面向烧结工业的多源异构数据融合与实时感知技术
Multi-source heterogeneous data fusion and real-time sensing technology for sintering industry
胡润琦 1何柏村 1杨冲 1钱金传 1张新民 1宋执环1
作者信息
- 1. 浙江大学工业控制技术全国重点实验室,浙江 杭州 310027;浙江大学控制科学与工程学院,浙江 杭州 310027
- 折叠
摘要
铁矿石烧结是高炉炼铁的关键初步工序,其中烧结过程关键生产指标在线实时智能感知是实现烧结工艺绿色、低耗、高效发展的关键技术之一.然而,一方面,传统的烧结生产指标(如FeO含量)测定方法存在高耗时,难以满足实时控制的需求;另一方面,烧结过程数据具有非线性、多源异构性和时滞性,对提高建模精度提出了很大的挑战.为此,本文提出了一种面向烧结工业的多源异构数据融合与实时感知技术.本研究采用多源异构信息融合方法,针对红外热像仪采集到的烧结机截面图像数据,通过专家知识和基于离散余弦变换(discrete cosine transform,DCT)的FcaNet模型分别提取浅层和深层特征,实现了特征级和数据级融合.在预测任务中将二维卷积块作用在时序数据上,使用FcaBlock作为特征提取的卷积块,有效提取了时序数据的频率分量信息.在真实炼钢厂的铁矿石烧结数据集上,本模型的预测精度和稳定性均优于现有模型,显著提高了对烧结过程关键质量指标的在线实时感知能力.
Abstract
Iron ore sintering is a key preliminary process in blast furnace ironmaking.Online real-time intelligent sensing of key production indicators in the sintering process is one of the key technol-ogies to achieve green,low-consumption,and efficient development of the sintering process.However,on one hand,traditional methods for measuring sintering production indicators(such as FeO content)are time-consuming and difficult to meet the needs of real-time control.On the other hand,the sinte-ring process data has nonlinearity,multi-source heterogeneity,and time lag,which poses a great chal-lenge to improving modeling accuracy.To this end,this paper proposes a multi-source heterogeneous data fusion and real-time sensing technology for the sintering industry.This study uses a multi-source heterogeneous information fusion method to extract shallow and deep features respectively through ex-pert knowledge and the FcaNet model based on discrete cosine transform(DCT)for the cross-sec-tional image data of the sintering machine collected by the infrared thermal imaging camera,achieving feature level and data level fusion.In the prediction task,the two-dimensional convolution block is applied to the time series data,and FcaBlock is used as the convolution block for feature extraction,which effectively extracts the frequency component information of the time series data.On the iron ore sintering data set of a real steelmaking plant,the prediction accuracy and stability of this model are superior to existing models,and it significantly improves the online real-time sensing of key quality indicators of the sintering process.
关键词
烧结过程/智能感知/多源异构信息融合/机器视觉/时间序列预测Key words
sintering process/intelligent sensing/multi-source heterogeneous information fusion/ma-chine vision/time series prediction引用本文复制引用
出版年
2024
NETL
NSTL
万方数据