Similarity-based probabilistic remaining useful life estimation for an aeroengine under variable operational conditions

Self Cite

This paper focuses on the anomaly detection for ionospheric total electron content (TEC) before earthquakes. In this paper, a novel unsupervised approach is proposed. First, interval-based method is employed to granulate the TEC series. Justiﬁable granularity principle is utilized to construct interval information granules (IGs) for representing TEC series. Second, high-order diﬀerence method is introduced to construct rectangle IGs and cube IGs for obtaining the new representation of TEC. Third, corresponding similarity measurement method is designed to calculate the anomaly score of each IG, which is the evaluation criterion for detecting the anomalies. Finally, experimental results using real TEC datasets validate the eﬀectiveness of the proposed approach. Compared with the existing major approaches, because the proposed approach can capture more morphological details and variation trend of TEC series, it can achieve a higher detection accuracy.

Section: Introductionmentioning

confidence: 99%

RETRACTED: An unsupervised anomaly detection approach for pre-seismic ionospheric total electron content

Wen¹,

Peng²,

Huang³

et al. 2023

Self Cite

“…To compare the performance of our proposed approach with current SOTA methods under the same criteria, two common metrics, root mean square error (RMSE) and Score, are utilized as performance indicator. The formulas of calculating RMSE and Score are described as follows [36,37]:…”

Section: Evaluation Metricsmentioning

confidence: 99%

DRLSTM-DA: a novel aeroengine remaining useful life prediction method based on deep optimization of multiple sensors information

Suo,

Fu,

Lin

et al. 2024

One of the crucial tasks in Remaining useful life prediction is to effectively extract key sensor information from numerous sensor signals. In this article, a novel dual-attention enhanced deep residual LSTM (DRLSTM-DA) is developed to deeply optimize multidimensional sensor signals. First, two LSTM layers are designed to compress and reconstruct representative degradation information from input multidimensional time series data, to generate a new feature space. Second, a novel channel adaptive soft threshold module is designed to assign different weights according to the importance of different sensor information, and simultaneously eliminate the noise information in the signal. Thirdly, a temporal attention mechanism is designed to automatically highlight moments containing important decay information while suppressing unimportant moments. Finally, compared with other SOTA methods, our architecture achieves RMSE of 11.55, 13.74, 11.25, and 14.19 on four sub-datasets of the C-MAPSS dataset, with scores of 234.24, 465.49, 202.23, and 537.66, respectively. Meanwhile, in real aeroengine operation dataset, our architecture achieved the smallest RMSE (8.62). These results all validate the good predictive performance of our model.

“…Yu et al [3] first utilized a bidirectional RNN-based autoencoder to obtain the low dimensional embedding which can represent the degradation state of the machine. Additionally, Wang et al [11,12] designed an unsupervised deep autoencoder to fuse multiple nonlinear sensor data and utilized the first-dimensional data output as the health indicators. Wei et al [13] developed a multiautoencoder and Gaussian mixture regression-based prediction scheme to obtain a syncretic HI which can adaptively extract indirect health indicators and solve the issue of redundancy and inadequacy.…”

Section: Introductionmentioning

confidence: 99%

A similarity-based remaining useful life prediction method using multimodal degradation features and adjusted cosine similarity

Kong

Zeng

et al. 2023

When a large amount of full life-cycle data are available, similarity-based methods are the preferred method for remaining useful life (RUL) prediction due to their reliability and accuracy. Traditional similarity-based RUL prediction methods use a single model and single-scale degradation features, which are incapable of fully capturing the degradation behavior of the system. Additionally, the similarity of spatial orientation is neglected in the similarity-matching process. To fill these research gaps, a novel method is developed based on multimodal degradation features and adjusted cosine similarity to tackle complex-system remaining useful life prediction in this paper. Complete ensemble empirical mode decomposition with adaptive noise is employed to decouple global degradation and random fluctuations in run-to-failure sensor data. Slow feature analysis is utilized to obtain local degradation features, and residual terms are used as global degradation features. Then, multimodal degradation features are transformed into one-dimensional health degradation indicators by bidirectional gated recurrent unit autoencoder. An adjusted cosine similarity is developed to estimate the matching similarity between the test degradation curve and the training degradation curve. The proposed scheme captures the time-varying multimodal degradation behavior which eliminates the effects of random fluctuations while retaining important degradation differences information. The designed scheme is evaluated on the C-MAPSS dataset and the results illustrate the competitiveness and effectiveness of the proposed method.