铝钨合金高温流变行为及神经网络本构关系模型
|
摘要
采用Gleeble-1500热模拟实验机研究铝钨合金在变形温度为450℃~540℃、应变速率为0.001s-1~1s-1下单道次压缩过程的高温流变行为。基于BP神经网络建立铝钨合金本构关系模型。在该模型中,输入变量为应变、应变速率和变形温度,输出变量为流变应力。与传统方法相比,该本构关系模型的测试数据可以为描述整个变形过程提供一个很好的代表性,也为开发铝钨合金本构关系提供方便和有效的途径。
The flow behaviors of the as-extruded aluminum-tungsten alloy were studied through single-pass compression experiments by using Gleeble1500 simulator within temperature range of 450℃~540℃ and strain rate range of 0.001s-1~1s-1.And the constitutive relationship model for this alloy was successfully developed by using BP neural network.In the proposed model,the input variables are strain,strain rate and temperature,while the flow stress is the output variable.It was found that the established constitutive relationship model could provide a good representation of the test data and better describe the whole deforming process compared with that by the traditional method.Moreover,the suggested model is available to provide a convenient and effective way to develop the constitutive relationship for aluminum-tungsten alloys.
The flow behaviors of the as-extruded aluminum-tungsten alloy were studied through single-pass compression experiments by using Gleeble1500 simulator within temperature range of 450℃~540℃ and strain rate range of 0.001s-1~1s-1.And the constitutive relationship model for this alloy was successfully developed by using BP neural network.In the proposed model,the input variables are strain,strain rate and temperature,while the flow stress is the output variable.It was found that the established constitutive relationship model could provide a good representation of the test data and better describe the whole deforming process compared with that by the traditional method.Moreover,the suggested model is available to provide a convenient and effective way to develop the constitutive relationship for aluminum-tungsten alloys.
引文
[1]中科院长春应用化学研究所.高性能钨铝合金增强铝基材料[J].技术与市场,2009.16(11):99
[2]黄鹏.低熔点高强度铝合金钎料制备与性能研究[D].杭州:浙江大学,2013
[3]崔恩强,王宝兵,肖旅.高强度铝合金ZL205A支座铸造技术[J].航天制造技术,2012.(10):35-38
[4]孙超.碳化硅颗粒增强铝基复合材料显微组织和力学性能的研究[D].长沙:中南大学,2012
[5]张璟伟.挤压铸造法制备Ti_2AlC颗粒增强铝基复合材料的组织及性能研究[D].哈尔滨:哈尔滨工业大学2012
[6]祝昌军.钨铝合金的制备、性能及合成机理的研究[D].长春:中科院长春应用化学研究所,2006
[7]元家钟,陈蓓京,陈利民等.世界粉末冶金工业一瞥[J].中国冶金,2005.15(9):4-8
[8]郑雪萍,李平,曲选辉等.世界粉末冶金行业的发展现状[J].稀有金属快报,2005.24(3):6-9
[9]刘咏,黄伯云,龙郑易等.从PM2004看世界粉末冶金的发展现状[J].粉末冶金材料科学与工程,2005.10(1):10-20.
[10]蔡韻,吴菊清.我国汽车粉末冶金零件发展动向趋势分析[J].新材料产业,2005.(1):60-62
[11]Bahrami A,Anijdan S H M,Hosseini H R M,et al.Effective parameters modeling in compression of an austenitic stainless steel using artificial neural network[J].Comput Mater Sci,2005.34:335-341
[12]Bhadeshia H K D H,Dimitriul R C,Forsikl S,et al.Performance of neural networks in materials science[J].Mater Sci Technol,2009.25:504-510
[13]林启权,李晓龙,朱远志等.2519铝合金本构关系的人工神经网络模型[J].湘潭大学自然科学学报,2004.26(3):112-115
[14]LIU Fang,SHAN De-bin,LV Yan,et al.Prediction of2A70aluminum alloy flow stress based on BP artificial neural network[J].Journal of Harbin Institute of Technology,2004.11(4):368-371
[15]王煜,孙志超,李志颖等.挤压态7075铝合金高温流变行为及神经网络本构模型[J].中国有色金属学报,2011.21(11):2880-2887
[16]Lin Gaoyong,Zhang Zhenfeng,Zhang Hui,et al.Study on the hot deformation behaviors of Al-Zn-Mg-Cu-Cr aluminum alloy[J].Acta Metallurgica Sinica,2008.21(2):109-115
[17]Zurada J M.Introduction to artificial neural networks[M].New York:West Publishing Co,1992
[18]Sellars C M,Mctegart W J.On the mechanism of hot deformation[J].Acta Metall,1966.14:1136-1138
[2]黄鹏.低熔点高强度铝合金钎料制备与性能研究[D].杭州:浙江大学,2013
[3]崔恩强,王宝兵,肖旅.高强度铝合金ZL205A支座铸造技术[J].航天制造技术,2012.(10):35-38
[4]孙超.碳化硅颗粒增强铝基复合材料显微组织和力学性能的研究[D].长沙:中南大学,2012
[5]张璟伟.挤压铸造法制备Ti_2AlC颗粒增强铝基复合材料的组织及性能研究[D].哈尔滨:哈尔滨工业大学2012
[6]祝昌军.钨铝合金的制备、性能及合成机理的研究[D].长春:中科院长春应用化学研究所,2006
[7]元家钟,陈蓓京,陈利民等.世界粉末冶金工业一瞥[J].中国冶金,2005.15(9):4-8
[8]郑雪萍,李平,曲选辉等.世界粉末冶金行业的发展现状[J].稀有金属快报,2005.24(3):6-9
[9]刘咏,黄伯云,龙郑易等.从PM2004看世界粉末冶金的发展现状[J].粉末冶金材料科学与工程,2005.10(1):10-20.
[10]蔡韻,吴菊清.我国汽车粉末冶金零件发展动向趋势分析[J].新材料产业,2005.(1):60-62
[11]Bahrami A,Anijdan S H M,Hosseini H R M,et al.Effective parameters modeling in compression of an austenitic stainless steel using artificial neural network[J].Comput Mater Sci,2005.34:335-341
[12]Bhadeshia H K D H,Dimitriul R C,Forsikl S,et al.Performance of neural networks in materials science[J].Mater Sci Technol,2009.25:504-510
[13]林启权,李晓龙,朱远志等.2519铝合金本构关系的人工神经网络模型[J].湘潭大学自然科学学报,2004.26(3):112-115
[14]LIU Fang,SHAN De-bin,LV Yan,et al.Prediction of2A70aluminum alloy flow stress based on BP artificial neural network[J].Journal of Harbin Institute of Technology,2004.11(4):368-371
[15]王煜,孙志超,李志颖等.挤压态7075铝合金高温流变行为及神经网络本构模型[J].中国有色金属学报,2011.21(11):2880-2887
[16]Lin Gaoyong,Zhang Zhenfeng,Zhang Hui,et al.Study on the hot deformation behaviors of Al-Zn-Mg-Cu-Cr aluminum alloy[J].Acta Metallurgica Sinica,2008.21(2):109-115
[17]Zurada J M.Introduction to artificial neural networks[M].New York:West Publishing Co,1992
[18]Sellars C M,Mctegart W J.On the mechanism of hot deformation[J].Acta Metall,1966.14:1136-1138