Wear Debris Classification and Quantity and Size Calculation Using Convolutional Neural Network

Wang, Hongbing; Yuan, Fei; Gao, Liyuan; Huang, Rong; Wang, Weishen

doi:10.1007/978-981-15-1922-2_33

Cited by 5 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sengupta et al [15] and Goilkar et al [16] demonstrated that a protective layer on a mild steel component will lessen corrosion, avoid material wear, and keep outside particles from getting into the lubricant. UstbNet is a better lightweight convolutional neural network that Wang et al [17] suggested for the classification of wear debris images.…”

Section: Researchmentioning

confidence: 99%

Online Gear Wear Particle Detection and Categorization Using a Convolutional Neural Network Algorithm Integrated with Cascade Classifier

Gupta¹,

Hirani²,

Muzakkir³

2023

Tribol. Ind.

View full text Add to dashboard Cite

Most gears fail because of wear caused by rubbing, metal to metal contact, contamination, or breakdown of lubrication. Because of this, figuring out how to find and sort wear debris particles is an important area of research for both predictive and proactive maintenance. By putting these wear particles into different categories like spherical, cutting, fatigue, sliding and rubbing, it would be possible to identify the wear modes present in the gearbox and predict the nature of failure and condition of the system. The present research aims to automate the detection and classification process using the Convolutional Neural Network (CNN) integrated with Cascade classifier. CNN automatically extracts different suitable features from images by applying multiple filters on it and also reduces the complexity of image processing whereas the Cascade classifier is used to detect the particles by differentiating between positive and negative images by applying the Haar-like features into it. The objective of the research work is to provide a most efficient and accurate detection and classification of wear debris particles using a trained cascade classifier integrated with a customized lightweight CNN model named as Wear Particle Classifier Net (WPCnet).

show abstract

Section: Researchmentioning

confidence: 99%

Online Gear Wear Particle Detection and Categorization Using a Convolutional Neural Network Algorithm Integrated with Cascade Classifier

Gupta¹,

Hirani²,

Muzakkir³

2023

Tribol. Ind.

View full text Add to dashboard Cite

show abstract

“…The researchers combined various techniques with magnetic sensors to detect the quality of the abrasive grains. These included optical sensors [ 16 , 17 ], resistive magnetic plug sensors [ 18 ], capacitive magnetic plug sensors [ 19 ], and inductive magnetic plug sensors [ 20 ]. There are two main optical detection methods: the light blockage method [ 16 ] and the imaging method [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

“…These included optical sensors [ 16 , 17 ], resistive magnetic plug sensors [ 18 ], capacitive magnetic plug sensors [ 19 ], and inductive magnetic plug sensors [ 20 ]. There are two main optical detection methods: the light blockage method [ 16 ] and the imaging method [ 17 ]. Nonetheless, these techniques necessitate the implementation of intricate algorithms and high-performance hardware infrastructure.…”

Section: Introductionmentioning

confidence: 99%

Investigation of the Effect of Debris Position on the Detection Stability of a Magnetic Plug Sensor Based on Alternating Current Bridge

Zhang,

Xie,

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Magnetic plug-type abrasive particle sensors have a wide range of applications in oil detection, but there is little literature on the effect of abrasive particle position on detection accuracy. In this paper, an alternating current (AC) bridge-type abrasive particle detection sensor is designed, in which the sensing module utilizes permanent magnets to attract iron particles, and the induction coil is specially designed to detect the magnetic field fluctuation caused by iron particles. A corresponding model was also designed to evaluate the sensor’s sensitivity at different locations. In this paper, the magnetic field distribution of the sensor was first analyzed using finite element analysis software to obtain the magnetic field strength at different positions. Then, the response sensitivity of the sensor to particles and the effect of different positions on the detection results are explored through experiments. The simulation and the experimental results show substantial signal difference signal at different sensor positions. The method outlined in this article can determine the optimal sensing range for subsequent magnetic plug-type abrasive particle detection sensors and subsequently improve their reliability.

show abstract

“…Another study used CNN to detect the wear condition present in a mechanical setup without classifying the wear debris, with an accuracy of 90% ( Wang et al, 2020 ). However, for the detailed quantitative analysis of wear debris, the average classification accuracies for different types of wear debris ranges from 77% to 83% across multiple studies ( Wang H et al, 2019 ; Wang et al, 2020 ; Wang S et al, 2019 ). CNN-based identification and classification of wear debris in joint arthroplasty have been shown to have very high accuracies in multi-class morphological classifications as shown in ( Hu et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

An automated system for polymer wear debris analysis in total disc arthroplasty using convolution neural network

Kandel

Hall

et al. 2023

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Introduction: Polymer wear debris is one of the major concerns in total joint replacements due to wear-induced biological reactions which can lead to osteolysis and joint failure. The wear-induced biological reactions depend on the wear volume, shape and size of the wear debris and their volumetric concentration. The study of wear particles is crucial in analysing the failure modes of the total joint replacements to ensure improved designs and materials are introduced for the next generation of devices. Existing methods of wear debris analysis follow a traditional approach of computer-aided manual identification and segmentation of wear debris which encounters problems such as significant manual effort, time consumption, low accuracy due to user errors and biases, and overall lack of insight into the wear regime.Methods: This study proposes an automatic particle segmentation algorithm using adaptive thresholding followed by classification using Convolution Neural Network (CNN) to classify ultra-high molecular weight polyethylene polymer wear debris generated from total disc replacements tested in a spine simulator. A CNN takes object pixels as numeric input and uses convolution operations to create feature maps which are used to classify objects.Results: Classification accuracies of up to 96.49% were achieved for the identification of wear particles. Particle characteristics such as shape, size and area were estimated to generate size and volumetric distribution graphs.Discussion: The use of computer algorithms and CNN facilitates the analysis of a wider range of wear debris with complex characteristics with significantly fewer resources which results in robust size and volume distribution graphs for the estimation of the osteolytic potential of devices using functional biological activity estimates.

show abstract

Wear Debris Classification and Quantity and Size Calculation Using Convolutional Neural Network

Cited by 5 publications

References 20 publications

Online Gear Wear Particle Detection and Categorization Using a Convolutional Neural Network Algorithm Integrated with Cascade Classifier

Online Gear Wear Particle Detection and Categorization Using a Convolutional Neural Network Algorithm Integrated with Cascade Classifier

Investigation of the Effect of Debris Position on the Detection Stability of a Magnetic Plug Sensor Based on Alternating Current Bridge

An automated system for polymer wear debris analysis in total disc arthroplasty using convolution neural network

Contact Info

Product

Resources

About