用人工神经网络研究钢的硬度的影响因素
|
摘要
用人工神经网络研究了化学成分及热处理工艺参数对低碳低合金钢的硬度的影响。首先设计了RBF型人工神经网络模型,用"舍一法"改进了模型,使其具有较好的预测性能。然后,用神经网络研究了化学成分和冷速对低碳低合金钢的硬度的定量影响。结果表明,碳的质量分数为0.11%～0.15%时,硬度随碳含量的增加而增大;硅的质量分数为0.24%～0.38%、锰的质量分数为0.94%～1.02%时,硬度值基本不变;铬的质量分数为0～0.6%时,硬度值呈增加趋势;镍的质量分数为0～0.04%时,硬度值基本不变;钼的质量分数为0～0.2%时,硬度值从HV 288降至HV 282;硼的质量分数为1%～2%时,硬度随含量增加而升高;钛、铌、钒的总质量分数为0.06%～0.14%时,硬度值基本不变;冷速从10℃/m增加至170℃/m,硬度值从HV 290增至HV 420。
The artificial neural network was used to research the influence of chemical composition and heat retreatment parameters on the hardness of the steel.Firstly,RBF artificial neural network was established to analyze the relationship of the chemical compositions-cooling rate-hardness,using the method of 'eave-one-out' to practice the model to achieve good prediction performance.Then,quantitative influence of composition and cooling rate on the hardness of low carbon and low alloy steels was investigated using the neural network.The result shows that,the hardness increases with the carbon content from 0.11% to 0.15%;while silicon content is 0.24%-0.38% and manganese content is 0.94%-1.02%,the hardness value basically unchanged;The hardness value has the increasing trend with chrome content is in 0-0.6%;While nickel content is 0-0.04%,hardness value basically unchanged;molybdenum content is 0-0.2%,hardness value falls from HV 288 to HV 282;With boron content rises from 1% to 2%,hardness increases;The total content of vanadium,titanium,niobium changes between 0.06%-0.14%,the hardness value basically unchanged;Cooling rate increases from 10 to 170 ℃/m,hardness value increases from HV 290 to HV 420.
The artificial neural network was used to research the influence of chemical composition and heat retreatment parameters on the hardness of the steel.Firstly,RBF artificial neural network was established to analyze the relationship of the chemical compositions-cooling rate-hardness,using the method of 'eave-one-out' to practice the model to achieve good prediction performance.Then,quantitative influence of composition and cooling rate on the hardness of low carbon and low alloy steels was investigated using the neural network.The result shows that,the hardness increases with the carbon content from 0.11% to 0.15%;while silicon content is 0.24%-0.38% and manganese content is 0.94%-1.02%,the hardness value basically unchanged;The hardness value has the increasing trend with chrome content is in 0-0.6%;While nickel content is 0-0.04%,hardness value basically unchanged;molybdenum content is 0-0.2%,hardness value falls from HV 288 to HV 282;With boron content rises from 1% to 2%,hardness increases;The total content of vanadium,titanium,niobium changes between 0.06%-0.14%,the hardness value basically unchanged;Cooling rate increases from 10 to 170 ℃/m,hardness value increases from HV 290 to HV 420.
引文
[1]由伟.人工神经网络预测新型空冷贝氏体钢的CCT图[D].北京:清华大学材料系,2004.
[2]Senuma T,Suehiro M,Yada H.Mathematical Models for Pre-dicting Microstructural Evolution and Mechannical Properties ofHot Strip[J].ISIJ International,1992,32(3):423.
[3]康大韬,郭成熊.工程用钢的组织转变与性能图册[M].北京:机械工业出版社,1992.
[4]Hecht-Nielsen.Neurocomputing[M].Massachussetes:Addi-son Wesley Publishing Co Inc,1991.
[5]Dobrzanski L A,Sitek W.Comparison of Hardenability Calcu-lation Methods of the Heat-Treatable Constructional Steels[J].Journal of Materials Processing Technology,1997(64):117.
[6]Dobrzanski L A,Sitek W.Application of Neural Network inModeling of Hardenability of Constructional Steels[J].Journalof Materials Processing Technology,1998(78):59.
[7]LIU Z Y,WANG W D,GAO W.Prediction of the MechanicalProperties of Hot-Rolled C-Mn Steels Using Artificial NeuralNetworks[J].J Master Proc Tech,1996(57):332.
[8]牛济泰,孙雷剑,李海涛.基于人工神经网络的微合金钢热轧奥氏体晶粒尺寸模型的研究[J].材料科学与工艺,1999,7(1):12.
[9]由伟,白秉哲,方鸿生.钢的连续冷却转变图的神经网络计算模型及预测软件设计[J].金属热处理,2004,29(7):17.
[10]The No.1Iron Factory,Benxi Iron,Steel Corporation,Tsin-ghua University.The Atlas of Super-Cooling AusteniteTransformation Diagram[M].Benxi:The No.1Iron FactoryPress,Benxi Iron and Steel Corporation,1978.
[11]American Society for Metals.Atlas of Isothermal Transforma-tion and Cooling Transformation Diagrams[M].Ohio:Amer-ican Society for Metals Press,1977.
[12]ZHANG S Z.Atlas of Super-Cooling Austennite Transforma-tion Diagrams[M].Beijing:Beijing Metallurgy IndustryPress,1993.
[13]Japan Society for Irons and Steels.Atlas of CCT of Weiding Steels[M].Tokyo:Japan Society for Irons and Steels Press,1992.
[14]Japan Society for Irons and Steels.Atlas of Continous CoolingTransformation Diagrams of Low Carbon Steels[M].Tokyo:Japan Society for Irons and Steels Press,1992.
[15]Narayan V,Abad R,Bhadeshia HK D H.Estimation of HotTorsion Stress Strain Curves in Iron Alloys Using Neural Net-work Analysis[J].ISIJ International,1999,39(10):999.
[16]吴耿峰,王炜.径向基函数(RBF)神经网络及其应用[J].地震学报,2005,25(2):82.
[17]So Sung-Sau,Martin Karplus.Evolutionnary Optimization inQuantiative Structure-Activity Relationship:An Applicationof Genetic Neural Networks[J].Journal of Medical Chemis-try,1996,39(7):1524.
[18]余宗森.钢的成分、残留元素及其性能的定量关系[M].北京:冶金工业出版社,2001.
[19]崔忠圻,覃耀春.金属学与热处理[M].2版.北京:机械工业出版社,2007.
[2]Senuma T,Suehiro M,Yada H.Mathematical Models for Pre-dicting Microstructural Evolution and Mechannical Properties ofHot Strip[J].ISIJ International,1992,32(3):423.
[3]康大韬,郭成熊.工程用钢的组织转变与性能图册[M].北京:机械工业出版社,1992.
[4]Hecht-Nielsen.Neurocomputing[M].Massachussetes:Addi-son Wesley Publishing Co Inc,1991.
[5]Dobrzanski L A,Sitek W.Comparison of Hardenability Calcu-lation Methods of the Heat-Treatable Constructional Steels[J].Journal of Materials Processing Technology,1997(64):117.
[6]Dobrzanski L A,Sitek W.Application of Neural Network inModeling of Hardenability of Constructional Steels[J].Journalof Materials Processing Technology,1998(78):59.
[7]LIU Z Y,WANG W D,GAO W.Prediction of the MechanicalProperties of Hot-Rolled C-Mn Steels Using Artificial NeuralNetworks[J].J Master Proc Tech,1996(57):332.
[8]牛济泰,孙雷剑,李海涛.基于人工神经网络的微合金钢热轧奥氏体晶粒尺寸模型的研究[J].材料科学与工艺,1999,7(1):12.
[9]由伟,白秉哲,方鸿生.钢的连续冷却转变图的神经网络计算模型及预测软件设计[J].金属热处理,2004,29(7):17.
[10]The No.1Iron Factory,Benxi Iron,Steel Corporation,Tsin-ghua University.The Atlas of Super-Cooling AusteniteTransformation Diagram[M].Benxi:The No.1Iron FactoryPress,Benxi Iron and Steel Corporation,1978.
[11]American Society for Metals.Atlas of Isothermal Transforma-tion and Cooling Transformation Diagrams[M].Ohio:Amer-ican Society for Metals Press,1977.
[12]ZHANG S Z.Atlas of Super-Cooling Austennite Transforma-tion Diagrams[M].Beijing:Beijing Metallurgy IndustryPress,1993.
[13]Japan Society for Irons and Steels.Atlas of CCT of Weiding Steels[M].Tokyo:Japan Society for Irons and Steels Press,1992.
[14]Japan Society for Irons and Steels.Atlas of Continous CoolingTransformation Diagrams of Low Carbon Steels[M].Tokyo:Japan Society for Irons and Steels Press,1992.
[15]Narayan V,Abad R,Bhadeshia HK D H.Estimation of HotTorsion Stress Strain Curves in Iron Alloys Using Neural Net-work Analysis[J].ISIJ International,1999,39(10):999.
[16]吴耿峰,王炜.径向基函数(RBF)神经网络及其应用[J].地震学报,2005,25(2):82.
[17]So Sung-Sau,Martin Karplus.Evolutionnary Optimization inQuantiative Structure-Activity Relationship:An Applicationof Genetic Neural Networks[J].Journal of Medical Chemis-try,1996,39(7):1524.
[18]余宗森.钢的成分、残留元素及其性能的定量关系[M].北京:冶金工业出版社,2001.
[19]崔忠圻,覃耀春.金属学与热处理[M].2版.北京:机械工业出版社,2007.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心