基于多特征融合和改进级联森林的MSWI过程燃烧状态识别  

Combustion State Identification of Municipal Solid Waste Incineration Process Based on Multiple Feature Fusion and Improved Cascade Forest

作　　者：汤健[1,2] 潘晓彤 夏恒 李帷韬[3] TANG Jian;PAN Xiaotong;XIA Heng;LI Weitao(a.School of Information Science and Technology,Beijing University of Technology,Beijing 100124,China;Beijing Laboratory of Smart Environmental Protection,Beijing University of Technology,Beijing 100124,China;School of Electrical Engineering and Automation,Hefei University of Technology,Hefei 230009,China)

机构地区：[1]北京工业大学信息科学技术学院,北京100124 [2]北京工业大学北京智慧环保实验室,北京100124 [3]合肥工业大学电气与自动化工程学院,安徽合肥230009

出　　处：《控制工程》2025年第2期306-316,共11页Control Engineering of China

基　　金：国家自然科学基金资助项目(62073006,62021003,62373017)。

摘　　要：准确识别城市固废焚烧(municipal solid wastes incineration,MSWI)过程的燃烧状态是提高焚烧效率、降低污染排放的关键因素之一。为此提出了一种基于多特征融合和改进级联森林(improved cascade forest,ICF)的燃烧状态识别策略。首先,采用人工多曝光图像融合去雾算法、特征归一化、陷波滤波、中值滤波等预处理手段进行去雾和去噪处理,获得清晰图像;然后,提取图像的亮度、火焰、颜色和主成分等多特征,从多个视图进行图像表征,并基于互信息对多特征进行约简;最后,将约简特征输入ICF模型以建立MSWI过程燃烧状态识别模型。基于北京某焚烧发电厂的实际火焰进行实验验证,结果表明所构建的模型可达到96.01%的识别准确率。Accurately identifying the combustion state in the municipal solid waste incineration(MSWI)process is one of the key factors to improve the incineration efficiency and reduce the emission of polluting gases.A combustion state identification method of MSWI process based on multiple feature fusion and improved cascade forest(ICF)is proposed.Firstly,image preprocessing methods such as artificial multi exposure image fusion,feature normalization,notch filter and median filter are used to remove fog and noise.Then,the multiple features,such as brightness,flame,color and principal component of images are extracted for image representation from multiple views and these features are reduced based on mutual information.Finally,the traditional cascade forest is improved to increase the diversity of base learners.Taking the above reduction features as input,an ICF-based combustion state recognition model for MSWI process is established.Based on the actual flame of MSWI plant in Beijing,the verification experiment is carried out.The results show that the constructed model can achieve a recognition accuracy of 96.01%.

关 键 词：城市固废焚烧 燃烧状态识别 特征提取 互信息 级联森林 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]