WP-DRnet: A novel wear particle detection and recognition network for automatic ferrograph image analysis

Peng, Yeping; Cai, Junhao; Wu, Tingting; Cao, Guang-Zhong; Kwok, Ngaiming; Peng, Zhongxiao

doi:10.1016/j.triboint.2020.106379

Cited by 48 publications

(19 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method proposed by Peng and Wang (2019) does not require particle segmentation, which can automatically separate overlapped wear particles and extract features. Peng et al (2020) have developed a wear-particle detection and recognition (WP-DR) network for classification of wear particles of fatigue, cutting, severe sliding and spherical wear particles using support vector machine. Class_Center Vectors and Distance Comparison CNN (CDCNN) model has been developed by Zhang et al (2020) based on class center vector.…”

Section: Introductionmentioning

confidence: 99%

Wear particles recognition through teachable machine

More¹,

Jaybhaye²

2022

ILT

View full text Add to dashboard Cite

Purpose The purpose of this paper is to adapt teachable machine as a web-based tool for recognition of wear pattern and type of wear by training a convolutional neural network (CNN) model. This helps to monitor the health of the lubricated system as a part of condition monitoring. Design/methodology/approach Ferrography technique is used for analysis of wear particles. It helps monitor the condition of lubricated mechanical system. In present paper, CNN model is developed for identifying the type of wear particles coming out of Gearbox system using teachable machine. Findings From the experimentation, it has been observed that the wear severity index has been increased due to increase in wear particle concentration. CNN model has achieved an accuracy of 95.4% to recognize five categories of wear particles. Originality/value Teachable machine is generally used for the prediction of images, gestures and sound features. An attempt is made to apply this model for micro and nano wear particles to classify them based on their characteristics.

show abstract

Section: Introductionmentioning

confidence: 99%

Wear particles recognition through teachable machine

More¹,

Jaybhaye²

2022

ILT

View full text Add to dashboard Cite

show abstract

“…In conclusion, the intelligent identification of ferrography wear debris images had been studied extensively, and the recognition of simple wear debris, such as cutting and colored debris, had been basically realized. However, there are still many problems in the realization of complex wear debris and classification system, such as the identification of severe sliding, lamellar fatigue, and spalling fatigue debris, which are still the technical bottlenecks of intelligent identification [16,17].…”

Section: Introductionmentioning

confidence: 99%

FWDNet: A Novel Recognition Network for Ferrography Wear Debris Image Analysis

Jia

Wei

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Ferrography wear debris in lubricating oil contains abundant worthy information about the state of the machinery and equipment. In order to develop an online monitoring system based on condition maintenance and fault diagnosis, wear debris needs to be identified automatically. Through various tribological experiments, a dataset of seven kinds of wear debris was established. In this study, DenseNet121 was used as the base network to construct a DCNN model (FWDNet) using the transfer learning method. FWDNet obtained an accuracy of 90.15% through a 10-fold crossvalidation test. The results indicate that FWDNet and DCNN mode is suitable for the identification of wear debris and can be used in actual condition monitoring systems in the future.

show abstract

“…Thus, we may be still far away from appreciating the full range of wear particles for which more useful wear information can be provided. Indeed, with the development of artificial intelligence, some neural networks have been employed to establish wear particle classifiers [16][17][18][19]. For instance, a multi-level belief rule base system [20] and a linear support vector machine [21] were employed to optimize the wear information and classify wear particles.…”

Section: Introductionmentioning

confidence: 99%

Morphological residual convolutional neural network (M-RCNN) for intelligent recognition of wear particles from artificial joints

Song

Liao

et al. 2021

Friction

View full text Add to dashboard Cite

Finding the correct category of wear particles is important to understand the tribological behavior. However, manual identification is tedious and time-consuming. We here propose an automatic morphological residual convolutional neural network (M-RCNN), exploiting the residual knowledge and morphological priors between various particle types. We also employ data augmentation to prevent performance deterioration caused by the extremely imbalanced problem of class distribution. Experimental results indicate that our morphological priors are distinguishable and beneficial to largely boosting overall performance. M-RCNN demonstrates a much higher accuracy (0.940) than the deep residual network (0.845) and support vector machine (0.821). This work provides an effective solution for automatically identifying wear particles and can be a powerful tool to further analyze the failure mechanisms of artificial joints.

show abstract

WP-DRnet: A novel wear particle detection and recognition network for automatic ferrograph image analysis

Cited by 48 publications

References 26 publications

Wear particles recognition through teachable machine

Wear particles recognition through teachable machine

FWDNet: A Novel Recognition Network for Ferrography Wear Debris Image Analysis

Morphological residual convolutional neural network (M-RCNN) for intelligent recognition of wear particles from artificial joints

Contact Info

Product

Resources

About