Image deep learning in fault diagnosis of mechanical equipment

Wang, Chuanhao; Sun, Yongjian; Wang, Xiaohong

doi:10.1007/s10845-023-02176-3

Cited by 8 publications

(2 citation statements)

References 138 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model-based methods demand prior knowledge to establish mathematical models and are mainly used for image restoration, deblurring, and super-resolution reconstruction [21]. Deep learning image enhancement techniques require training with a large amount of image data, enabling them to learn image features and handle complex images [22,23]. Methods based on deep learning mainly include Convolutional Neural Networks [24], Generative Adversarial Networks [25], Autoencoders [26], and Deep Residual Networks [27].…”

Section: Introductionmentioning

confidence: 99%

Bearing fault diagnosis based on the feature enhancement of improved mean differential SDP images★

Wang,

Sun

2024

Eng. Res. Express

Self Cite

View full text Add to dashboard Cite

In the fault diagnosis of mechanical equipment, vibrational signals often contain noise. In order to solve the problem of rolling bearing fault diagnosis under the influence of noise, an image enhancement method based on mean difference images is proposed. Convert one-dimensional time series into two-dimensional image data by using the symmetrized dot pattern method. The data are processed and grouped by variational mode decomposition to obtain a mean image with stable features. A feature enhancement method based on improved mean difference images is used to achieve data mining of fault features. The improved Canberra distance is used as the classification basis to realize the accurate classification of rolling bearing faults. Finally, the classification effect of the method is verified by experiments. The experimental results show that the image enhancement method proposed in this paper can improve fault features in the image and has a good anti-noise ability.

show abstract

Section: Introductionmentioning

confidence: 99%

Bearing fault diagnosis based on the feature enhancement of improved mean differential SDP images★

Wang,

Sun

2024

Eng. Res. Express

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine vision offers notable advantages in diagnosing faults of special equipment [5,6]. With the help of deep learning and image processing technology, detecting and diagnosing equipment faults quickly and accurately is achieved by utilizing images and video.…”

Section: Introductionmentioning

confidence: 99%

An Improved Method for Detecting Crane Wheel–Rail Faults Based on YOLOv8 and the Swin Transformer

Li,

Tang,

Liu

et al. 2024

Sensors

View full text Add to dashboard Cite

In the realm of special equipment, significant advancements have been achieved in fault detection. Nonetheless, faults originating in the equipment manifest with diverse morphological characteristics and varying scales. Certain faults necessitate the extrapolation from global information owing to their occurrence in localized areas. Simultaneously, the intricacies of the inspection area’s background easily interfere with the intelligent detection processes. Hence, a refined YOLOv8 algorithm leveraging the Swin Transformer is proposed, tailored for detecting faults in special equipment. The Swin Transformer serves as the foundational network of the YOLOv8 framework, amplifying its capability to concentrate on comprehensive features during the feature extraction, crucial for fault analysis. A multi-head self-attention mechanism regulated by a sliding window is utilized to expand the observation window’s scope. Moreover, an asymptotic feature pyramid network is introduced to augment spatial feature extraction for smaller targets. Within this network architecture, adjacent low-level features are merged, while high-level features are gradually integrated into the fusion process. This prevents loss or degradation of feature information during transmission and interaction, enabling accurate localization of smaller targets. Drawing from wheel–rail faults of lifting equipment as an illustration, the proposed method is employed to diagnose an expanded fault dataset generated through transfer learning. Experimental findings substantiate that the proposed method in adeptly addressing numerous challenges encountered in the intelligent fault detection of special equipment. Moreover, it outperforms mainstream target detection models, achieving real-time detection capabilities.

show abstract

Dual prototypical contrastive network: a novel self-supervised method for cross-domain few-shot fault diagnosis

Zhang,

Huang,

Wang

et al. 2023

J Intell Manuf

View full text Add to dashboard Cite

Image deep learning in fault diagnosis of mechanical equipment

Cited by 8 publications

References 138 publications

Bearing fault diagnosis based on the feature enhancement of improved mean differential SDP images★

Bearing fault diagnosis based on the feature enhancement of improved mean differential SDP images★

An Improved Method for Detecting Crane Wheel–Rail Faults Based on YOLOv8 and the Swin Transformer

Dual prototypical contrastive network: a novel self-supervised method for cross-domain few-shot fault diagnosis

Contact Info

Product

Resources

About