重介旋流器分选过程智能控制策略研究与实现
|
摘要
为实现重介旋流器精煤灰分的稳定和分选数量效率的提高,以唐口选煤厂重介分选工艺为研究对象,针对其控制系统的多变量、非线性、强耦合、纯滞后等特点,提出了以PID反馈控制为基础、基于神经网络学习和带抗饱和积分控制为核心的前馈控制策略.针对该策略中的神经网络学习问题,构建了"多输入、两输出"的智能算法,即以精煤灰分和数量效率为输出目标的重介分选过程的多个输入变量BP神经网络算法,并用Python语言编制了针对该网络结构的BP算法程序;采集和分析了唐口选煤厂生产实时在线数据,并进行了相关训练和仿真模拟.结果表明:当输入层节点数为3,且在输入变量为入料灰分、入料压力、循环介质密度条件下,输出变量精煤灰分和数量效率的预测值与实际值间的误差平方和最小,为0.114.通过系统的工业化应用可以看出,采用智能控制的悬浮液密度偏差幅度为0.01 g/cm~3,仅为人工控制的1/6,同时密度曲线呈短周期(3～5 min)高频率波动,比人工控制速度提高了4倍左右.此外,密度智能控制系统的稳定运行时间可长达6 h,表明该智能策略在选煤厂具有较好的应用潜力.
To obtain steady clean coal ash and higher quantity efficiency of the heavy medium cyclone, the control strategy combined the PID feedback and feedforward of the neural network learning as well as the anti-saturation integral were investigated, which focuses on the multivariable, nonlinear, strong coupling and hysteretic control system in Tangkou Coal Preparation Plant. The intelligent algorithms of multi-input and two output variables were studied, namely, the BP neural network algorithm with multiple input variables for the heavy medium separation process were developed to output the clean coal ash and the quantity efficiency, which was programmed by the Python. The training and simulation of data collected from Tangkou Coal preparation Plant were conducted. The results show that three input variables of feed ash, feed pressure and circulating medium density could result in the least error sum of squares of 0.114 between the predicted and actual values. The industrial application of control system indicates that the deviation amplitude of suspension density is 0.01 g/cm~3, which is only 1/6 of that in manual control. The density curve presents high-frequency fluctuation with short cycle(3—5 min), about 4 times faster than manual control. Moreover, the intelligent control system could run more than 6 h. The above results indicate the excellent application potential of the control strategy.
To obtain steady clean coal ash and higher quantity efficiency of the heavy medium cyclone, the control strategy combined the PID feedback and feedforward of the neural network learning as well as the anti-saturation integral were investigated, which focuses on the multivariable, nonlinear, strong coupling and hysteretic control system in Tangkou Coal Preparation Plant. The intelligent algorithms of multi-input and two output variables were studied, namely, the BP neural network algorithm with multiple input variables for the heavy medium separation process were developed to output the clean coal ash and the quantity efficiency, which was programmed by the Python. The training and simulation of data collected from Tangkou Coal preparation Plant were conducted. The results show that three input variables of feed ash, feed pressure and circulating medium density could result in the least error sum of squares of 0.114 between the predicted and actual values. The industrial application of control system indicates that the deviation amplitude of suspension density is 0.01 g/cm~3, which is only 1/6 of that in manual control. The density curve presents high-frequency fluctuation with short cycle(3—5 min), about 4 times faster than manual control. Moreover, the intelligent control system could run more than 6 h. The above results indicate the excellent application potential of the control strategy.
引文
[1] 石焕,程宏志,刘万超.我国选煤技术现状及发展趋势[J].煤炭科学技术,2016,44(6):169-174.SHI Huan,CHENG Hongzhi,LIU Wanchao.Present status and development trend of China's coal preparation technology[J].Coal Science and Technology,2016,44(6):169-174.
[2] 吴式瑜.提高重介质选煤技术促进我国选煤业发展[J].煤炭加工与综合利用,2008(4):1-4.WU Shiyu.Promoting the development of Chinese coal preparation by upgrading the HM cleaning technology[J].Coal Processing & Comprehensive Utilization,2008(4):1-4.
[3] 殷海宁.重介质选煤自动控制技术的发展[J].选煤技术,2006(增1):46-49.YIN Haining.Development of automatic control technology of dense medium coal preparation[J].Coal Preparation Technology,2006(Sup1):46-49.
[4] 张士聪.180万吨重介选煤自动控制系统的设计与开发[D].太原:太原理工大学,2011:49-53.ZHANG Shicong.Design and development of auto-controlling system of 1.8 million tons of heavy media coal preparation[D].Taiyuan:Taiyuan University of Technology,2011:49-53.
[5] 赵春祥,叶桂森.重介质选煤过程控制模型及控制算法的研究[J].煤炭学报,2000,25(增1):196-200.ZHAO Chunxiang,YE Guisen.Study of heavy-medium coal preparation process control model and control algorithm[J].Journal of China Coal Society,2000,25(Sup1):196-200.
[6] 尹春荣,范明栋,王忠青,等.重介选煤悬浮液密度及液位模糊控制方法的研究[J].矿山机械,2009(15):97-101.YIN Chunrong,FAN Mingdong,WANG Zhongqing,et al.Research on the fuzzy control methods for the density acid liquid levels of suspensions in dense-rnediucn separation[J].Mining & Processing Equipment,2009(15):97-101.
[7] 陈章宝.基于PLC的重介选煤工艺模糊控制的研究[D].淮南:安徽理工大学,2006:30-54.CHEN Zhangbao.The study of fuzzy control based on PLC in dense medium separation[D].Huainan:Anhui University of Science and Technology,2006:30-54.
[8] 郭西进,张志强,王广胜.重介选煤中密度与液位解耦控制研究[J].煤炭技术,2017(1):296-298.GUO Xijin,ZHANG Zhiqiang,WANG Guangsheng.Research on decoupling control method of density and level in dense medium coal preparation[J].Coal Technology,2017(1):296-298.
[9] 孟凡芹,王耀才,姜建国,等.重介工艺悬浮液密度和液位的多变量模糊控制方法研究[J].中国矿业大学学报,2005,34(2):252-255.MENG Fanqin,WANG Yaocai,JIANG Jianguo,et al.Study of multivariable fuzzy control for density and level of suspension in heavy media coal processing[J].Journal of China University of Mining & Technology,2005,34(2):252-255.
[10] 王海,李艳娟,巩亚东,等.基于PLC的Fuzzy-PID分选密度控制研究[J].控制工程,2006,13(5):474-477.WANG Hai,LI Yanjuan,GONG Yadong,et al.Fuzzy-PID algorithm of density control based on PLC[J].Control Engineering of China,2006,13(5):474-477.
[11] 王龙.基于模糊PID控制的选煤厂洗选质量控制[J].图书情报导刊,2007,17(16):174-175.WANG Long.The washing quality control in coal washery based on fuzzy PID[J].Sci-Tech Information Development & Economy,2007,17(16):174-175.
[12] 王占富.模糊PID控制系统在鲍店选煤厂的应用[J].选煤技术,2013(3):76-79.WANG Zhanfu.Application of fuzzy PID control system in Baodian coal preparation plant[J].Coal Preparation Technology,2013(3):76-79.
[13] 于春风,张天开,王倩.基于PLC与模糊控制器的选煤厂灰分监控系统的研发[J].选煤技术,2007(6):53-55.YU Chunfeng,ZHANG Tiankai,WANG Qian.Development of ash monitoring system for coal preparation plant based on PLC and fuzzy controller[J].Coal Preparation Technology,2007(6):53-55.
[14] BARBEE C,WOOD C,LUTTRELL G.Development of a transponder-based tracer system for evaluating dense medium separator performance[C]//Society for Mining,Metallurgy,and Exploration(U.S.).SME Annual Meeting and Exhibit 2008.Salt Lake City,Utah,USA:Society for Mining,Metallurgy and Exploration.2008:18-23.
[15] FIRTH B A.Dense medium cyclone control:A reconsideration[J].Coal Preparation,2009,29(3):112-129.
[16] SPENCER S,LIU Y.Statistical signal processing methods for acoustic emission monitoring of dense medium cyclones[C]//BOUZERDOUM A,BEGHDADI A.Proceedings of the 8th International Symposium on Signal Processing and Its Applications.Piscataway:IEEE,2005:875-878.
[17] 曹珍贯.重介选煤过程中重介质的密度预测控制研究[D].徐州:中国矿业大学,2014:49-69.CAO Zhenguan.Study of prediction control on heavy medium density in the process of coal preparation[D].Xuzhou:China University of Mining and Technology,2014:49-69.
[18] 曹珍贯,匡亚莉.隐式GPC算法在重介分选过程控制中的研究[J].计算机工程与应用,2014,50(12):6-10.CAO Zhenguan,KUANG Yali.Study on implicit GPC in process control of dense medium coal preparation[J].Computer Engineering and Applications,2014,50(12):6-10.
[19] 李国辉,孙经平,梁鑫.重介质选煤悬浮液密度智能给定系统设计[J].选煤技术,2015(6):74-76.LI Guohui,SUN Jingping,LIANG Xin.Design of intelligent given density system for dense medium suspension[J].Coal Preparation Technology,2015(6):74-76.
[20] 梁斌昌,赵建章,田树丹,等.基于BP神经网络的循环介质密度控制系统设计[J].选煤技术,2017(2):62-66.LIANG Binchang,ZHAO Jianzhang,TIAN Shudan,et al.Design of the circulation medium density control system based on BP neural network[J].Coal Preparation Technology,2017(2):62-66.
[21] 赵峻,褚涛,王碧秋.基于遗传神经网络的重介质密度预测控制[C]//中国煤炭学会自动化专业委员会.第十六届全国煤炭自动化学术年会、中国煤炭学会自动化专业委员会学术会议论文集,2006年.深圳:中国煤炭学会自动化专业委员会,2006:249-251.ZHAO Jun,CHU Tao,WANG Biqiu.Prediction control on dense medium density based on genetic neural network[C]// Automation Committee of China Coal Society.The Conference Proceedings of the 16th National Coal Automation Academic Annual Meeting,China Coal Association Automation Professional Committee Academic Meeting.Shenzhen:Automation Committee of China Coal Society,2006:249-251.
[22] 中国国家标准化管理委员会,中华人民共和国国家质量监督检验检疫总局.煤用重选设备工艺性能评定方法:GB/T 15715-2014[S].北京:中国标准出版社,2014:3-4.Standardization Administration of the People’s Republic of China,General Administration of Quality Supervision,Inspection and Quarantine of the People’s Republic of China.Performance evaluation for coal gravity separating equipment:GB/T 15715—2014[S].Beijing:Standards Press of China,2014:3-4.
[23] 谢广元.选矿学[M].徐州:中国矿业大学出版社,2016:211-306.XIE Guanyuan.Mineral processing[M].Xuzhou:China University of Mining and Technology Press,2016:211-306.
[24] YANG P H.Control design for a class of unstable nonlinear systems with input constraint[D].Berkeley:University of California,Berkeley,1998:68-75.
[2] 吴式瑜.提高重介质选煤技术促进我国选煤业发展[J].煤炭加工与综合利用,2008(4):1-4.WU Shiyu.Promoting the development of Chinese coal preparation by upgrading the HM cleaning technology[J].Coal Processing & Comprehensive Utilization,2008(4):1-4.
[3] 殷海宁.重介质选煤自动控制技术的发展[J].选煤技术,2006(增1):46-49.YIN Haining.Development of automatic control technology of dense medium coal preparation[J].Coal Preparation Technology,2006(Sup1):46-49.
[4] 张士聪.180万吨重介选煤自动控制系统的设计与开发[D].太原:太原理工大学,2011:49-53.ZHANG Shicong.Design and development of auto-controlling system of 1.8 million tons of heavy media coal preparation[D].Taiyuan:Taiyuan University of Technology,2011:49-53.
[5] 赵春祥,叶桂森.重介质选煤过程控制模型及控制算法的研究[J].煤炭学报,2000,25(增1):196-200.ZHAO Chunxiang,YE Guisen.Study of heavy-medium coal preparation process control model and control algorithm[J].Journal of China Coal Society,2000,25(Sup1):196-200.
[6] 尹春荣,范明栋,王忠青,等.重介选煤悬浮液密度及液位模糊控制方法的研究[J].矿山机械,2009(15):97-101.YIN Chunrong,FAN Mingdong,WANG Zhongqing,et al.Research on the fuzzy control methods for the density acid liquid levels of suspensions in dense-rnediucn separation[J].Mining & Processing Equipment,2009(15):97-101.
[7] 陈章宝.基于PLC的重介选煤工艺模糊控制的研究[D].淮南:安徽理工大学,2006:30-54.CHEN Zhangbao.The study of fuzzy control based on PLC in dense medium separation[D].Huainan:Anhui University of Science and Technology,2006:30-54.
[8] 郭西进,张志强,王广胜.重介选煤中密度与液位解耦控制研究[J].煤炭技术,2017(1):296-298.GUO Xijin,ZHANG Zhiqiang,WANG Guangsheng.Research on decoupling control method of density and level in dense medium coal preparation[J].Coal Technology,2017(1):296-298.
[9] 孟凡芹,王耀才,姜建国,等.重介工艺悬浮液密度和液位的多变量模糊控制方法研究[J].中国矿业大学学报,2005,34(2):252-255.MENG Fanqin,WANG Yaocai,JIANG Jianguo,et al.Study of multivariable fuzzy control for density and level of suspension in heavy media coal processing[J].Journal of China University of Mining & Technology,2005,34(2):252-255.
[10] 王海,李艳娟,巩亚东,等.基于PLC的Fuzzy-PID分选密度控制研究[J].控制工程,2006,13(5):474-477.WANG Hai,LI Yanjuan,GONG Yadong,et al.Fuzzy-PID algorithm of density control based on PLC[J].Control Engineering of China,2006,13(5):474-477.
[11] 王龙.基于模糊PID控制的选煤厂洗选质量控制[J].图书情报导刊,2007,17(16):174-175.WANG Long.The washing quality control in coal washery based on fuzzy PID[J].Sci-Tech Information Development & Economy,2007,17(16):174-175.
[12] 王占富.模糊PID控制系统在鲍店选煤厂的应用[J].选煤技术,2013(3):76-79.WANG Zhanfu.Application of fuzzy PID control system in Baodian coal preparation plant[J].Coal Preparation Technology,2013(3):76-79.
[13] 于春风,张天开,王倩.基于PLC与模糊控制器的选煤厂灰分监控系统的研发[J].选煤技术,2007(6):53-55.YU Chunfeng,ZHANG Tiankai,WANG Qian.Development of ash monitoring system for coal preparation plant based on PLC and fuzzy controller[J].Coal Preparation Technology,2007(6):53-55.
[14] BARBEE C,WOOD C,LUTTRELL G.Development of a transponder-based tracer system for evaluating dense medium separator performance[C]//Society for Mining,Metallurgy,and Exploration(U.S.).SME Annual Meeting and Exhibit 2008.Salt Lake City,Utah,USA:Society for Mining,Metallurgy and Exploration.2008:18-23.
[15] FIRTH B A.Dense medium cyclone control:A reconsideration[J].Coal Preparation,2009,29(3):112-129.
[16] SPENCER S,LIU Y.Statistical signal processing methods for acoustic emission monitoring of dense medium cyclones[C]//BOUZERDOUM A,BEGHDADI A.Proceedings of the 8th International Symposium on Signal Processing and Its Applications.Piscataway:IEEE,2005:875-878.
[17] 曹珍贯.重介选煤过程中重介质的密度预测控制研究[D].徐州:中国矿业大学,2014:49-69.CAO Zhenguan.Study of prediction control on heavy medium density in the process of coal preparation[D].Xuzhou:China University of Mining and Technology,2014:49-69.
[18] 曹珍贯,匡亚莉.隐式GPC算法在重介分选过程控制中的研究[J].计算机工程与应用,2014,50(12):6-10.CAO Zhenguan,KUANG Yali.Study on implicit GPC in process control of dense medium coal preparation[J].Computer Engineering and Applications,2014,50(12):6-10.
[19] 李国辉,孙经平,梁鑫.重介质选煤悬浮液密度智能给定系统设计[J].选煤技术,2015(6):74-76.LI Guohui,SUN Jingping,LIANG Xin.Design of intelligent given density system for dense medium suspension[J].Coal Preparation Technology,2015(6):74-76.
[20] 梁斌昌,赵建章,田树丹,等.基于BP神经网络的循环介质密度控制系统设计[J].选煤技术,2017(2):62-66.LIANG Binchang,ZHAO Jianzhang,TIAN Shudan,et al.Design of the circulation medium density control system based on BP neural network[J].Coal Preparation Technology,2017(2):62-66.
[21] 赵峻,褚涛,王碧秋.基于遗传神经网络的重介质密度预测控制[C]//中国煤炭学会自动化专业委员会.第十六届全国煤炭自动化学术年会、中国煤炭学会自动化专业委员会学术会议论文集,2006年.深圳:中国煤炭学会自动化专业委员会,2006:249-251.ZHAO Jun,CHU Tao,WANG Biqiu.Prediction control on dense medium density based on genetic neural network[C]// Automation Committee of China Coal Society.The Conference Proceedings of the 16th National Coal Automation Academic Annual Meeting,China Coal Association Automation Professional Committee Academic Meeting.Shenzhen:Automation Committee of China Coal Society,2006:249-251.
[22] 中国国家标准化管理委员会,中华人民共和国国家质量监督检验检疫总局.煤用重选设备工艺性能评定方法:GB/T 15715-2014[S].北京:中国标准出版社,2014:3-4.Standardization Administration of the People’s Republic of China,General Administration of Quality Supervision,Inspection and Quarantine of the People’s Republic of China.Performance evaluation for coal gravity separating equipment:GB/T 15715—2014[S].Beijing:Standards Press of China,2014:3-4.
[23] 谢广元.选矿学[M].徐州:中国矿业大学出版社,2016:211-306.XIE Guanyuan.Mineral processing[M].Xuzhou:China University of Mining and Technology Press,2016:211-306.
[24] YANG P H.Control design for a class of unstable nonlinear systems with input constraint[D].Berkeley:University of California,Berkeley,1998:68-75.