人工神经网络在轧钢中的应用综述
|
摘要
综述人工神经网络在轧制参数预报中的应用,包括轧制力能参数、组织性能和温度的预报;并介绍了混合人工神经网络模型与改进的人工神经网络模型,其中混合对象包括传统数学模型、有限元和其他智能算法.研究表明,人工神经网络在轧钢参数预报中具备很大的优势,能显著提高轧钢相关参数预报精度,提升轧材的品质.
The applications of artificial neural network(ANN)in the prediction of rolling parameters,including predictions of rolling force-energy parameters,micro-structure properties and temperature were reviewed.The hybrid artificial neural network and improved neural network models were introduced.The mixed objects include traditional mathematical models,finite element and other intelligent algorithms.The research shows that the artificial neural network have great advantages in prediction of rolling parameters,which can significantly improve prediction accuracy and the quality of rolled products.
The applications of artificial neural network(ANN)in the prediction of rolling parameters,including predictions of rolling force-energy parameters,micro-structure properties and temperature were reviewed.The hybrid artificial neural network and improved neural network models were introduced.The mixed objects include traditional mathematical models,finite element and other intelligent algorithms.The research shows that the artificial neural network have great advantages in prediction of rolling parameters,which can significantly improve prediction accuracy and the quality of rolled products.
引文
[1] ZHANG H C,HUANG S H.Applications of neural networks in manufacturing:A state-of-the-art survey[J].International Journal of Production Research,1995,33(3):705-728.
[2] BHADESHIA H K D H. Neuralnetworksin materials science[J].ISIJ International,1999,39(10):966-979.
[3] SCHLANG M,FELDKELLER B,LANG B,et al.Neural computation in steel industry[C]//Proceedings of European Control Conference.Karlsruhe:IEEE,1999:1-6.
[4] SCHLANG M,LANG B,POPPE T,et al.Current and future development in neural computation in steel processing[J].Control Engineering Practice,2001,9(9):975-986.
[5]刘相华,赵启林,黄贞益.人工智能在轧制领域中的应用进展[J].轧钢,2017(4):1-5.
[6]王建军,徐宗本.近似指数型神经网络的本质逼近阶[J].中国科学E辑:信息科学,2006,36(6):579-592.
[7]魏立群,卢冬华.基于BP网络的平整轧制压力计算[J].钢铁,2002,37(12):33-35.
[8] RATH S,SINGH A P,BHASKAR U,et al.Artificial neural network modeling for prediction of roll force during plate rolling process[J].Advanced Manufacturing Processes,2010,25(1/2/3):149-153.
[9] DIXIT U S,CHANDRA S.A neural network based methodology for the prediction of roll force and roll torque in fuzzy form for cold flat rolling process[J].The International Journal of Advanced Manufacturing Technology,2003,22(11/12):883-889.
[10] GARCIN T,MILITZER M,POOLE W J,et al.Microstructure model for the heat-affected zone of X80 linepipe steel[J].Materials Science and Technology,2016,32(7):708-721.
[11] NWACHUKWU P U,OLUWOLE O O.Effects of rolling process parameters on the mechanical properties of hot-rolled St60Mn steel[J].Case Studies in Construction Materials,2017,6:134-146.
[12] LIU S G,XIA C Q,FENG Z H,et al.Influence of phase composition and microstructure on mechanical properties of hot-rolled Ti-χZr-4Al-0.005B alloys[J].Journal of Alloys and Compounds,2018,751:247-256.
[13] LALAM S,TIWARI P K,SAHOO S,et al.Online prediction and monitoring of mechanical properties of industrial galvanised steel coils using neural networks[J].Ironmaking&Steelmaking,2017,44(9):1-8.
[14]井玉安,胡晓东,胡林,等.人工神经网络在热轧宽厚板力学性能预测中的应用[J].钢铁,2002,37(9):26-30.
[15]马文博,吴斌,朱天,等.基于径向基函数神经网络的热轧产品性能预测[J].广西师范大学学报(自然科学版),2010,28(3):182-186.
[16]吕志民,隋筱玥.基于多输入层遗传神经网络的热轧产品性能预测[J].数据采集与处理,2012,27(5):625-629.
[17] GORNI A A,CAVALCANTI C G.Modeling the controlledrollingcriticaltemperaturesusing empirical equations and neural networks[C]//Proceedings of 7th International Conference on Steel Rolling.Chiba:ISIJ,1998:1-5.
[18]贾春玉,李兴东,宋战.热轧带钢卷取温度高精度预报的人工神经网络方法[J].钢铁,2003(2):30-33.
[19] LEE D M,CHOI S G.Application of on-line adaptable neural network for the rolling force set-up of a plate mill[J].Engineering Applications of Artificial Intelligence,2004,17(5):557-565.
[20] SON J,LEE D M,KIM I S,et al.A study on on-line learning neural network for prediction for rolling force in hot-rolling mill[J].Journal of Materials Processing Technology,2005,164-165:1612-1617.
[21] CHO S,JANG M,YOON S,et al.A hybrid neuralnetwork/mathematical prediction model for tandem cold mill[J].Computers&Industrial Engineering,1997,33(3/4):453-456.
[22] LEE D,LEE Y.Application of neural-network for improving accuracy of roll-force model in hot-rolling mill[J].Control Engineering Practice,2002,10(4):473-478.
[23] SHAHANI A R,SETAYESHI S,NODAMAIE S A,et al.Prediction of influence parameters on the hot rolling process using finite element method and neural network[J].Journal of Materials Processing Technology,2009,209(4):1920-1935.
[24] YANG Y Y,LINKENS D A,TALAMANTESSILVA J,et al.Roll force and torque prediction using neural network and finite element modelling[J].ISIJ International,2003,43(12):1957-1966.
[25] YANG Y Y,LINKENS D A,TALAMANTESSILVA J.Roll load prediction-data collection,analysis and neural network modelling[J].Journal of Materials Processing Technology,2004,152(3):304-315.
[26] BAGHERIPOOR M,BISADI H.Application of artificial neural networks for the prediction of roll force and roll torque in hot strip rolling process[J].Applied Mathematical Modelling,2013,37(7):4593-4607.
[27] MAHMOODKHANI Y,WELLS M A,SONG G.Prediction of roll force in skin pass rolling using numerical and artificial neural network methods[J].Ironmaking&Steelmaking,2017,44(4):281-286.
[28] KANUMURI L,PUSHPALATHA D V,NAIDU A S K,et al.A Hybrid neural network-genetic algorithm for prediction of mechanical properties of ASS-304 at elevated temperatures[J].Materials Today:Proceedings,2017,4(2):746-751.
[29]杨景明,顾佳琪,闫晓莹,等.基于改进遗传算法优化BP网络的轧制力预测研究[J].矿冶工程,2015,35(1):111-115.
[30] CHAKRABORTY S,CHATTOPADHYAY P P,GHOSH S K,et al.Incorporation of prior knowledge in neural network model for continuous cooling of steel using genetic algorithm[J].Applied Soft Computing,2017,58:297-306
[31]杨景明,刘舒慧,车海军,等.一种结合模拟退火算法的BP网络冷连轧参数预报模型[J].钢铁,2008,43(7):55-58.
[32]杨景明,孙晓娜,车海军,等.基于蚁群算法的神经网络冷连轧机轧制力预报[J].钢铁,2009,44(3):52-55.
[33]杨景明,闫晓莹,顾佳琪,等.基于改进粒子群优化RBF神经网络的轧制力预报[J].矿冶工程,2014,34(6):110-113,118.
[34] KARAYIANNIS N B,VENETSANOPOULOS A N.Fast learning algorithms for neural networks[C]//Proceedings of the 1991 International Conference on Artificial Neural Networks.Espoo:ICANN,1991:1141-1144.
[35]ZNERGIZ E,GIILEZ K,ZSOY C.Neural network modeling of a plate hot-rolling process and comparison with the conventional techniques[C]//Proceedings of International Conference on Control and Automation.Barcelona:IEEE,2005:646-651.
[36] YANG Y Y,LINKENS D A,MAHFOUF M,et al.Grain growth modelling for continuous reheating process:A neural network-based approach[J].ISIJ International,2003,43(7):1040-1049.
[37] KIM H J,MAHFOUF M,YANG Y Y.Modelling of hot strip rolling process using a hybrid neural network approach[J].Journal of Materials Processing Technology,2008,201(1/2/3):101-105.
[38] JIA C Y,SHAN X Y,NIU Z P.High precision prediction of rolling force based on fuzzy and nerve method for cold tandem mill[J].Journal of Iron and Steel Research,International,2008,15(2):23-27.
[2] BHADESHIA H K D H. Neuralnetworksin materials science[J].ISIJ International,1999,39(10):966-979.
[3] SCHLANG M,FELDKELLER B,LANG B,et al.Neural computation in steel industry[C]//Proceedings of European Control Conference.Karlsruhe:IEEE,1999:1-6.
[4] SCHLANG M,LANG B,POPPE T,et al.Current and future development in neural computation in steel processing[J].Control Engineering Practice,2001,9(9):975-986.
[5]刘相华,赵启林,黄贞益.人工智能在轧制领域中的应用进展[J].轧钢,2017(4):1-5.
[6]王建军,徐宗本.近似指数型神经网络的本质逼近阶[J].中国科学E辑:信息科学,2006,36(6):579-592.
[7]魏立群,卢冬华.基于BP网络的平整轧制压力计算[J].钢铁,2002,37(12):33-35.
[8] RATH S,SINGH A P,BHASKAR U,et al.Artificial neural network modeling for prediction of roll force during plate rolling process[J].Advanced Manufacturing Processes,2010,25(1/2/3):149-153.
[9] DIXIT U S,CHANDRA S.A neural network based methodology for the prediction of roll force and roll torque in fuzzy form for cold flat rolling process[J].The International Journal of Advanced Manufacturing Technology,2003,22(11/12):883-889.
[10] GARCIN T,MILITZER M,POOLE W J,et al.Microstructure model for the heat-affected zone of X80 linepipe steel[J].Materials Science and Technology,2016,32(7):708-721.
[11] NWACHUKWU P U,OLUWOLE O O.Effects of rolling process parameters on the mechanical properties of hot-rolled St60Mn steel[J].Case Studies in Construction Materials,2017,6:134-146.
[12] LIU S G,XIA C Q,FENG Z H,et al.Influence of phase composition and microstructure on mechanical properties of hot-rolled Ti-χZr-4Al-0.005B alloys[J].Journal of Alloys and Compounds,2018,751:247-256.
[13] LALAM S,TIWARI P K,SAHOO S,et al.Online prediction and monitoring of mechanical properties of industrial galvanised steel coils using neural networks[J].Ironmaking&Steelmaking,2017,44(9):1-8.
[14]井玉安,胡晓东,胡林,等.人工神经网络在热轧宽厚板力学性能预测中的应用[J].钢铁,2002,37(9):26-30.
[15]马文博,吴斌,朱天,等.基于径向基函数神经网络的热轧产品性能预测[J].广西师范大学学报(自然科学版),2010,28(3):182-186.
[16]吕志民,隋筱玥.基于多输入层遗传神经网络的热轧产品性能预测[J].数据采集与处理,2012,27(5):625-629.
[17] GORNI A A,CAVALCANTI C G.Modeling the controlledrollingcriticaltemperaturesusing empirical equations and neural networks[C]//Proceedings of 7th International Conference on Steel Rolling.Chiba:ISIJ,1998:1-5.
[18]贾春玉,李兴东,宋战.热轧带钢卷取温度高精度预报的人工神经网络方法[J].钢铁,2003(2):30-33.
[19] LEE D M,CHOI S G.Application of on-line adaptable neural network for the rolling force set-up of a plate mill[J].Engineering Applications of Artificial Intelligence,2004,17(5):557-565.
[20] SON J,LEE D M,KIM I S,et al.A study on on-line learning neural network for prediction for rolling force in hot-rolling mill[J].Journal of Materials Processing Technology,2005,164-165:1612-1617.
[21] CHO S,JANG M,YOON S,et al.A hybrid neuralnetwork/mathematical prediction model for tandem cold mill[J].Computers&Industrial Engineering,1997,33(3/4):453-456.
[22] LEE D,LEE Y.Application of neural-network for improving accuracy of roll-force model in hot-rolling mill[J].Control Engineering Practice,2002,10(4):473-478.
[23] SHAHANI A R,SETAYESHI S,NODAMAIE S A,et al.Prediction of influence parameters on the hot rolling process using finite element method and neural network[J].Journal of Materials Processing Technology,2009,209(4):1920-1935.
[24] YANG Y Y,LINKENS D A,TALAMANTESSILVA J,et al.Roll force and torque prediction using neural network and finite element modelling[J].ISIJ International,2003,43(12):1957-1966.
[25] YANG Y Y,LINKENS D A,TALAMANTESSILVA J.Roll load prediction-data collection,analysis and neural network modelling[J].Journal of Materials Processing Technology,2004,152(3):304-315.
[26] BAGHERIPOOR M,BISADI H.Application of artificial neural networks for the prediction of roll force and roll torque in hot strip rolling process[J].Applied Mathematical Modelling,2013,37(7):4593-4607.
[27] MAHMOODKHANI Y,WELLS M A,SONG G.Prediction of roll force in skin pass rolling using numerical and artificial neural network methods[J].Ironmaking&Steelmaking,2017,44(4):281-286.
[28] KANUMURI L,PUSHPALATHA D V,NAIDU A S K,et al.A Hybrid neural network-genetic algorithm for prediction of mechanical properties of ASS-304 at elevated temperatures[J].Materials Today:Proceedings,2017,4(2):746-751.
[29]杨景明,顾佳琪,闫晓莹,等.基于改进遗传算法优化BP网络的轧制力预测研究[J].矿冶工程,2015,35(1):111-115.
[30] CHAKRABORTY S,CHATTOPADHYAY P P,GHOSH S K,et al.Incorporation of prior knowledge in neural network model for continuous cooling of steel using genetic algorithm[J].Applied Soft Computing,2017,58:297-306
[31]杨景明,刘舒慧,车海军,等.一种结合模拟退火算法的BP网络冷连轧参数预报模型[J].钢铁,2008,43(7):55-58.
[32]杨景明,孙晓娜,车海军,等.基于蚁群算法的神经网络冷连轧机轧制力预报[J].钢铁,2009,44(3):52-55.
[33]杨景明,闫晓莹,顾佳琪,等.基于改进粒子群优化RBF神经网络的轧制力预报[J].矿冶工程,2014,34(6):110-113,118.
[34] KARAYIANNIS N B,VENETSANOPOULOS A N.Fast learning algorithms for neural networks[C]//Proceedings of the 1991 International Conference on Artificial Neural Networks.Espoo:ICANN,1991:1141-1144.
[35]ZNERGIZ E,GIILEZ K,ZSOY C.Neural network modeling of a plate hot-rolling process and comparison with the conventional techniques[C]//Proceedings of International Conference on Control and Automation.Barcelona:IEEE,2005:646-651.
[36] YANG Y Y,LINKENS D A,MAHFOUF M,et al.Grain growth modelling for continuous reheating process:A neural network-based approach[J].ISIJ International,2003,43(7):1040-1049.
[37] KIM H J,MAHFOUF M,YANG Y Y.Modelling of hot strip rolling process using a hybrid neural network approach[J].Journal of Materials Processing Technology,2008,201(1/2/3):101-105.
[38] JIA C Y,SHAN X Y,NIU Z P.High precision prediction of rolling force based on fuzzy and nerve method for cold tandem mill[J].Journal of Iron and Steel Research,International,2008,15(2):23-27.