Long-range Dependencies Learning Based on Non-Local 1D-Convolutional Neural Network for Rolling Bearing Fault Diagnosis

Abstract

In the field of data-driven bearing fault diagnosis, convolutional neural network (CNN) has been widely researched and applied due to its superior feature extraction and classification ability. However, the convolutional operation could only process a local neighborhood at a time and thus lack ability of capturing long-range dependencies. Therefore, building an efficient learning method for long-range dependencies is crucial to comprehend and express signal features considering that the vibration signals obtained in a real industrial environment always have strong instability, periodicity, and temporal correlation. This paper introduces non-local mean to the CNN and presents 1D non-local block (1D-NLB) to extract long-range dependencies. The 1D-NLB computes the response at a position as a weighted average value of the features at all positions. Based on it, we propose a non-local 1D convolutional neural network (NL-1DCNN) aiming at rolling bearing fault diagnosis. Furthermore, the 1D-NLB could be simply plugged into most existing deep learning architecture to improve their fault diagnosis ability. Under multiple noise conditions, the 1D-NLB improves the performance of the CNN on the wheelset bearing dataset of high-speed train and the Case Western Reserve University bearing dataset. The experiment results show that the NL-1DCNN exhibits superior results compared with six state-of-the-art fault diagnosis methods.

Coupling Dilated Encoder–Decoder Network for Multi-Channel Airborne LiDAR Bathymetry Full-Waveform Denoising

“…Since sea-surface and seabed signals are not fixed in each frame signal, the denoising effect of ALB signals is limited. The seabed topography is complicated and easily affected by impulse noise, so it is necessary to introduce a nonlocal [39] processing module or use multi-frame features to alleviate the problem of the model falling into the local optimal solution.…”

Attention mechanism guided sparse filtering for mechanical intelligent fault diagnosis under variable speed condition

“…In this way, statistical information on the whole image can be obtained, which is very common in previous feature learning [20]. In this paper, the global average pool technique is adopted to aggregate local descriptors.…”

Data Augmentation and Intelligent Fault Diagnosis of Planetary Gearbox Using ILoFGAN Under Extremely Limited Samples

“…Thanks to the rapid development of data-driven technology, many researchers have investigated intelligent fault diagnosis of planetary gearbox by mining the rich information provided by the collected vibration signals. Particularly, fault diagnosis based on deep learning has attracted more attention than traditional data-driven technology, due to its end-to-end feature learning ability [5][6][7]. However, the success of deep learning largely depends on the sufficiency of training samples.…”