TTSNet: Transformer–Temporal Convolutional Network–Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft Engines
Accurately predicting the remaining useful life (RUL) is crucial for ensuring the safety and reliability of aircraft engine operation. However, aircraft engines operate in harsh conditions, with the characteristics of high speed, high temperature, and high load, resulting in high-dimensional and noi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/2/432 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587473885069312 |
|---|---|
| author | Zhaofei Li Shilin Luo Haiqing Liu Chaobin Tang Jianguo Miao |
| author_facet | Zhaofei Li Shilin Luo Haiqing Liu Chaobin Tang Jianguo Miao |
| author_sort | Zhaofei Li |
| collection | DOAJ |
| description | Accurately predicting the remaining useful life (RUL) is crucial for ensuring the safety and reliability of aircraft engine operation. However, aircraft engines operate in harsh conditions, with the characteristics of high speed, high temperature, and high load, resulting in high-dimensional and noisy data. This makes feature extraction inadequate, leading to low accuracy in the prediction of the RUL of aircraft engines. To address this issue, Transformer-TCN-Self-attention network (TTSNet) with feature fusion, as a parallel three-branch network, is proposed for predicting the RUL of aircraft engines. The model first applies exponential smoothing to smooth the data and suppress noise to the original signal, followed by normalization. Then, it uses a parallel transformer encoder, temporal convolutional network (TCN), and multi-head attention three-branch network to capture both global and local features of the time series. The model further completes feature dimension weight allocation and fusion through a multi-head self-attention mechanism, emphasizing the contribution of different features to the model. Subsequently, it fuses the three parts of features through a linear layer and concatenation. Finally, a fully connected layer is used to establish the mapping relationship between the feature matrix and the RUL label, obtaining the RUL prediction value. The model was validated on the C-MAPSS aircraft engine dataset. Experimental results show that compared to other related RUL models, the RMSE and Score reached 11.02 and 194.6 on dataset FD001, respectively; on dataset FD002, the RMSE and Score reached 13.25 and 874.1, respectively. On dataset FD003, the RMSE and Score reached 11.06 and 200.1 and on dataset FD004, the RMSE and Score reached 18.26 and 1968.5, respectively, demonstrating better performance of RUL prediction. |
| format | Article |
| id | doaj-art-025e2347577f40579b8017de870d4c39 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-025e2347577f40579b8017de870d4c392025-01-24T13:48:54ZengMDPI AGSensors1424-82202025-01-0125243210.3390/s25020432TTSNet: Transformer–Temporal Convolutional Network–Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft EnginesZhaofei Li0Shilin Luo1Haiqing Liu2Chaobin Tang3Jianguo Miao4School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, ChinaSchool of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, ChinaSchool of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, ChinaSchool of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, ChinaKey Laboratory of Artificial Intelligence of Sichuan Province, Yibin 644000, ChinaAccurately predicting the remaining useful life (RUL) is crucial for ensuring the safety and reliability of aircraft engine operation. However, aircraft engines operate in harsh conditions, with the characteristics of high speed, high temperature, and high load, resulting in high-dimensional and noisy data. This makes feature extraction inadequate, leading to low accuracy in the prediction of the RUL of aircraft engines. To address this issue, Transformer-TCN-Self-attention network (TTSNet) with feature fusion, as a parallel three-branch network, is proposed for predicting the RUL of aircraft engines. The model first applies exponential smoothing to smooth the data and suppress noise to the original signal, followed by normalization. Then, it uses a parallel transformer encoder, temporal convolutional network (TCN), and multi-head attention three-branch network to capture both global and local features of the time series. The model further completes feature dimension weight allocation and fusion through a multi-head self-attention mechanism, emphasizing the contribution of different features to the model. Subsequently, it fuses the three parts of features through a linear layer and concatenation. Finally, a fully connected layer is used to establish the mapping relationship between the feature matrix and the RUL label, obtaining the RUL prediction value. The model was validated on the C-MAPSS aircraft engine dataset. Experimental results show that compared to other related RUL models, the RMSE and Score reached 11.02 and 194.6 on dataset FD001, respectively; on dataset FD002, the RMSE and Score reached 13.25 and 874.1, respectively. On dataset FD003, the RMSE and Score reached 11.06 and 200.1 and on dataset FD004, the RMSE and Score reached 18.26 and 1968.5, respectively, demonstrating better performance of RUL prediction.https://www.mdpi.com/1424-8220/25/2/432TCNtransformerself-attentionaircraft enginesRUL prediction |
| spellingShingle | Zhaofei Li Shilin Luo Haiqing Liu Chaobin Tang Jianguo Miao TTSNet: Transformer–Temporal Convolutional Network–Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft Engines Sensors TCN transformer self-attention aircraft engines RUL prediction |
| title | TTSNet: Transformer–Temporal Convolutional Network–Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft Engines |
| title_full | TTSNet: Transformer–Temporal Convolutional Network–Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft Engines |
| title_fullStr | TTSNet: Transformer–Temporal Convolutional Network–Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft Engines |
| title_full_unstemmed | TTSNet: Transformer–Temporal Convolutional Network–Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft Engines |
| title_short | TTSNet: Transformer–Temporal Convolutional Network–Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft Engines |
| title_sort | ttsnet transformer temporal convolutional network self attention with feature fusion for prediction of remaining useful life of aircraft engines |
| topic | TCN transformer self-attention aircraft engines RUL prediction |
| url | https://www.mdpi.com/1424-8220/25/2/432 |
| work_keys_str_mv | AT zhaofeili ttsnettransformertemporalconvolutionalnetworkselfattentionwithfeaturefusionforpredictionofremainingusefullifeofaircraftengines AT shilinluo ttsnettransformertemporalconvolutionalnetworkselfattentionwithfeaturefusionforpredictionofremainingusefullifeofaircraftengines AT haiqingliu ttsnettransformertemporalconvolutionalnetworkselfattentionwithfeaturefusionforpredictionofremainingusefullifeofaircraftengines AT chaobintang ttsnettransformertemporalconvolutionalnetworkselfattentionwithfeaturefusionforpredictionofremainingusefullifeofaircraftengines AT jianguomiao ttsnettransformertemporalconvolutionalnetworkselfattentionwithfeaturefusionforpredictionofremainingusefullifeofaircraftengines |