Abstract
In the era of big data, longer time series fault signals will not only be easy to copy and store, but also reduce the labor cost of manual labeling, which can better meet the needs of industrial big data. Aiming to effectively extract the key classification information from a longer time series of bearing vibration signals and achieve high diagnostic accuracy under noise and different load conditions. The one-dimensional adaptive long sequence convolutional network (ALSCN) is proposed. ALSCN can better extract features directly from high-dimensional original signals without manually extracting features and relying on expert knowledge. By adding two improved multi-scale modules, ALSCN can not only extract important features efficiently from noise signals, but also alleviate the problem of losing key information due to continuous down-sampling. Moreover, a Bayesian optimization algorithm is constructed to automatically find the best combination of hyperparameters in ALSCN. Based on two bearing data sets, the model is compared with traditional model such as SVM and deep learning models such as convolutional neural networks (CNN) et al. The results prove that ALSCN has a higher diagnostic accuracy rate on 5120-dimensional sequences under −5 signal to noise ratio (SNR) with better generalization.
Highlights
Rolling bearings are prevalent components in rotating machinery for modern industrial applications [1]
Gao proposed a gearbox bearing fault diagnosis method based on self-reference adaptive noise cancellation technology (SANC) and one-dimensional convolutional neural network (1D-convolutional neural networks (CNN)) [15]
The structure of the convolutional block consists of a convolutional layer, batch normalization (BN) and rectified linear unit (ReLU)
Summary
Introduction of of Thispaper paperproposes proposes a multi-scale module to reduce information loss in max. 4 × 4, 8 ×of8,4×4, and 8×8, 16 × and 16 are all,pooling the three poolingare branches are parallelized, and the max pooling of operations performed respectively to obtainto1/4, 1/8, and of the original feature doingBy this, 16×16 are performed respectively obtain. The various features of the original features by using the nearest neighbor interpolation method. Double upsampling pooling to get the feature vector pooling02 ∈ Rbatch_size× 4 ×d by using nearest neighbor linear interpolation. Four times upsampling pooling to get the feature vector pooling03 ∈ Rbatch_size× 4 ×d by using nearest neighbor linear interpolation. Merge features, perform ReLU d d activation and BN operations to obtain the output vector b0i ∈ Rbatch_size×m× 4 , i = 1, 2 .
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
