摘要
转炉炼钢过程中碳温连续实时预报是终点控制的关键,针对过程数据波动影响炉次样本相似性度量进而造成建模困难、通用性差的问题,同时考虑炼钢过程数据存在的时间序列特性,提出一种自动聚类和计算待测样本后验概率的即时学习方法.首先,采用灰色关联度加权的模糊C聚类策略将历史库样本进行自动聚类;然后,利用混合高斯模型计算待测样本的后验概率确定关联度最大的样本集合;最后,度量出待测样本的最佳小样本子集,进而采用LSTM网络预测终点碳温.通过该方法对钢厂转炉炼钢生产过程数据进行验证,实验结果表明,按照炼钢的工艺要求,温度预测误差在±10℃的精确率为93.3%,碳含量预测误差在±0.02的精精确率为90.0%.
Continuous real-time prediction of carbon and temperature is the key to the end point control in the process of converter steelmaking. Aiming at the problem that the fluctuation of process data affects the similarity measurement of furnace samples, which causes difficulties in modeling and poor generality, the time series characteristics of steelmaking process data are also considered, a real-time learning method of automatic clustering and calculating the posterior probability of samples to be tested is proposed. Firstly, the fuzzy C clustering strategy weighted by grey relational degree is adopted to automatically cluster the historical database samples. Then, the mixed Gaussian model is used to calculate the posterior probability of samples to be tested to determine the sample set with the largest correlation degree. Finally,the best small sample is measured out from a subset of the samples under test to predict end point carbon temperature with the LSTM network. Through the method of data verification, steel converter steelmaking experimental results show that,in accordance with requirements of the steelmaking process, the temperature prediction error on the accuracy of ± 10℃ is 93.33 %, the accuracy of carbon content of the prediction error in ± 0.02 % is 90.0 %.
作者
刘辉
曾鹏飞
LIU Hui;ZENG Peng-fei(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China;Yunnan Key Laboratory of Artificial Intelligence,Kunming University of Science and Technology,Kunming 650500,China)
出处
《控制与决策》
EI
CSCD
北大核心
2021年第9期2170-2178,共9页
Control and Decision
基金
国家自然科学基金项目(61863018)
云南省科技厅应用基础研究项目(202001AT070038)。
