Sage Journals: Discover world-class research

Abstract

The air turbine starter (ATS) is a critical device for starting aircraft engines, in which rolling bearings play a core role. Predicting the remaining useful life (RUL) of rolling bearings is challenged by complex dependencies. Feature extraction, as a crucial step for RUL prediction, reveals the operational state of the bearings. To comprehensively extract the operational characteristics of rolling bearings, this paper introduces the multi-scale adaptive dual forecast (MADF) model. First, the model employs a multi-scale adaptive router to dynamically select optimal patch scales. Subsequently, these scales are used to segment the data into different temporal slices. For each scale, the model applies a dual forecast block to capture global and local temporal dependencies. Finally, a multi-scale aggregator integrates information across different bearing scales, further refining the multi-scale modeling process to predict the RUL. The experimental results demonstrate that the proposed method achieves reductions in mean absolute error (MAE) by 15.76%, 24.79%, 33.08%, 39.83%, and 49.15%; root mean square error (RMSE) by 16.01%, 29.64%, 29.97%, 38.72%, and 47.92%; and score by 21.01%, 34.52%, 41.29%, 43.61%, and 47.52% compared to the multi-resolution time-series transformer (MTST), patch time-series transformer (PatchTST), TimesNet, Scaleformer, and convolutional neural network (CNN) models, respectively. The effectiveness of the proposed method is validated through experimental data from the RUL prediction of civil aircraft-bearing components, showcasing its ability to achieve high-precision predictions of bearing RUL.

Keywords

Remaining useful life bearing patch multi-scale adaptive

Get full access to this article

View all access options for this article.

References

Ferreira

Gonçalves

(2022) Remaining useful life prediction and challenges: A literature review on the use of machine learning methods. Journal of Energy Chemistry 63: 550–562.

Guo

(2023) Remaining useful life prediction for bearing of an air turbine starter using a novel end-to-end network. Measurement Science and Technology 34(6): 065109.

Guo

Huang

(2024) Operation stage division and RUL prediction of bearings based on 1DCNN-ON-LSTM. Measurement Science and Technology 35(2): 025035.

Luo

(2024a) Remaining useful life prediction and uncertainty quantification for bearings based on cascaded multiscale convolutional neural network. IEEE Transactions on Instrumentation and Measurement 73: 1–13.

Kong

Jin

(2024b) Remaining useful life prediction of radioisotope thermoelectric generator using a component-level mechanism-based nonlinear additive Wiener process. IEEE Transactions on Instrumentation and Measurement 73: 1–14.

Huang

Liu

(2024) FL-Net: A multi-scale cross-decomposition network with frequency external attention for long-term time series forecasting. Knowledge-Based Systems 288: 111473.

Jiang

Shi

Sheng

(2024) Lightweight CNN architecture design for rolling bearing fault diagnosis. Measurement Science and Technology 35(12): 126142.

Kim

Tae

(2022) Reversible instance normalization for accurate time-series forecasting against distribution shift. In: International conference on learning representations Virtual conference, 25–29 April.

Byg

(2023) The development of machine learning-based remaining useful life prediction for lithium-ion batteries. Journal of Energy Chemistry 82: 103–121.

10.

Liu

Liao

(2022) Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. In: International conference on learning representations, Virtual conference, 25–29 April.

11.

Dan

(2023) Long-term structural state trend forecasting based on an FFT–informer model. Applied Sciences 13(4): 2553.

12.

Nie

Nguyen

Sinthong

(2023) A time series is worth 64 words: Long-term forecasting with transformers. In: International conference on learning representations, Kigali, Rwanda, 1–5 May.

13.

Nimri

Wang

Zhang

(2023) Data-driven approaches and model-based methods for detecting and locating leaks in water distribution systems: A literature review. Neural Computing and Applications 35(16): 11611–11623.

14.

Peng

Jiang

Mao

(2023) Local enhancing transformer with temporal convolutional attention mechanism for bearings remaining useful life prediction. IEEE Transactions on Instrumentation and Measurement 72: 1–12.

15.

Sanghyun

Jongchan

Joon-Young

(2018) CBAM: Convolutional block attention module. In: Proceedings of the 15th European conference on computer vision, Munich, 8–14 September, pp. 3–19. Cham: Springer.

16.

Shabani

Abdi

Meng

(2023) Scaleformer: Iterative multi-scale refining transformers for time series forecasting. In: International conference on learning representations, Kigali, Rwanda, 1–5 May.

17.

Waghumbare

Singh

Kasera

(2024) DIAT-DSCNN-ECA-Net: Separable convolutional neural network-based classification of galaxy morphology. Astrophysics and Space Science 369(4): 38.

18.

Liu

(2023a) Timesnet: Temporal 2d-variation modeling for general time series analysis. In: International conference on learning representations, Kigali, Rwanda, 1–5 May.

19.

Wang

(2021) Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. In: Proceedings of the 35th international conference on neural information processing systems, Red Hook, NY, 6–14 December.

20.

(2023b) Remaining useful life prediction via a data-driven deep learning fusion model-CALAP. IEEE Access 11: 112085–112096.

21.

Xue

Yang

(2023) An improved generic hybrid prognostic method for RUL prediction based on PF-LSTM learning. IEEE Transactions on Instrumentation and Measurement 72: 1–21.

22.

Yin

Shen

Wang

(2024) Remaining useful life prediction of lithium-ion batteries based on DBO-CNN-DSformer. Electrochimica Acta 508: 145123.

23.

Ying

(2024) TFEformer: Temporal feature enhanced transformer for multivariate time series forecasting. IEEE Access 12: 153694–153708.

24.

Zhang

Fang

(2023) A review of remaining useful life prediction approaches for mechanical equipment. IEEE Sensors Journal 23(24): 29991–30006.

25.

Zhang

Pal

(2024) Multi-resolution time-series transformer for long-term forecasting. In: Proceedings of the 27th International conference on artificial intelligence and statistics, Valencia, 2–4 May.

26.

Zheng

Zhou

(2024) A remaining useful life prediction method of rolling bearings based on deep reinforcement learning. IEEE Internet of Things Journal 11(13): 22938–22949.

27.

Zhou

Wen

(2022) FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. In: Proceedings of the 39th International conference on machine learning, Baltimore, MD, 17–23 July.

A multi-scale adaptive dual forecast model applied to remaining useful life prediction of air turbine starter bearing

Abstract

Keywords

Get full access to this article

References