《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 其他 > 設(shè)計(jì)應(yīng)用 > 基于光電檢測技術(shù)的電纜表面缺陷實(shí)時(shí)監(jiān)測系統(tǒng)研究
基于光電檢測技術(shù)的電纜表面缺陷實(shí)時(shí)監(jiān)測系統(tǒng)研究
信息技術(shù)與網(wǎng)絡(luò)安全 1期
劉秀婷
(無錫學(xué)院 理學(xué)院,江蘇 無錫214105)
摘要: 基于光電檢測技術(shù)開發(fā)了電纜表面缺陷實(shí)時(shí)監(jiān)測系統(tǒng)。在硬件結(jié)構(gòu)方面,系統(tǒng)采用半環(huán)形LED白光源照射電纜,利用線陣CCD相機(jī)采集電纜表面圖像。在軟件算法方面,提出一種改進(jìn)的ROI(Region of Interest)算法精確定位電纜區(qū)域,利用一種基于改進(jìn)雙邊濾波的圖像差分算法建立背景模型,改進(jìn)一種基于CV-Kmeans區(qū)域分類自適應(yīng)濾波窗口算法來凸顯電纜表面缺陷特征。研究結(jié)果表明,基于光電檢測技術(shù)研發(fā)的電纜表面缺陷實(shí)時(shí)監(jiān)測系統(tǒng)的識別能力較高,整體監(jiān)測準(zhǔn)確率不低于97.0%。
中圖分類號: TP919.8
文獻(xiàn)標(biāo)識碼: A
DOI: 10.19358/j.issn.2096-5133.2022.01.011
引用格式: 劉秀婷. 基于光電檢測技術(shù)的電纜表面缺陷實(shí)時(shí)監(jiān)測系統(tǒng)研究[J].信息技術(shù)與網(wǎng)絡(luò)安全,2022,41(1):69-74.
Research on the real-time monitoring system for the cable surface defects based on the photoelectric detection technology
Liu Xiuting
(School of Sciences, Wuxi University,Wuxi 214105,China)
Abstract: A real-time detection system for cable surface defects was designed based on the photoelectric detection technology. In its hardware, the linear CCD camera and the arc-shaped LED white lights were selected to take the cable images. In its software, an improved ROI(Region of Interest) algorithm was proposed to locate the cable surface defect, a novel image difference algorithm based on the improved bilateral filtering algorithm was employed to build the background model, and an adaptive filtering window algorithm based on the CV-Kmeans region classification was improved to highlight the cable defect features. The obtained results show that the developed detection system for cable surface defects has high recognition ability, and the overall monitoring accuracy is not less than 97.0%.
Key words : cable surface defect;real-time detection;machine vision;image processing

0 引言

在實(shí)際生產(chǎn)環(huán)境中,電纜通常受到原料、溫度等原因影響而出現(xiàn)小孔、鼓包、破損等表面缺陷[1]。這些缺陷不僅影響其外觀質(zhì)量,而且嚴(yán)重影響其性能,甚至?xí)斐砂踩鹿蔥2]。目前,國內(nèi)大多數(shù)電纜生產(chǎn)線的質(zhì)量監(jiān)測主要依賴人工目測和手觸的主觀經(jīng)驗(yàn)方法,遠(yuǎn)遠(yuǎn)不能滿足工業(yè)生產(chǎn)的監(jiān)測要求[3]。為此,迫切需要尋找一種性能優(yōu)異的自動化監(jiān)測技術(shù)來滿足工程生產(chǎn)需求。

近年來,以機(jī)器視覺為基礎(chǔ)的光電檢測技術(shù)成為自動監(jiān)測領(lǐng)域的熱點(diǎn),得到許多學(xué)者的關(guān)注,并對此展開了廣泛的系統(tǒng)研究。樊迪等[4]設(shè)計(jì)了基于機(jī)器視覺的FTU插口狀態(tài)自動識別系統(tǒng),提高了監(jiān)測作業(yè)的自動化程度,降低了人工帶電作業(yè)的安全隱患;王敏等[5]提出一種基于機(jī)器視覺的參數(shù)信息監(jiān)測方法,能夠準(zhǔn)確監(jiān)測識別電能表銘牌的額定參數(shù)信息。



本文詳細(xì)內(nèi)容請下載:http://theprogrammingfactory.com/resource/share/2000003939







作者信息:

劉秀婷

(無錫學(xué)院 理學(xué)院,江蘇 無錫214105)


此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。