadataaugmentation AT wenxiuzhang annpredictionmodelofconcretefatiguelifebasedongrwdbadataaugmentation AT yanruzhao annpredictionmodelofconcretefatiguelifebasedongrwdbadataaugmentation |