Multi-time-scale TFe prediction for iron ore sintering process with complex time delay

Iron ore sintering is a critical process in steel-making industry. It produces sinter with qualified iron grade (TFe) for the blast furnace process. The process variables display a multi-time-scale feature that is derived from the complex time delays involved in a sintering process. To resolve the contradiction between a single-time-scale data acquisition of TFe and a multi-time-scale feature that the process displays. A multi-scale prediction approach in offline and online modes was presented for the prediction of TFe. The approach not only solves the contradiction, but also meets the requirements of online and offline optimizations of a sintering process. First, a discrete wavelet transform method was combined with process knowledge to decompose the online and offline TFe component with different time scales. Then, an improved back-propagation neural network (IBPNN) with its input neurons not only connected to the hidden neurons but also to the output neurons was built for the offline TFe prediction under large-time scale. Last, a just-in-time-learning-based online model was built under the mixture time scales of medium and small. The simulation results of actual run data show that an IBPNN has a good overall performance compared with an extreme learning machine (ELM), an improved ELM, and a back-propagation neural network for the offline TFe prediction. The results also show the superiority of the multi-time-scale prediction model compared with an offline prediction and a one-time-scale prediction models.     

A hybrid just-in-time soft sensor for carbon efficiency of iron ore sintering process based on feature extraction of cross-sectional frames at discharge end

Iron ore sintering is the second-most energy-consuming process in steelmaking. The main source of energy for it is the combustion of carbon. In order to reduce energy consumptions and improve industrial competitiveness, it is important to improve carbon efficiency. Reliable online prediction of the carbon efficiency would be extremely beneficial for making timely adjustments to the process to improve it. In this study, the comprehensive carbon ratio (CCR) was taken to be a measure of the carbon efficiency; and a soft sensing system was built to make an online estimation of the CCR. First, the sintering process was analyzed, and the key characteristics of the process parameters were extracted. Then, the configuration of the soft sensing system was devised based on the characteristics of the process. The system consists of three parts: an image selection, an image segmentation, and a hybrid just-in-time learning soft sensor (HJITL-SS). First, an image selection method was devised to automatically select the key frames (KFs) from the video taken at the discharge end of the sintering machine. Then, a genetic-algorithm-based fuzzy c-means clustering method was devised to extract feature parameters from the KFs. Finally, an HJITL-SS, which consists of online and offline submodels, was devised to estimate the CCR using the extracted feature parameters as inputs. Actual run data were used to verify the validity of our system. Accuracy, overfitness, and error distribution of the HJITL-SS, offline, and JITL-based soft sensing methods were compared, which show the validity of the HJITL-SS. The actual run results also show the validity of the soft sensing system with 97% of the actual runs are in an acceptable range.     

铅锌烧结过程综合透气性的集成预测模型

针对铅锌烧结过程透气性的预测具有模型不确定性和输入变量不确定性等特点,建立了综合透气性智能集成预测模型.首先建立了基于满意聚类的T-S综合透气性预测模型,针对聚类后各子模型结论参数的辨识工作计算复杂、容易陷入局部极值的问题,将混合粒子群优化算法用于这些结论参数的辨识;然后利用灰色理论建立了时间序列综合透气性预测模型;最后利用信息熵技术将2个预测模型进行集成,以获得集成预测模型.选取实际生产过程中100组合格的数据,分别用以上3种预测模型来预测相应的综合透气性,其相对误差的平均值分别为2.1%.3.2%,1.8%.实验结果表明,本文提出的集成预测方法能够有效地克服不确定性带来的影响、提高综合透气性的预测精度.     

Modeling and optimization method featuring multiple operating modes for improving carbon efficiency of iron ore sintering process

Iron ore sintering is one of the most energy-consuming processes in steelmaking. Since its main source of energy is the combustion of carbon, it is important to improve the carbon efficiency to save energy and to reduce undesired emissions. A modeling and optimization method based on the characteristics of the sintering process has been developed to do that. It features multiple operating modes and employs the comprehensive carbon ratio (CCR) as a measure of carbon efficiency. The method has two parts. The first part is the modeling of multiple operating modes of the sintering process. K-means clustering is used to identify the operating modes; and for each mode, a predictive model is built that contains two submodels, one for predicting the state parameters and one for predicting the CCR. The submodels are built using back-propagation neural networks (BPNNs). An analysis of material and energy flow, and correlation analyses of process data and the CCR, are used to determine the most appropriate inputs for the submodels. The second part of the method is optimization based on a determination of the optimal operating mode. The problem of how to reduce the CCR is formulated as a two-step optimization problem, and particle swarm optimization is used to solve it. Finally, verification of the modeling and optimization method based on actual process data shows that it improves the carbon efficiency of iron ore sintering.