Dual-Thread Gated Recurrent Unit for Gear Remaining Useful Life Prediction

Bearing remaining useful life (RUL) prediction has always been a central topic in the industry field, which is aimed to optimize system safety and sustainability. The validity of the prediction model and the accuracy of the prediction results are affected by mid-term singularities and terminal mutations, under the time-domain bearing vibration information. In this paper, a network structure-Cascaded dilated convolution vision informer (CDC-Vii) is put forward to precisely forecast the RUL of bearings, which uses the time-frequency fault features as input. CDC-Vii breaks the limitation of the Original Informer which is only sensitive to time series information. An adaptive fault frequency band selection (AFFBS) algorithm is proposed, which can reduce training time while utilizing rich time-frequency information. Based on the Informer architecture, the attention mechanism is improved to form vision subsampling ProbSparse self-attention(VSPS). VSPS can precisely assign spatial attention weights and reduce computational complexity. At the same time, a truncated relative position encoding (TRPE) technique is proposed to strengthen the position dependence between attention information. Moreover, Cascaded dilated convolution (CDC) enhances the image contrast of faulty frequency bands while enlarging the use of receptive field. Experiments on extensively utilized two bearing datasets reveal that CDC-Vii surpasses the advanced RUL prediction models.

Section: Related Workmentioning

confidence: 99%

A vision subsampling probsparse self-attention-based informer for bearing remaining useful life prediction

Geng

Pan

et al. 2023

“…Accordingly, some RNN variants have been investigated for solving the above problems and further improving network performance [24][25][26], among which GRU has received widespread attention. Zhou et al [27] proposed a novel dual-thread GRU architecture to extract both static and non-static information from input data and capture the hidden state difference between two consecutive time steps. Nie and Xie [28] developed an innovative framework based on GRU for fault diagnosis of rotating machinery noise labels.…”

Section: Introductionmentioning

confidence: 99%

Multi-scale residual neural network with enhanced gated recurrent unit for fault diagnosis of rolling bearing

Liao,

Fu,

Yang

et al. 2024

As the key component of rotating machinery, effective and reliable fault diagnosis of rolling bearing is particularly critical for promoting production safety and economic benefits. The powerful representation learning ability of convolutional neural network (CNN) enables it to effectively extract fault information from vibration signals of rolling bearing. Nevertheless, challenges are faced by CNN in extracting features at multi-scale and capturing temporal features. With regard to this issue, a hybrid deep learning model that incorporates the multi-scale residual neural network (MSRN) with the enhanced gated recurrent unit (EGRU), namely MSRN-EGRU, is proposed in this paper. To begin with, MSRN is designed by introducing multi-scale structure and residual connections into CNN for extracting local features effectively and improving the feature representation of the model. Then, the extracted local features are input into EGRU to further extract temporal features, where EGRU is proposed by improving gated recurrent unit (GRU) structure and embeding scaled exponential liner unit (SELU), which enhances the nonlinear modeling and memory ability. Eventually, the obtained features are processed by α-Dropout and global average pooling (GAP) before being inputted into the softmax layer for fault diagnosis. To validate the effectiveness of the proposed model, three baseline models and two ablation models were employed for comparative experiments with two bearing datasets. The experimental results reveal that the proposed model achieves commendable performance in terms of accuracy, robustness, and convergence for fault diagnosis of rolling bearing.

“…The gated recurrent unit (GRU) modifies the network structure by adding different gating units to regulate the information transfer in the RNN. RNNs can learn dependencies across relatively long spans without gradient disappearance and gradient explosion [8,9]. Long short-term memory (LSTM) is proposed to enable the memory unit to selectively remember performance degradation data for various value amounts of information by defining various control unit functions [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Degradation trend feature generation improved rotating machines RUL prognosis method with limited run-to-failure data

Zhang

Liu

Zou

et al. 2023

The success of data-driven remaining useful life (RUL) prognosis approaches of rotating machines depends heavily on the abundance of entire life cycle data. However, it is difficult to obtain sufficient run-to-failure data in industrial practice. Data generation technology is a promising solution for enriching data but fails to address the intrinsic complexity of non-linear stage degradation and the time correlation of long-term data. This research proposes an RUL prognosis approach improved by the degradation trend feature generation variational autoencoder (DTVAE). First, this study develops a framework combining degradation trend generation features to resolve the issue of capturing the elements of time distribution for run-to-failure data. Second, a generation variational autoencoder network with a tendency block is proposed to create high-quality correlation features of time series data. Third, original and created degradation trend features are subjected to deep adaptive fusion and health indicator extraction. A bi-directional long short-term memory network is employed to predict the degradation trend and obtain the RUL prognosis. Finally, the proposed approach’s feasibility is confirmed by cross-validation experiments on a bearing dataset, which reduces the prediction error by 22.309%.