基于工业大数据的厚板板形预报系统研发  被引量:2

Research and development of thick plate shape prediction system based on industrial big data

在线阅读下载全文

作  者:马宇飞 刘长鑫 孔伟[2] 丁进良 MA Yufei;LIU Changxin;KONG Wei;DING Jinliang(State Key Laboratory of Synthetical Automation for Process Industries,Northeastern University,Shenyang 110819,China;Central Research Institute,Baoshan Iron&Steel Co.,Ltd.,Shanghai 201900,China)

机构地区:[1]东北大学流程工业综合自动化国家重点实验室,辽宁沈阳110819 [2]宝山钢铁股份有限公司中央研究院,上海201900

出  处:《物联网学报》2021年第3期39-48,共10页Chinese Journal on Internet of Things

基  金:国家重点研发计划(No.2018YFB1701104);辽宁省兴辽英才计划(No.XLYC1808001);辽宁省科技技术项目(No.2020JH2/10500001)。

摘  要:厚板板形是衡量厚板产品质量的重要指标之一,生产中最终板形的及时预报对于调整厚板生产操作与控制具有重要的意义。实际工业生产中,厚板数据具有耦合信息多、冗余信息量大、数据呈现多源异构性等特点,结合厚板板形预报的需求,设计并开发了厚板板形预报系统。利用数据转存功能,对工业大数据进行数据过滤和数据预处理,去除数据中的耦合信息和冗余变量。利用LSTM神经网络、卷积神经网络以及3D卷积神经网络对不同维度的数据分别提取数据特征,基于最大互信息系数将特征进行融合建立集成学习预报模型,有效地解决了多源异构数据所带来的建模困难。采用国内某厚板生产线的实际工业数据进行验证,结果证明了所开发系统的有效性。Thick plate shape is one of the important indicators to measure the quality of thick plate products.The timely prediction of the final plate shape in production is of great significance for adjusting the operation and control of thick plate production.In actual industrial production,thick plate data has many characteristics,such as multiple coupling information,large amount of redundant information,and multi-source heterogeneity of data.Combining the needs of thick plate shape prediction,a thick plate shape prediction system was designed and developed.The data dump function was used to filter and preprocess the industrial big data to remove the coupling information and redundant variables in the data.LSTM neural network,convolutional neural network and 3D convolutional neural network were used to extract data features from data of different dimensions,and the features were fused based on the maximum mutual information coefficient to establish an integrated learning prediction model,which effectively solved the modeling difficulties caused by multi-source heterogeneous data.The actual industrial data of a domestic thick plate production line was used for verification,and the results showed the effectiveness of the developed system.

关 键 词:厚板板形 预报模型 多源异构数据 系统开发 

分 类 号:TP18[自动化与计算机技术—控制理论与控制工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象