基于线阵相机的煤矿机械加工表面质量检测方法  

Detection Method of Surface Quality of Coal Mine Machining Based on Line Scan Camera

作　　者：郭玉龙 陈一兵 GUO Yulong;CHEN Yibing(CCTEG Wuhan Engineering Company,Wuhan 430064,China)

机构地区：[1]中煤科工集团武汉设计研究院有限公司,湖北武汉430064

出　　处：《机械与电子》2023年第6期21-25,共5页Machinery & Electronics

基　　金：国家能源集团2020年第二批科技项目(GJNY-20-238)。

摘　　要：为解决当前煤矿机械经加工后表面质量检测准确率低、峰值信噪比低等问题,提出基于线阵相机的煤矿机械加工表面质量检测方法。以煤矿带式运输机中的传动滚筒为研究对象,在线阵相机提取图像的基础上,利用平滑滤波对图像进行去噪处理,避免噪声对煤矿机械加工后的表面检测结果产生影响,并采用GLCM模型对去噪后的图像实行特征提取,将提取的特征输入LSTM模型中完成特征识别分类,输出机械加工表面的质量检测结果。实验结果证明,所提方法的检测准确率高、峰值信噪比数值高。In order to solve the problems of low detection accuracy and low peak signal-to-noise ratio of the current surface quality of coal mine machinery after processing,a method for surface quality detection of coal mine machinery processing based on line scan camera is proposed.In this paper,the transmission roller in the coal mine belt conveyor is taken as the research object.On the basis of the image extracted by the line scan camera,the image is denoised by smooth filtering to avoid the influence of noise on the surface detection results after the coal mine machining.The model performs feature extraction on the denoised image,and the extracted features are input into the LSTM model to complete feature recognition and classification,and output the quality inspection results of the machined surface.The experimental results show that the proposed method has high detection accuracy and high peak signal-to-noise ratio value.

关 键 词：煤矿带式运输机 线阵相机 特征提取 灰度计算 峰值信噪 

分 类 号：TH161.1[机械工程—机械制造及自动化] TP391.41[自动化与计算机技术—计算机应用技术]