高光谱成像技术在特殊材料体检测中的应用

导读：【论文速递】栏目精选客户利用双利合谱高光谱设备发表的研究成果，从农林生态遥感、食品质检、到生物医学等领域，展现高光谱成像技术如何以“图谱合一”的硬核能力，突破传统检测方法的痛点，推动学科交叉创新。将定期分享客户使用双利合谱产品发表的SCI论文，涵盖技术前沿、应用创新以及行业突破，为您在高光谱成像技术向更宽领域的拓展提供参考。

1

Pollution Degree Detection of Insulators based on Hyperspectral Imaging Technology

基于高光谱成像技术的绝缘子污秽度检测

论文中所使用双利合谱产品：
便携式成像光谱系统

摘要：

Present researches prove that the pollution flash over of operating insulators still threatens the safe and reliable operation of power system. However, traditional detection methods are difficult to achieve noncontact detection. The hyperspectral imaging technology is a nondestructive testing technology which combines image information and spectral information, therefore it has potential to become an important detection method for power device external insulation. In order to study the application of hyperspectral imaging technology in the detection of insulator pollution degree, a new data processing method is produced. On the one hand, the result of spectral processing shows that there are corresponding relationships between the pollution degree and the reflectivity value, the reflectivity waveform and base material. On the other hand, the result of image processing proves that it can distinguish between the polluted and non polluted areas by using principal components analysis and K means clustering algorithm. The above parts prove that the application of hyperspectral imaging technology in the detection of insulator's external insulation is feasible and it will have a broad application prospect.

目前研究证明，运行绝缘子的污闪现象仍然威胁着电力系统的安全可靠运行，而传统的检测方法难以实现非接触检测，高光谱成像技术是一种将图像信息与光谱信息相结合的无损检测技术，有潜力成为电力设备外绝缘的重要检测手段。为了研究高光谱成像技术在绝缘子污秽度检测中的应用，提出了一种新的数据处理方法。一方面，光谱处理结果表明，污秽度与反射率值、反射率波形与基材之间存在对应关系；另一方面，图像处理结果证明，利用主成分分析和K均值聚类算法可以区分污秽区域和非污秽区域。以上证明了高光谱成像技术在绝缘子外绝缘检测中的应用是可行的，具有广阔的应用前景。

DOI：10.1109/ICDL.2019.8796617

期刊：IEEE 20th International Conference on Dielectric Liquids (ICDL),

关键词：输电线路绝缘子、污秽程度、高光谱成像技术、光谱处理、图像处理

2

Surface Roughness Detection of Roof Insulator Based on Hyperspectral Technology

基于高光谱技术的车顶绝缘子表面粗糙度检测

论文中所使用双利合谱产品：
便携式成像光谱系统

摘要：

The strong air ow generated during the operation of the high-speed train will carry sand and dust, causing high-speed sand and dust to hit the surface of the external equipment of the vehicle body, which will increase the surface roughness of the roof insulators, resulting in the changes of the hydrophobicity, fouling characteristics and insulation performance of the insulator. It poses a hidden danger to the safe and stable operation of the train. In our existing surface roughness testing methods, contact detections and optical stylus methods can cause damage to the insulator surface. Infrared detection methods will be disturbed by leakage current. Most methods need to be disassembled for testing. These methods have certain disadvantages. Therefore, this paper proposes a non-contact detection method for the surface roughness of the roof insulators. Firstly, we extract the image information of the insulator surface by hyperspectral imager, then preprocess the extracted hyperspectral image and use the continuous projection algorithm to reduce the data. Finally, we use the support vector machine to construct the insulator surface roughness discriminant model, and successfully realize the hyperspectral detection method of the surface roughness of the roof insulators, and verify the effectiveness of the proposed method by experiments. As a non-contact detection method, this method can detect the surface roughness of the roof insulators in the non-disassembly conditions, and help the eld staffs to grasp the surface roughness of the high-speed train roof insulators in time.

高速列车运行过程中产生的强气流会夹带沙尘，导致高速的沙尘撞击到车体外部设备表面，使车顶绝缘子表面粗糙度增大，导致绝缘子的憎水性、污垢特性和绝缘性能发生变化，对列车安全稳定运行造成隐患。在我国现有的表面粗糙度检测方法中，接触式检测和光触针法会对绝缘子表面造成损伤，红外检测法会受到漏电流的干扰，大部分方法需要拆卸检测，这些方法都存在一定的缺点。因此，本文提出了一种车顶绝缘子表面粗糙度的非接触检测方法。首先利用高光谱成像仪提取绝缘子表面的图像信息，然后对提取到的高光谱图像进行预处理，并利用连续投影算法对数据进行缩减。最后利用支持向量机构建绝缘子表面粗糙度判别模型，成功实现了车顶绝缘子表面粗糙度的高光谱检测方法，并通过实验验证了所提方法的有效性。作为一种非接触式检测方法，该方法可以在非拆卸条件下检测出车顶绝缘子的表面粗糙度，有助于现场工作人员及时掌握高铁车顶绝缘子的表面粗糙度。

DOI：https://DOI.org/10.1364/OE.26.009822

期刊：ACCESS
关键词：车顶绝缘子，表面粗糙度，高光谱技术，非接触检测，支持向量机

3

Identification of white degradable and non-degradable plastics in food f ield: A dynamic residual network coupled with hyperspectral technology

食品领域白色可降解与不可降解塑料的识别：一种结合高光谱技术的动态残差网络

论文中所使用双利合谱产品：
“盖亚”高光谱分选仪

摘要：

In the food field, with the improvement of people’s health and environmental protection awareness, degradable plastics have become a trend to replace non-degradable plastics. However, their appearance is very similar, making it difficult to distinguish them. This work proposed a rapid identification method for white non- degradable and degradable plastics. Firstly, a hyperspectral imaging system was used to collect the hyper spectral images of the plastics in visible and near-infrared bands (380–1038 nm). Secondly, a residual network (ResNet) was designed according to the characteristics of hyperspectral information. Finally, a dynamic convolution module was introduced into the ResNet to establish a dynamic residual network (Dy-ResNet) to adaptively mine the data features and realize the classification of the degradable and non-degradable plastics. Dy-ResNet had better classification performance than the other classical deep learning methods. The classifi cation accuracy of the degradable and non-degradable plastics was 99.06%. In conclusion, hyperspectral imaging technology was combined with Dy-ResNet to identify the white non-degradable and degradable plastics effectively.

在食品领域，随着人们健康与环保意识的提高，可降解塑料替代不可降解塑料已成为趋势，但二者外观十分相似，难以区分。本文提出了一种白色不可降解与可降解塑料的快速识别方法。首先，利用高光谱成像系统采集塑料在可见光和近红外波段（380–1038 nm）的高光谱图像。其次，根据高光谱信息的特点设计残差网络（ResNet）。最后，在ResNet中引入动态卷积模块，建立动态残差网络（Dy-ResNet），自适应地挖掘数据特征，实现可降解与不可降解塑料的分类。Dy-ResNet比其他经典深度学习方法具有更好的分类性能。可降解与不可降解塑料的分类准确率为99.06%。综上所述，高光谱成像技术与Dy-ResNet相结合可以有效识别白色不可降解与可降解塑料。

DOI：https://DOI.org/10.1364/OE.26.009822

期刊：Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy

关键词：食品塑料分类、降解性、高光谱成像技术、残差网络、动态卷积

4

基于高光谱结合机器学习对塑料瓶盖的快速分类研究

论文中所使用双利合谱产品：

便携式成像光谱系统

摘要：

为建立一种快速无损分类塑料瓶盖的方法，采用高光谱成像技术对48个塑料瓶盖样品进行检验。首先对原始光谱进行预处理，再分别采用主成分分析法、偏最小二乘判别分析法和竞争自适应重加权采样法构建高光谱数据集，并对数据集分别使用支持向量机、多层感知机模型和卷积神经网络进行训练。结果表明：利用竞争自适应重加权特征提取构建的塑料瓶盖高光谱图像，在卷积神经网络中的测试集准确率达到了100％。该方法方便快捷，对样品无损且用量少，为塑料瓶盖的分类提供了有力的支持。

DOI：https://DOI.org/10.1063/1.5048795

期刊：上海塑料

关键词：高光谱技术、塑料瓶盖、偏最小二乘判别分析、竞争自适应重加权采样、卷积神经网络

相关产品推荐

每一篇论文都是科研人员智慧的结晶，也是双利合谱与客户携手共进的见证。期待通过“论文速递”栏目，与您共同见证高光谱成像技术在科研领域的每一次突破，分享科研人员的智慧结晶。让我们一起探索高光谱成像技术的无限可能，推动行业的发展与进步。欢迎关注双利合谱“论文速递”栏目，更多精彩论文敬请期待！