A deep bi-directional long short-term memory model for automatic rotating speed extraction from raw vibration signals

Rao, Meng; Li, Qing; Wei, Dongdong; Zuo, Ming J.

doi:10.1016/j.measurement.2020.107719

Cited by 23 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared the proposed MLKDCE-PBiLSTM with five advanced methods. They are a DCAE network with five-layer convolutional network [ 15 ], BiLSTM network [ 24 ], LSTM with multiple CNN [ 23 ], MSCNN [ 40 ], LeNet-5 with a new convolutional neural network proposed by Wen [ 41 ]. The six methods adopt the same training strategies in the overall experiments.…”

Section: Performance Verificationmentioning

confidence: 99%

“…An et al [ 23 ] utilized CNN-based LSTM for fault feature extraction of the bearing under time-varying working conditions. Rao et al [ 24 ] utilized convolutional BiLSTM to accurately realize fault diagnosis of rotating machinery. The abovementioned studies proved that DCE and BiLSTM have better diagnostic results than the normal machine learning networks in the fault diagnosis of rotating machinery.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multilocation and Multiscale Learning Framework with Skip Connection for Fault Diagnosis of Bearing under Complex Working Conditions

Ban

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

Considering various fault states under severe working conditions, the comprehensive feature extraction from the raw vibration signal is still a challenge for the diagnosis task of rolling bearing. To deal with strong coupling and high nonlinearity of the vibration signal, this article proposes a novel multilocation and multikernel scale learning network based on deep convolution encoder (DCE) and bidirectional short-term memory network (BiLSTM). The former multifeature learning network of this article proposed combines the skip connection and the DCE network. The network can automatically extract and fuse global and local features from different network depth and time scales of the raw vibration signal. Then, the former network as the input of the latter network is fed into the feature protection layer for further mining sensitive and complementary features. Consequently, the proposed network scheme can perform well in generalization capability. The performance of the proposed method is verified on the two kinds of bearing datasets. The diagnostic results demonstrate that the proposed method can diagnose multiple fault types more accurately. Also, the method performs better in load and speed adaptation compared with other intelligent fault classification methods.

show abstract

Section: Performance Verificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multilocation and Multiscale Learning Framework with Skip Connection for Fault Diagnosis of Bearing under Complex Working Conditions

Ban

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…2020, 10, 2477 of 14 only difference is that masked fraction is set to 0.5 (this parameter in SAE is setting to 0) to denoise. The sigmoid function [26] is selected as active function for the BPNN, DAE, and DBN, the optimizing search algorithms for adjusting the parameters of those neural networks is the traditional gradient descent [27]. Meanwhile, both DBN and DAE directly handle the raw signals, whereas the signal is without statistical filter and stepwise diagnosis.…”

Section: Comparative Experimentsmentioning

confidence: 99%

Stepwise Intelligent Diagnosis Method for Rotor System with Sliding Bearing Based on Statistical Filter and Stacked Auto-Encoder

et al. 2020

View full text Add to dashboard Cite

Since the raw signal collected from the sliding bearing is contaminated with background noise, and it is difficult to obtain high-precision results for the traditional methods due to the low signal-to-noise ratio (SNR). Therefore, a stepwise intelligent diagnosis method based on statistical filter and stacked auto-encoder (SAE) that is established with several auto-encoders is proposed to identify several faults of sliding bearing in a rotor system. Firstly, the statistical filter is utilized to reduce the interference information for the different abnormal states and to increase the SNR. Secondly, the stepwise intelligent diagnosis based on SAE is performed to learn the useful fault features, and it can automatically complete the fault diagnosis which is contributed with the superiority binary classification to fully mine the relationship between the fault characteristics and the health condition of bearing. Finally, the diagnosis of the oil whirl and structural faults in a rotor system is cited as an example to demonstrate the effectiveness of proposed method. It can effectively illustrate the advantages of the stepwise diagnosis method to obtain the maximum diagnostic accuracy.

show abstract

“…Time-frequency domain analysis combined with vibration imaging and feature extraction with CNN, are also used for gearbox and rotor fault diagnosis [21]. LSTM based algorithms are also used in regression problems or as virtual sensing applications for identifying specific parameters such as turbine engine vibration [22] or rotation speed of a fixed shaft gearbox [23].…”

Section: Introductionmentioning

confidence: 99%

“…In conclusion, even though the existing literature demonstrates the successful use of DL in condition monitoring and diagnosis, most of these studies are based on classification problems, where the goal is to predict a categorical value, especially for bearing related faults. The existing models rarely focus on regression or parameter identification with a few exceptions such as [23] and [22]. There is a need for developing intelligent models to automatically identify support parameters and evaluate how the on-site support affects the behavior of a rotating machine.…”

Section: Introductionmentioning

confidence: 99%

Simulation-Based Transfer Learning for Support Stiffness Identification

et al. 2021

View full text Add to dashboard Cite

The mounting of a rotating machine affects the dynamic behavior of the machine. Typically in large machines, the support structures have lower stiffness on the actual site than in the acceptance tests conducted by the manufacturers. In this research, a method is developed for the support stiffness identification for an in-situ machine using a simulation-data-driven, deep learning algorithm. The novel approach aims to utilize transfer learning to first teach the deep learning algorithm using vibration response data generated from a simulation model of the rotor-bearing-support system, and then test it with measured response. To validate the stiffness estimation of the algorithm for multiple cases, an experimental test rig is used where the horizontal support stiffness can be varied through a range of values. The results from the deep learning algorithm are compared with simpler algorithms such as Linear regression (LR), Artificial Neural Network (ANN), and Support vector regression (SVR) for benchmarking. The models are trained with filtered frequency domain response, and challenges due to measurement uncertainty are analyzed. With proposed pre-processing steps of the frequency domain response and outlier elimination, the deep learningbased virtual sensor can predict the support stiffness with reasonable accuracy, where the limiting factor is the data quality and lack of excitation at critical speed frequencies.

show abstract

A deep bi-directional long short-term memory model for automatic rotating speed extraction from raw vibration signals

Cited by 23 publications

References 23 publications

Multilocation and Multiscale Learning Framework with Skip Connection for Fault Diagnosis of Bearing under Complex Working Conditions

Multilocation and Multiscale Learning Framework with Skip Connection for Fault Diagnosis of Bearing under Complex Working Conditions

Stepwise Intelligent Diagnosis Method for Rotor System with Sliding Bearing Based on Statistical Filter and Stacked Auto-Encoder

Simulation-Based Transfer Learning for Support Stiffness Identification

Contact Info

Product

Resources

About