Decomposition-Aware Framework for Probabilistic and Flexible Time Series Forecasting in Aerospace Electronic Systems
Degradation prediction for aerospace electronic systems plays a crucial role in maintenance work. This paper proposes a concise and efficient framework for multivariate time series forecasting that is capable of handling diverse sequence representations through a Channel-Independent (CI) strategy. T...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/2/262 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588087048273920 |
|---|---|
| author | Yuanhong Mao Xin Hu Yulang Xu Yilin Zhang Yunan Li Zixiang Lu Qiguang Miao |
| author_facet | Yuanhong Mao Xin Hu Yulang Xu Yilin Zhang Yunan Li Zixiang Lu Qiguang Miao |
| author_sort | Yuanhong Mao |
| collection | DOAJ |
| description | Degradation prediction for aerospace electronic systems plays a crucial role in maintenance work. This paper proposes a concise and efficient framework for multivariate time series forecasting that is capable of handling diverse sequence representations through a Channel-Independent (CI) strategy. This framework integrates a decomposition-aware layer to effectively separate and fuse global trends and local variations and a temporal attention module to capture temporal dependencies dynamically. This design enables the model to process multiple distinct sequences independently while maintaining the flexibility to learn shared patterns across channels. Additionally, the framework incorporates probabilistic distribution forecasting using likelihood functions, addressing the dynamic variations and uncertainty in time series data. The experimental results on multiple real-world datasets validate the framework’s effectiveness, demonstrating its robustness and adaptability in handling diverse sequences across various application scenarios. |
| format | Article |
| id | doaj-art-c114207935f942f6ab35c9082af28abb |
| institution | Kabale University |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-c114207935f942f6ab35c9082af28abb2025-01-24T13:39:56ZengMDPI AGMathematics2227-73902025-01-0113226210.3390/math13020262Decomposition-Aware Framework for Probabilistic and Flexible Time Series Forecasting in Aerospace Electronic SystemsYuanhong Mao0Xin Hu1Yulang Xu2Yilin Zhang3Yunan Li4Zixiang Lu5Qiguang Miao6Xi’an Microelectronics Technology Institute, Xi’an 710065, ChinaSchool of Computer Science and Technology, Xidian University, Xi’an 710071, ChinaSchool of Computer Science and Technology, Xidian University, Xi’an 710071, ChinaSchool of Computer Science and Technology, Xidian University, Xi’an 710071, ChinaSchool of Computer Science and Technology, Xidian University, Xi’an 710071, ChinaSchool of Computer Science and Technology, Xidian University, Xi’an 710071, ChinaSchool of Computer Science and Technology, Xidian University, Xi’an 710071, ChinaDegradation prediction for aerospace electronic systems plays a crucial role in maintenance work. This paper proposes a concise and efficient framework for multivariate time series forecasting that is capable of handling diverse sequence representations through a Channel-Independent (CI) strategy. This framework integrates a decomposition-aware layer to effectively separate and fuse global trends and local variations and a temporal attention module to capture temporal dependencies dynamically. This design enables the model to process multiple distinct sequences independently while maintaining the flexibility to learn shared patterns across channels. Additionally, the framework incorporates probabilistic distribution forecasting using likelihood functions, addressing the dynamic variations and uncertainty in time series data. The experimental results on multiple real-world datasets validate the framework’s effectiveness, demonstrating its robustness and adaptability in handling diverse sequences across various application scenarios.https://www.mdpi.com/2227-7390/13/2/262multivariate time series forecastingdecomposition-aware layerchannel-independent strategyprobabilistic distribution forecasting |
| spellingShingle | Yuanhong Mao Xin Hu Yulang Xu Yilin Zhang Yunan Li Zixiang Lu Qiguang Miao Decomposition-Aware Framework for Probabilistic and Flexible Time Series Forecasting in Aerospace Electronic Systems Mathematics multivariate time series forecasting decomposition-aware layer channel-independent strategy probabilistic distribution forecasting |
| title | Decomposition-Aware Framework for Probabilistic and Flexible Time Series Forecasting in Aerospace Electronic Systems |
| title_full | Decomposition-Aware Framework for Probabilistic and Flexible Time Series Forecasting in Aerospace Electronic Systems |
| title_fullStr | Decomposition-Aware Framework for Probabilistic and Flexible Time Series Forecasting in Aerospace Electronic Systems |
| title_full_unstemmed | Decomposition-Aware Framework for Probabilistic and Flexible Time Series Forecasting in Aerospace Electronic Systems |
| title_short | Decomposition-Aware Framework for Probabilistic and Flexible Time Series Forecasting in Aerospace Electronic Systems |
| title_sort | decomposition aware framework for probabilistic and flexible time series forecasting in aerospace electronic systems |
| topic | multivariate time series forecasting decomposition-aware layer channel-independent strategy probabilistic distribution forecasting |
| url | https://www.mdpi.com/2227-7390/13/2/262 |
| work_keys_str_mv | AT yuanhongmao decompositionawareframeworkforprobabilisticandflexibletimeseriesforecastinginaerospaceelectronicsystems AT xinhu decompositionawareframeworkforprobabilisticandflexibletimeseriesforecastinginaerospaceelectronicsystems AT yulangxu decompositionawareframeworkforprobabilisticandflexibletimeseriesforecastinginaerospaceelectronicsystems AT yilinzhang decompositionawareframeworkforprobabilisticandflexibletimeseriesforecastinginaerospaceelectronicsystems AT yunanli decompositionawareframeworkforprobabilisticandflexibletimeseriesforecastinginaerospaceelectronicsystems AT zixianglu decompositionawareframeworkforprobabilisticandflexibletimeseriesforecastinginaerospaceelectronicsystems AT qiguangmiao decompositionawareframeworkforprobabilisticandflexibletimeseriesforecastinginaerospaceelectronicsystems |