激光与光电子学进展, 2018, 55 (12): 121504, 网络出版: 2019-08-01
基于离散余弦变换特征和隐马尔科夫模型的铜熔炼过程烟雾分级 下载: 921次
Smoke Classification in Copper Smelting Process Based on Discrete Cosine Transform Features and Hidden Markov Model
图像处理 铜熔炼 图像分析 离散余弦变换(DCT) 隐马尔科夫模型(HMM) 烟雾分级 image processing copper smelting process image analysis discrete cosine transform (DCT) hidden Markov model (HMM) smoke classification
摘要
为实现铜熔炼过程除尘风机转速的自动调节,提出了基于图像分析技术的烟雾浓度分级方法。通过采样窗对烟雾图像从上至下进行采样,形成时间序列,对每个采样子图进行离散余弦变换(DCT)特征提取,提取的系数视作该时刻隐马尔科夫模型(HMM)隐含状态产生的的观测值,一幅图像则分割成一个完整的HMM序列。通过对4种工况分别建立HMM,每种工况各用30幅图像训练估计模型参数,再对待测烟雾样本图像进行分类。实验结果表明,采用HMM分类的准确率最高可达95%,优于最小二乘支持向量机(LSSVM)的识别效果。
Abstract
A smoke concentration grading method based on the image analysis technique is proposed for the automatic speed adjustment of the dust removal fan in the copper smelting process. We obtain a sequence of sub images by using a moving window to slide over the whole smoke image from top to bottom. Then, discrete cosine transform (DCT) is utilized to extract the features of each sub-image and the DCT coefficients are vectorized as the observation data for hidden Markov model (HMM). Thus an image is divided into an observed sequence to build the HMM model for grade classification. Four different running states are considered in the smelting process, in which a HMM model is built for each running state. For each running state, 30 images are used for the training of HMM model. The results show that the classification accuracy can reach 95% with HMM, which is higher than that of least squares support vector machine (LSSVM).
张宏伟, 张凌婕, 袁小锋, 宋执环. 基于离散余弦变换特征和隐马尔科夫模型的铜熔炼过程烟雾分级[J]. 激光与光电子学进展, 2018, 55(12): 121504. Hongwei Zhang, Lingjie Zhang, Xiaofeng Yuan, Zhihuan Song. Smoke Classification in Copper Smelting Process Based on Discrete Cosine Transform Features and Hidden Markov Model[J]. Laser & Optoelectronics Progress, 2018, 55(12): 121504.