基于大数据的锻造生产过程模型的搭建与分析
|
摘要
锻造生产车间中的工业大数据是重要资源,可实时反映出当前锻造生产过程中所反映的状态,然而有些锻造生产厂往往会产生数据采集不上来、数据无法利用等瓶颈。针对这些问题,在基于智能制造新模式的背景下,采集到了锻造实时全流程数据,对影响产品的各质量数据类型进行了归纳总结,分析了各因素对产品质量的影响,利用特征提取等一系列方法,对锻造生产过程中的几个主要影响因素进行分析。在找出影响锻造过程数据的几种重要因素的基础上,针对某一种情况运用Kmeans算法对该流程进行了验证,得出了准确的生产模型。
Industrial big data in the forging production workshop is an important resource,which can reflect the status of the current forging production process in real-time. However,some forging production plants often have bottlenecks such as data collection and data utilization. For these problems,based on the new model of intelligent manufacturing,the data of forging full-process in real-time were collected,and the types of quality data affecting products were summarized. Furthermore,the influences of various factors on product quality were analyzed,and several main influencing factors in forging process were analyzed by a series of methods such as feature extraction.Based on the identification of several important factors affecting the data of forging process,the process for a certain situation was verified by the Kmeans algorithm,and an accurate production model was obtained.
Industrial big data in the forging production workshop is an important resource,which can reflect the status of the current forging production process in real-time. However,some forging production plants often have bottlenecks such as data collection and data utilization. For these problems,based on the new model of intelligent manufacturing,the data of forging full-process in real-time were collected,and the types of quality data affecting products were summarized. Furthermore,the influences of various factors on product quality were analyzed,and several main influencing factors in forging process were analyzed by a series of methods such as feature extraction.Based on the identification of several important factors affecting the data of forging process,the process for a certain situation was verified by the Kmeans algorithm,and an accurate production model was obtained.
引文
[1]倪骏.运用大数据思维锻造“编辑力”---浅议现代企业制度下的总编办工作[J].编辑学刊,2018,(4):62-65.Ni J.Applying big data thinking to forge‘editing power’-On the general compilation work under the modern enterprise system[J].Editorial Journal,2018,(4):62-65.
[2]酆亚楠,孙勇,苏畅,等.离散锻造企业数据采集系统的实施与应用[J].锻压技术,2018,43(5):162-166.Feng Y N,Sun Y,Su C,et al.Implementation and application of data acquisition system for discrete forging enterprises[J].Forging&Stamping Technology,2018,43(5):162-166.
[3]陈奎.基于机电液联合仿真的液压机锻造精度与速度参数匹配技术及其应用[D].杭州:浙江大学,2015.Chen K.Hydraulic Machine Forging Precision and Speed Parameter Matching Technology Based on Electromechanical Fluid Combined Simulation and its Application[D].Hangzhou:Zhejiang University,2015.
[4]马士龙,张来成.锻造数据生命线[J].数据,2005,(10):44-46.Ma S L,Zhang L C.Forging data lifeline[J].Data,2005,(10):44-46.
[5]黄昕宇,张栋良,李帅位.基于改进模糊支持向量机的汽轮机热耗率预测模型[J].热力发电,2019,(3):22-27.Huang X Y,Zhang D L,Li S W.Steam turbine heat rate prediction model based on improved fuzzy support vector machine[J].Thermal Power Generation,2019,(3):22-27.
[6]胡健,朱海湾,毛伊敏.基于自适应蜂群优化的DBSCAN聚类算法[J].计算机工程与应用,2019,(2):1-17.Hu J,Zhu H W,Mao Y M.DBSCAN clustering algorithm based on adaptive bee colony optimization[J].Computer Engineering and Application,2019,(2):1-17.
[7]贾彬,梁毅,苏航.一种改进的K-Modes聚类算法[J].软件导刊,2019,(3):1-6.Jia B,Liang Y,Su H.An improved K-Modes clustering algorithm[J].Software Guide,2019,(3):1-6.
[8]杨静雅,孙林夫,吴奇石.基于半监督谱聚类集成的售后客户细分[J].计算机工程与应用,2019,(3):1-8.Yang J Y,Sun L F,Wu Q S.After-sales customer segmentation based on semi-supervised spectral clustering integration[J].Computer Engineering and Applications,2019,(3):1-8.
[9]张波,李舸.基于改进聚类算法的Web异常数据挖掘软件设计[J].现代电子技术,2019,(3):1-7.Zhang B,Li K.Design of Web anomaly data mining software based on improved clustering algorithm[J].Modern Electronic Technology,2019,(3):1-7.
[10]古新展,陈文天,战跃福.模糊C均值聚类算法在肺部CT图像感兴趣区域特征提取中的临床应用研究[J].中国医学装备,2019,(2):20-23.Gu X Z,Chen W T,Zhan Y F.Clinical application of fuzzy C-means clustering algorithm in feature extraction of CT images of lungs[J].China Medical Equipment,2019,(2):20-23.
[11]董安平.让材料热制造更智能,让材料加工更高效---材料智能热制造论坛侧记[J].中国材料进展,2017,36(11):802-803.Dong A P.Make material heat manufacturing smarter,make material processing more efficient-material intelligent thermal manufacturing forum side note[J].China Material Progress,2017,36(11):802-803.
[12]白雪.基于类等势场法的锻造预成形优化设计研究[D].济南:山东大学,2013.Bai X.Research on Forging Pre-form Optimization Design Based on Equipotential Field Method[D].Jinan:Shandong University,2013.
[13]段博文.基于现场总线的锻造生产线控制系统研究及应用[D].沈阳:东北大学,2012.Duan B W.Research and Application of Forging Production Line Control System Based on Field Bus[D].Shenyang:Northeastern University,2012.
[2]酆亚楠,孙勇,苏畅,等.离散锻造企业数据采集系统的实施与应用[J].锻压技术,2018,43(5):162-166.Feng Y N,Sun Y,Su C,et al.Implementation and application of data acquisition system for discrete forging enterprises[J].Forging&Stamping Technology,2018,43(5):162-166.
[3]陈奎.基于机电液联合仿真的液压机锻造精度与速度参数匹配技术及其应用[D].杭州:浙江大学,2015.Chen K.Hydraulic Machine Forging Precision and Speed Parameter Matching Technology Based on Electromechanical Fluid Combined Simulation and its Application[D].Hangzhou:Zhejiang University,2015.
[4]马士龙,张来成.锻造数据生命线[J].数据,2005,(10):44-46.Ma S L,Zhang L C.Forging data lifeline[J].Data,2005,(10):44-46.
[5]黄昕宇,张栋良,李帅位.基于改进模糊支持向量机的汽轮机热耗率预测模型[J].热力发电,2019,(3):22-27.Huang X Y,Zhang D L,Li S W.Steam turbine heat rate prediction model based on improved fuzzy support vector machine[J].Thermal Power Generation,2019,(3):22-27.
[6]胡健,朱海湾,毛伊敏.基于自适应蜂群优化的DBSCAN聚类算法[J].计算机工程与应用,2019,(2):1-17.Hu J,Zhu H W,Mao Y M.DBSCAN clustering algorithm based on adaptive bee colony optimization[J].Computer Engineering and Application,2019,(2):1-17.
[7]贾彬,梁毅,苏航.一种改进的K-Modes聚类算法[J].软件导刊,2019,(3):1-6.Jia B,Liang Y,Su H.An improved K-Modes clustering algorithm[J].Software Guide,2019,(3):1-6.
[8]杨静雅,孙林夫,吴奇石.基于半监督谱聚类集成的售后客户细分[J].计算机工程与应用,2019,(3):1-8.Yang J Y,Sun L F,Wu Q S.After-sales customer segmentation based on semi-supervised spectral clustering integration[J].Computer Engineering and Applications,2019,(3):1-8.
[9]张波,李舸.基于改进聚类算法的Web异常数据挖掘软件设计[J].现代电子技术,2019,(3):1-7.Zhang B,Li K.Design of Web anomaly data mining software based on improved clustering algorithm[J].Modern Electronic Technology,2019,(3):1-7.
[10]古新展,陈文天,战跃福.模糊C均值聚类算法在肺部CT图像感兴趣区域特征提取中的临床应用研究[J].中国医学装备,2019,(2):20-23.Gu X Z,Chen W T,Zhan Y F.Clinical application of fuzzy C-means clustering algorithm in feature extraction of CT images of lungs[J].China Medical Equipment,2019,(2):20-23.
[11]董安平.让材料热制造更智能,让材料加工更高效---材料智能热制造论坛侧记[J].中国材料进展,2017,36(11):802-803.Dong A P.Make material heat manufacturing smarter,make material processing more efficient-material intelligent thermal manufacturing forum side note[J].China Material Progress,2017,36(11):802-803.
[12]白雪.基于类等势场法的锻造预成形优化设计研究[D].济南:山东大学,2013.Bai X.Research on Forging Pre-form Optimization Design Based on Equipotential Field Method[D].Jinan:Shandong University,2013.
[13]段博文.基于现场总线的锻造生产线控制系统研究及应用[D].沈阳:东北大学,2012.Duan B W.Research and Application of Forging Production Line Control System Based on Field Bus[D].Shenyang:Northeastern University,2012.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |