厚度预测模型的精度是影响厚度控制的重要因素.针对本项目国内水平领先、最宽幅的“1＋4”热连轧生产线，根据生产现场获取的5083宽幅铝合金中厚板实测数据，在研究分析关键影响因素的基础上，运用人工神经网络技术建立了铝合金宽幅中厚板厚度预测的BP神经网络模型.其相对误差在0．5％之内，高于已有模型预测精度，能实现高精度预报.应用模型预测了5052宽幅铝合金中厚板的出口厚度，结果表明，模型能较好的预测轧件厚度的变化，有很好的泛化能力.
The accuracy of the thickness prediction model is an important factor which was influenced the thick-ness control.Aiming at the “1+4”hot tandem rolling line which was domestic leading and most wide,Accord-ing to the processed measured data of as-rolled 5083 wild aluminum medium plates,a thickness prediction mod-el was developed by artificial neural network based on the analysis of key factors.The relative error of the model is within 0.5%,which is better than that of previous models.And the high-precision prediction for rolling thick-ness was achieved.The developed model was successfully to predict the thickness of 5052 wild aluminum medi-um plate and exhibited good generation ability.
参考文献
| [1] | 阮鹏跃.高性能铝合金厚板的生产技术及应用[J].轻金属,2011(07):3-8. |
| [2] | Liu Yude.Production of high performance aluminium al-loy plate and its application[J].East China Science &Technology,2014(06):407-407. |
| [3] | Fan Yutao .Hydraulic AGC roll gap control based on PID neural network[D].Harbin University of Science and Tecnology,2010. |
| [4] | Chen Qingan .Study on gauge set-up calculation in process of plate rolling[D].沈阳:东北大学,2010. |
| [5] | 用BP神经网络模型预测Ni-TiN镀层的耐腐蚀性能[J].功能材料,2014(13):13079-13081. |
| [6] | 刘彬,汤爱涛,潘复生,黄光杰,毛建军.基于参数优化的人工神经网络的AZ31镁合金力学性能预测模型[J].重庆大学学报,2011(03):44-49. |
| [7] | 刘莹莹,王焱.基于粗糙集和神经网络的薄带钢厚度预测[J].济南大学学报（自然科学版）,2014(02):110-113. |
| [8] | 郭斌,孟令启,杜勇,马生彪.基于GRNN神经网络的中厚板轧机厚度预测[J].中南大学学报（自然科学版）,2011(04):960-965. |
| [9] | 刘东东,王焱.基于RBF神经网络的热连轧精轧厚度的预报[J].济南大学学报（自然科学版）,2006(04):312-314. |
| [10] | Wang Ailun;Shu Chang.Application of neural network and spring equation to thickness prediction in aluminum hot tandem rolling[J].Aluminum Processing,2007(01):5-9. |
| [11] | Sun Tao .Development and application of high accuracy gauge control for plate mill[D].Northeastern Universi-ty,2009. |
| [12] | Hecht-Nielsen R.Theory of the backpropagation neural network[A].,1989 |
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%