带有轮廓变形的 Si3N4 轴承滚动体微裂纹的边缘分割方法

IF 6.1 1区工程技术 Q1 ENGINEERING, MECHANICAL

Tribology International Pub Date : 2024-10-24 DOI:10.1016/j.triboint.2024.110351

Dahai Liao , Jianfei Yang , Guangmao Li , Jianbo Le , Hu Chen , Nanxing Wu

{"title":"带有轮廓变形的 Si3N4 轴承滚动体微裂纹的边缘分割方法","authors":"Dahai Liao , Jianfei Yang , Guangmao Li , Jianbo Le , Hu Chen , Nanxing Wu","doi":"10.1016/j.triboint.2024.110351","DOIUrl":null,"url":null,"abstract":"<div><div>For the profile-distortion of Si<sub>3</sub>N<sub>4</sub> bearing rolling elements microcracks image. A coupling method of variable-scale truncated median filtering and detection-driven active contour model is proposed. Details are as follows. The sigmoid activation function is constructed to dynamically adjust the circular window. The local threshold truncation is designed to adapt to the characteristics of different regions in the image. The area threshold is defined to eliminate non-target features. The mean peak signal-to-noise ratio (PSNR) of filtered images is about 40.263. The edge overlap rate is as low as 0.1027. The mean accuracy of feature extraction is about 94.33 %. To sum up, the influence result from profile-distortion on the accuracy of feature extraction of Si<sub>3</sub>N<sub>4</sub> bearing rolling elements microcracks is effectively solved.</div></div>","PeriodicalId":23238,"journal":{"name":"Tribology International","volume":"202 ","pages":"Article 110351"},"PeriodicalIF":6.1000,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Edge segmentation method for Si3N4 bearing rolling elements microcracks with profile-distortion\",\"authors\":\"Dahai Liao , Jianfei Yang , Guangmao Li , Jianbo Le , Hu Chen , Nanxing Wu\",\"doi\":\"10.1016/j.triboint.2024.110351\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>For the profile-distortion of Si<sub>3</sub>N<sub>4</sub> bearing rolling elements microcracks image. A coupling method of variable-scale truncated median filtering and detection-driven active contour model is proposed. Details are as follows. The sigmoid activation function is constructed to dynamically adjust the circular window. The local threshold truncation is designed to adapt to the characteristics of different regions in the image. The area threshold is defined to eliminate non-target features. The mean peak signal-to-noise ratio (PSNR) of filtered images is about 40.263. The edge overlap rate is as low as 0.1027. The mean accuracy of feature extraction is about 94.33 %. To sum up, the influence result from profile-distortion on the accuracy of feature extraction of Si<sub>3</sub>N<sub>4</sub> bearing rolling elements microcracks is effectively solved.</div></div>\",\"PeriodicalId\":23238,\"journal\":{\"name\":\"Tribology International\",\"volume\":\"202 \",\"pages\":\"Article 110351\"},\"PeriodicalIF\":6.1000,\"publicationDate\":\"2024-10-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Tribology International\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0301679X24011034\",\"RegionNum\":1,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, MECHANICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tribology International","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0301679X24011034","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}

引用次数: 0

摘要

针对 Si3N4 轴承滚动体微裂纹图像的轮廓失真。提出了一种变尺度截断中值滤波与检测驱动主动轮廓模型的耦合方法。具体方法如下构建 sigmoid 激活函数来动态调整圆形窗口。设计了局部阈值截断，以适应图像中不同区域的特征。区域阈值用于消除非目标特征。滤波图像的平均峰值信噪比（PSNR）约为 40.263。边缘重叠率低至 0.1027。特征提取的平均准确率约为 94.33%。综上所述，轮廓失真对 Si3N4 轴承滚动体微裂纹特征提取精度的影响得到了有效解决。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Edge segmentation method for Si3N4 bearing rolling elements microcracks with profile-distortion

For the profile-distortion of Si₃N₄ bearing rolling elements microcracks image. A coupling method of variable-scale truncated median filtering and detection-driven active contour model is proposed. Details are as follows. The sigmoid activation function is constructed to dynamically adjust the circular window. The local threshold truncation is designed to adapt to the characteristics of different regions in the image. The area threshold is defined to eliminate non-target features. The mean peak signal-to-noise ratio (PSNR) of filtered images is about 40.263. The edge overlap rate is as low as 0.1027. The mean accuracy of feature extraction is about 94.33 %. To sum up, the influence result from profile-distortion on the accuracy of feature extraction of Si₃N₄ bearing rolling elements microcracks is effectively solved.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Tribology International 工程技术-工程：机械

CiteScore

10.10

自引率

16.10%

发文量

627

审稿时长

35 days

期刊介绍： Tribology is the science of rubbing surfaces and contributes to every facet of our everyday life, from live cell friction to engine lubrication and seismology. As such tribology is truly multidisciplinary and this extraordinary breadth of scientific interest is reflected in the scope of Tribology International. Tribology International seeks to publish original research papers of the highest scientific quality to provide an archival resource for scientists from all backgrounds. Written contributions are invited reporting experimental and modelling studies both in established areas of tribology and emerging fields. Scientific topics include the physics or chemistry of tribo-surfaces, bio-tribology, surface engineering and materials, contact mechanics, nano-tribology, lubricants and hydrodynamic lubrication.