Zhang Lei, Sui YiPing, Wang HaoSheng, Hao ShangKai, Zhang NingBo
Key Laboratory of Deep Coal Mining of the Ministry of Education, School of Mines, China University of Mining and Technology, Xuzhou, 221116, China.
College of Coal Engineering, Shanxi Datong University, Datong, 037003, Shanxi, China.
Sci Rep. 2022 Dec 5;12(1):20983. doi: 10.1038/s41598-022-25496-5.
Using image recognition technology to realize coal gangue recognition is one of the development directions of intelligent fully mechanized caving mining. Aiming at the problem of low accuracy of coal gangue recognition in fully mechanized caving mining, the extraction method of Coal and gangue images features is proposed, and the corresponding coal gangue recognition model is constructed. The illuminance value is an important factor affecting the imaging quality. Therefore, a multi-light source image acquisition system is designed, and the optimal illuminance value suitable for coal and gangue images acquisition is determined to be 17,130 Lux. There is a large amount of image noise in the gray-sc5ale image, so Gaussian filtering is used to eliminate the noise in the gray-scale image of coal and gangue. Then, six gray-scale features and four texture features are extracted from 900 coal and gangue images respectively. It is concluded that the three kinds of features of gray skewness, gray variance and texture contrast have the highest discrimination on coal and gangue images. Least squares vector machine has a strong ability to classify, so the use of least squares vector machine to achieve coal gangue identification, and build coal gangue identification model. The results show that the recognition accuracy of the model for coal gangue images is 92.2% and 91.5%, respectively, with gray skewness and texture contrast as indicators. This study provides a reliable theoretical support for solving the problem of low recognition rate of coal gangue in fully mechanized caving mining.
利用图像识别技术实现煤矸石识别是智能化综采放顶煤开采的发展方向之一。针对综采放顶煤开采中煤矸石识别准确率低的问题，提出了煤矸石图像特征提取方法，并构建了相应的煤矸石识别模型。光照度值是影响成像质量的重要因素，因此设计了多光源图像采集系统，确定适合煤矸石图像采集的最佳光照度值为17130勒克斯。灰度图像中存在大量图像噪声，因此采用高斯滤波消除煤矸石灰度图像中的噪声。然后，分别从900张煤矸石图像中提取了六种灰度特征和四种纹理特征。得出灰度偏度、灰度方差和纹理对比度这三种特征对煤矸石图像的判别能力最强。最小二乘向量机具有较强的分类能力，因此利用最小二乘向量机实现煤矸石识别，并建立煤矸石识别模型。结果表明，以灰度偏度和纹理对比度为指标，该模型对煤矸石图像的识别准确率分别为92.2%和91.5%。本研究为解决综采放顶煤开采中煤矸石识别率低的问题提供了可靠的理论支持。
