Using Deep Convolutional Neural Networks and Infrared Thermography to Identify Coal Quality and Gangue
Using Deep Convolutional Neural Networks and Infrared Thermography to Identify Coal Quality and Gangue
复制标题
使用深度卷积神经网络和红外热成像识别煤质和煤矸石
DOI：
10.1109/access.2021.3121270
复制
发表时间：
2021-01-01
期刊：
影响因子：
3.9
通讯作者：
Liu, Tonggang
中科院分区：
文献类型：
--
作者：
Eshaq, Refat Mohammed Abdullah;Hu, Eryi;Liu, Tonggang
由于中国、印度和美国对煤炭的巨大需求以及煤炭大规模使用的不断增长，人们对环境质量和人类健康可能面临的危害产生了猜测。劣质煤中的粉煤灰和挥发物含量对环境极其有害。因此，对于已知的对地球自然环境的危害，仍有很多需要探索的地方。对于优质煤的检测，我们提出了一种新方法，即根据不同的“煤种”（无烟煤、烟煤、次烟煤和褐煤）来区分煤质，并通过利用红外机器视觉和卷积神经网络进行深度学习，有效地从选煤厂的生产线上分离煤矸石和岩石，这可以使煤炭的使用对人类和自然的危害更小和/或对大众福利更有益。在本文中，我们进行了两个实验。第一个实验是研究在50℃、70℃、90℃、110℃和150℃温度下，煤种、煤矸石和岩石与红外辐射的反应。第二个实验是对几种常见的卷积神经网络模型（如AlexNet、DarkNet - 53、GoogLeNet、NasNet_Mobileb、ResNet - 18、MobileNet - v2、Inception - v3和DenseNet - 201）进行训练和测试，以对煤种进行分类并区分煤矸石和岩石。当使用ResNet - 18和DenseNet - 201模型时，我们在这些训练和测试过程中实现了100%的显著分类准确率。
Owing to the enormous demand for and growing large-scale use of coal in the China, India and USA speculation has arisen about possible hazards to environmental quality and human health. The contents of fly ash and volatile matter in low-quality coal are extremely harmful to the environment. As a result, there is still much to be explored regarding known hazards and harms to the natural environment of the Earth. For the detection of high-quality coal, we propose a new method of distinguishing coal quality or types (i.e., anthracite, bituminous coal, subbituminous coal and lignite) and efficiently separating gangue and rock from the production lines of coal preparation plants (CPPs) by exploiting infrared machine vision and convolutional neural networks (CNNs) for deep learning, which can make coal use less harmful to humans and nature and/or more useful for general welfare. In this paper, we carried out two experiments. First experiment to study the reaction coal types, gangue and rock with infrared radiation at temperatures of 50°C, 70°C, 90°C, 110°C, and 150°C. Second experiment, several common CNN models (i.e., AlexNet, DarkNet-58, GoogLeNet, NasNet_Mobileb, ResNet-18, MobileNet-v2, Inception-v3 and DenseNet-201) are trained and tested to classify coal types and distinguish gangue and rock. We achieve a remarkable classification accuracy of 100% in these training and testing processes when employing the ResNet-18 and DenseNet-201 models.