Long-Term Prediction of Crack Growth Using Deep Recurrent Neural Networks and Nonlinear Regression: A Comparison Study
Cracks in a building can potentially result in financial and life losses. Thus, it is essential to predict when the crack growth is reaching a certain threshold, to prevent possible disaster. However, long-term prediction of the crack growth in newly built facilities or existing facilities with rece...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/20/10514 |
| _version_ | 1797475583776522240 |
|---|---|
| author | Salahuddin Muhammad Iqbal Jun-Ryeol Park Kyu-Il Jung Jun-Seoung Lee Dae-Ki Kang |
| author_facet | Salahuddin Muhammad Iqbal Jun-Ryeol Park Kyu-Il Jung Jun-Seoung Lee Dae-Ki Kang |
| author_sort | Salahuddin Muhammad Iqbal |
| collection | DOAJ |
| description | Cracks in a building can potentially result in financial and life losses. Thus, it is essential to predict when the crack growth is reaching a certain threshold, to prevent possible disaster. However, long-term prediction of the crack growth in newly built facilities or existing facilities with recently installed sensors is challenging because only the short-term crack sensor data are usually available in the aforementioned facilities. In contrast, we need to obtain equivalently long or longer crack sensor data to make an accurate long-term prediction. Against this background, this research aims to make a reasonable long-term estimation of crack growth within facilities that have crack sensor data with limited length. We show that deep recurrent neural networks such as LSTM suffer when the prediction’s interval is longer than the observed data points. We also observe a limitation of simple linear regression if there are abrupt changes in a dataset. We conclude that segmented nonlinear regression is suitable for this problem because of its advantage in splitting the data series into multiple segments, with the premise that there are sudden transitions in data. |
| first_indexed | 2024-03-09T20:46:13Z |
| format | Article |
| id | doaj.art-f42543ea96db48adaf27f803892733d8 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T20:46:13Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f42543ea96db48adaf27f803892733d82023-11-23T22:45:51ZengMDPI AGApplied Sciences2076-34172022-10-0112201051410.3390/app122010514Long-Term Prediction of Crack Growth Using Deep Recurrent Neural Networks and Nonlinear Regression: A Comparison StudySalahuddin Muhammad Iqbal0Jun-Ryeol Park1Kyu-Il Jung2Jun-Seoung Lee3Dae-Ki Kang4Department of Computer Engineering, Dongseo University, Busan 47011, KoreaBuzzni AI Lab., Seoul 08788, KoreaJCMEEK, Seoul 07591, KoreaInfranics Research Lab., Seoul 06640, KoreaDepartment of Computer Engineering, Dongseo University, Busan 47011, KoreaCracks in a building can potentially result in financial and life losses. Thus, it is essential to predict when the crack growth is reaching a certain threshold, to prevent possible disaster. However, long-term prediction of the crack growth in newly built facilities or existing facilities with recently installed sensors is challenging because only the short-term crack sensor data are usually available in the aforementioned facilities. In contrast, we need to obtain equivalently long or longer crack sensor data to make an accurate long-term prediction. Against this background, this research aims to make a reasonable long-term estimation of crack growth within facilities that have crack sensor data with limited length. We show that deep recurrent neural networks such as LSTM suffer when the prediction’s interval is longer than the observed data points. We also observe a limitation of simple linear regression if there are abrupt changes in a dataset. We conclude that segmented nonlinear regression is suitable for this problem because of its advantage in splitting the data series into multiple segments, with the premise that there are sudden transitions in data.https://www.mdpi.com/2076-3417/12/20/10514deep recurrent neural networksLSTMSeq2Seq LSTMsegmented nonlinear regressionlong-term predictioncrack growth |
| spellingShingle | Salahuddin Muhammad Iqbal Jun-Ryeol Park Kyu-Il Jung Jun-Seoung Lee Dae-Ki Kang Long-Term Prediction of Crack Growth Using Deep Recurrent Neural Networks and Nonlinear Regression: A Comparison Study Applied Sciences deep recurrent neural networks LSTM Seq2Seq LSTM segmented nonlinear regression long-term prediction crack growth |
| title | Long-Term Prediction of Crack Growth Using Deep Recurrent Neural Networks and Nonlinear Regression: A Comparison Study |
| title_full | Long-Term Prediction of Crack Growth Using Deep Recurrent Neural Networks and Nonlinear Regression: A Comparison Study |
| title_fullStr | Long-Term Prediction of Crack Growth Using Deep Recurrent Neural Networks and Nonlinear Regression: A Comparison Study |
| title_full_unstemmed | Long-Term Prediction of Crack Growth Using Deep Recurrent Neural Networks and Nonlinear Regression: A Comparison Study |
| title_short | Long-Term Prediction of Crack Growth Using Deep Recurrent Neural Networks and Nonlinear Regression: A Comparison Study |
| title_sort | long term prediction of crack growth using deep recurrent neural networks and nonlinear regression a comparison study |
| topic | deep recurrent neural networks LSTM Seq2Seq LSTM segmented nonlinear regression long-term prediction crack growth |
| url | https://www.mdpi.com/2076-3417/12/20/10514 |
| work_keys_str_mv | AT salahuddinmuhammadiqbal longtermpredictionofcrackgrowthusingdeeprecurrentneuralnetworksandnonlinearregressionacomparisonstudy AT junryeolpark longtermpredictionofcrackgrowthusingdeeprecurrentneuralnetworksandnonlinearregressionacomparisonstudy AT kyuiljung longtermpredictionofcrackgrowthusingdeeprecurrentneuralnetworksandnonlinearregressionacomparisonstudy AT junseounglee longtermpredictionofcrackgrowthusingdeeprecurrentneuralnetworksandnonlinearregressionacomparisonstudy AT daekikang longtermpredictionofcrackgrowthusingdeeprecurrentneuralnetworksandnonlinearregressionacomparisonstudy |