摘要
城市固废焚烧(MSWI)过程产生的副产品之一是被称为“世纪之毒”的二噁英(DXN),受限于其排放浓度检测技术难度以及时间与经济成本等因素,难以获得足量的有标记样本用于构建DXN排放浓度软测量模型。为有效利用现场控制系统采集的大量无标记样本,同时解决传统浅层学习模型泛化性能较差的问题,提出了基于Bagging半监督深度森林回归(DFR)的DXN排放浓度软测量方法。首先,基于Bagging机制以重采样原始标记数据集的方式获得多个训练子集,并构建具有差异性的多个随机森林(RF)模型;接着,将RF模型迭代更新、近邻集合选择和性能评估策略相结合用于获得高置信度伪标记样本;最后,基于伪标记和原始标记样本集构建DFR模型。采用北京某MSWI电厂的实际DXN检测数据验证了所提方法的有效性,结果表明,该方法的预测稳定性较好,其训练、验证和测试集的均方根误差分别为0.015 50、0.020 23和0.019 73。
Dioxin(DXN), known as “the poison of the century”, is one of the by-products emitted by the municipal solid waste incineration(MSWI) process. Limited by the technical difficulty, time and economic cost of DXN emission concentration detection, it is difficult to obtain sufficient labeled samples for building a DXN emission soft sensor model. To effectively utilize a large number of unlabeled samples collected by the field control system and solve the problem of poor generalization performance of traditional shallow learning models, a soft-sensor method of DXN emission concentration based on Bagging semi-supervised deep forest regression(DFR) is proposed. First, multiple training subsets are obtained by resampling the original labeled dataset based on the Bagging mechanism, and multiple random forest(RF) models with diversities are formulated. Then, the RF model is iteratively updated, the nearest neighbor set is selected and the generalization performance strategies are evaluated, which are all used to obtain high-confidence pseudo-labeled samples. Finally, a DFR model is constructed based on the pseudo-labeled and original labeled sample sets. The effectiveness of the proposed method is evaluated with the actual DXN detection data of MSWI power plant in Beijing. It shows that the propose method has well prediction stability, and the root mean square errors are 0.015 50, 0.020 23 and 0.019 73 for training, validation and testing datasets respectively.
作者
徐雯
汤健
夏恒
乔俊飞
Xu Wen;Tang Jian;Xia Heng;Qiao Junfei(Fraculty of Information Technology,Beijing Unirersiy of Technology,Bejjing 100124,China)
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2022年第6期251-259,共9页
Chinese Journal of Scientific Instrument
基金
北京市自然科学基金(4212032)
国家自然科学基金(62073006)项目资助。
关键词
城市固废焚烧
二噁英软测量
Bagging半监督
伪标记样本
随机森林
深度森林回归
municipal solid waste incineration
soft sensor of dioxin
Bagging semi-supervised
pseudo-labeled samples
random forest
deep forest regression
