电子测量与仪器学报

陈博桓,王馨雨,许学彬,沈洋,倪军.基于优化 ELM 的光纤连接器表面自识别降噪技术[J].电子测量与仪器学报,2022,36(4):169-178

基于优化 ELM 的光纤连接器表面自识别降噪技术

Optical fiber connector surface self-identification noise reductiontechnology based on optimized ELM

DOI：

英文关键词:fiber optic connector machine learning extreme learning machine images processing optical engineering

基金项目:浙江省大学生科研创新活动计划（2021R409045）、国家级大学生创新创业训练计划（2020103560009）、浙江省公益技术研究计划（LGN20F050001）、国家重点研发计划（2020YFF0217803）项目资助

作者	单位
陈博桓	1. 中国计量大学光学与电子科技学院
王馨雨	2. 中国计量大学艺术与传播学院
许学彬	1. 中国计量大学光学与电子科技学院
沈洋	1. 中国计量大学光学与电子科技学院
倪军	1. 中国计量大学光学与电子科技学院

Author	Institution
Chen Bohuan	1. College of Optical and Electronic Technology, China Jiliang University
Wang Xinyu	2. College of Art and Communication, China Jiliang University
Xu Xuebin	1. College of Optical and Electronic Technology, China Jiliang University
Shen Yang	1. College of Optical and Electronic Technology, China Jiliang University
Ni Jun	1. College of Optical and Electronic Technology, China Jiliang University

摘要点击次数: 234

全文下载次数: 5627

中文摘要:

光纤连接器的表面检测属于精密仪器检测,因此工厂环境中的大量灰尘会影响连接器表面的复原效果。然而现有的检测技术运行时间长,对于图像细节的保留能力差,并且难以克服实际工作环境中的干扰。因此提出一种优化超限学习机的自识别降噪技术。首先对于干涉数据进行降维处理;其次,采用 AdaBoost 算法优化超限学习机对噪声点进行定位;最后通过滤波算法对噪声点位置进行修复。实验得出,基于 AdaBoost-Elm 的自识别降噪算法具有较高的噪声识别能力,其平均噪声识别率达 97. 33%。此外,采用基于 AdaBoost-Elm 降噪算法得到 BBS 的平均值为 131. 14,NRIQAVR 的平均值为 2. 61,降噪效果均优于全局滤波算法。最后,通过模拟工厂环境,采用基于 AdaBoost-Elm 的中值滤波算法在不同光强条件下对重度污染的光纤探头进行 3D 复原测试,其 BBS 达到 130 左右,NRIQAVR 低于 2. 57,对比基于 Elm 的中值滤波算法具有明显优势。

英文摘要:

The surface detection of optical fiber connector belongs to precision instrument detection, accordingly, making it possible for the large amounts of dust in the factory environment that exerts detrimental influence on the recovery of optical fiber connector. Nonetheless, the current detection technology possesses long running time, poor retention ability for image details, and is problematic to overcome interference in the actual working environment. To this end, we propose a self-identification noise reduction technology based on optimised extreme learning machine. Firstly, the interference data is processed by dimensionality reduction. Secondly, select the dimensionality reduction data as the training data, and use the extreme learning machine optimised by AdaBoost algorithm to locate the noise. Ultimately, the positions of noise points are repaired by filtering algorithms. The experimental results demonstrate that the selfrecognition noise reduction algorithm based on AdaBoost-Elm is equipped with high noise recognition ability and its ANRR reaches 97. 33%. Additionally, the average value of BBS and NRIQAVR based on AdaBoost-Elm noise reduction algorithm are 131. 14 and 2. 61 respectively, which are better than global filtering algorithm. In the end, we simulate the factory environment and use mean filtering based on AdaBoost-Elm to perform 3D restoration test on the sharply polluted fiber optic probe under different light intensity conditions. It is found that its BBS reaches around 130 and its NRIQAVR is lower than 2. 57, which has apparent merits compared with the median filtering based on Elm.

查看全文查看/发表评论下载PDF阅读器