Long-Term Structural State Trend Forecasting Based on an FFT–Informer Model
Machine learning has been widely applied in structural health monitoring. While most existing methods, which are limited to forecasting structural state evolution of large infrastructures. forecast the structural state in a step-by-step manner, extracting feature of structural state trends and the n...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/4/2553 |
| _version_ | 1797622472680407040 |
|---|---|
| author | Jihao Ma Jingpei Dan |
| author_facet | Jihao Ma Jingpei Dan |
| author_sort | Jihao Ma |
| collection | DOAJ |
| description | Machine learning has been widely applied in structural health monitoring. While most existing methods, which are limited to forecasting structural state evolution of large infrastructures. forecast the structural state in a step-by-step manner, extracting feature of structural state trends and the negative effects of data collection under abnormal conditions are big challenges. To address these issues, a long-term structural state trend forecasting method based on long sequence time-series forecasting (LSTF) with an improved Informer model integrated with Fast Fourier transform (FFT) is proposed, named the FFT–Informer model. In this method, by using FFT, structural state trend features are represented by extracting amplitude and phase of a certain period of data sequence. Structural state trend, a long sequence, can be forecasted in a one-forward operation by the Informer model that can achieve high inference speed and accuracy of prediction based on the Transformer model. Furthermore, a Hampel filter that filters the abnormal deviation of the data sequence is integrated into the Multi-head ProbSparse self-attention in the Informer model to improve forecasting accuracy by reducing the effect of abnormal data points. Experimental results on two classical data sets show that the FFT–Informer model achieves high and stable accuracy and outperforms the comparative models in forecasting accuracy. It indicates that this model can effectively forecast the long-term state trend change of a structure and is proposed to be applied to structural state trend forecasting and early damage warning. |
| first_indexed | 2024-03-11T09:11:45Z |
| format | Article |
| id | doaj.art-297d2914b7d84d258cdd0061a1926fab |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T09:11:45Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-297d2914b7d84d258cdd0061a1926fab2023-11-16T18:57:24ZengMDPI AGApplied Sciences2076-34172023-02-01134255310.3390/app13042553Long-Term Structural State Trend Forecasting Based on an FFT–Informer ModelJihao Ma0Jingpei Dan1College of Computer Science, Chongqing University, Chongqing 400044, ChinaCollege of Computer Science, Chongqing University, Chongqing 400044, ChinaMachine learning has been widely applied in structural health monitoring. While most existing methods, which are limited to forecasting structural state evolution of large infrastructures. forecast the structural state in a step-by-step manner, extracting feature of structural state trends and the negative effects of data collection under abnormal conditions are big challenges. To address these issues, a long-term structural state trend forecasting method based on long sequence time-series forecasting (LSTF) with an improved Informer model integrated with Fast Fourier transform (FFT) is proposed, named the FFT–Informer model. In this method, by using FFT, structural state trend features are represented by extracting amplitude and phase of a certain period of data sequence. Structural state trend, a long sequence, can be forecasted in a one-forward operation by the Informer model that can achieve high inference speed and accuracy of prediction based on the Transformer model. Furthermore, a Hampel filter that filters the abnormal deviation of the data sequence is integrated into the Multi-head ProbSparse self-attention in the Informer model to improve forecasting accuracy by reducing the effect of abnormal data points. Experimental results on two classical data sets show that the FFT–Informer model achieves high and stable accuracy and outperforms the comparative models in forecasting accuracy. It indicates that this model can effectively forecast the long-term state trend change of a structure and is proposed to be applied to structural state trend forecasting and early damage warning.https://www.mdpi.com/2076-3417/13/4/2553structural health monitoringtime series forecastingFFTInformer modelFFT–Informer |
| spellingShingle | Jihao Ma Jingpei Dan Long-Term Structural State Trend Forecasting Based on an FFT–Informer Model Applied Sciences structural health monitoring time series forecasting FFT Informer model FFT–Informer |
| title | Long-Term Structural State Trend Forecasting Based on an FFT–Informer Model |
| title_full | Long-Term Structural State Trend Forecasting Based on an FFT–Informer Model |
| title_fullStr | Long-Term Structural State Trend Forecasting Based on an FFT–Informer Model |
| title_full_unstemmed | Long-Term Structural State Trend Forecasting Based on an FFT–Informer Model |
| title_short | Long-Term Structural State Trend Forecasting Based on an FFT–Informer Model |
| title_sort | long term structural state trend forecasting based on an fft informer model |
| topic | structural health monitoring time series forecasting FFT Informer model FFT–Informer |
| url | https://www.mdpi.com/2076-3417/13/4/2553 |
| work_keys_str_mv | AT jihaoma longtermstructuralstatetrendforecastingbasedonanfftinformermodel AT jingpeidan longtermstructuralstatetrendforecastingbasedonanfftinformermodel |