锻压技术

基于GRA的PSO-BP神经网络斜轧穿孔管形预测

英文标题：Prediction of pipe shape in cross-rolled piercing by PSO-BP neural network based on GRA

作者：王清华加世滢胡建华双远华赵铁琳

分类号：TP183

出版年,卷(期):页码：2022,47(8):88-94

摘要：

针对斜轧穿孔中无缝钢管管形计算复杂且精度不高的缺陷，提出了基于灰色关联度分析（GRA）的PSO-BP神经网络管形预测模型。由于轧制过程中影响管形的因素较多，通过灰色关联度分析对工艺参数进行了相关性分析,选择相关度较高的影响因素作为输入；并使用粒子群优化算法对BP神经网络进行优化，确定了最佳的神经网络结构，构建了无缝钢管的斜轧穿孔管形预测模型。最后，应用现场数据对该模型进行了训练和测试，并将其与BP神经网络和传统数学模型进行了对比分析。研究结果表明：该预测模型的精度较高、可靠性较好，为提高无缝钢管的生产质量奠定了基础。

For the defects of complicated calculation and low precision for pipe shape of seamless steel pipe in cross-rolled piercing, a pipe shape prediction model of PSO-BP neural network based on grey relational analysis was proposed. Since there were many factors affecting the pipe shape during the rolling process, the correlation analysis of the process parameters was carried out by the gray correlation analysis, and the influencing factors with higher correlation were selected as the input. Then, the BP neural network was optimized by particle swarm optimization algorithm, the optimal neural network structure was determined, and the pipe shape prediction model of cross-rolled piercing for seamless steel pipe was constructed. Finally, the model was trained and tested by field data and was compared with BP neural network and traditional mathe-matical models. The research results show that the prediction model has higher accuracy and better reliability, which lays a foundation for improving the production quality of seamless steel pipes.

基金项目：

山西省科技重大专项(20191102009)

作者简介：王清华（1980-），女，博士，讲师，E-mail：2002043@tyust.edu.cn；通信作者：加世滢（1996-），女，硕士研究生，E-mail：13103421357@163.com

参考文献：

[1]李群, 高秀华. 钢管生产[M]. 北京：冶金工业出版社, 2008.

Li Q,Gao X H. Steel Pipe Production[M]. Beijing：Metallurgical Industrial Press,2008.

[2]张进, 朱宝禄, 韩建新,等.连轧钢管的壁厚不均原因分析[J].钢管, 2013,42(1):55-58.

Zhang J,Zhu B L,Han J X, et al. Research on wall thickness inhomogeneity of steel pipe as rolled with mandrel mill[J]. Steel Pipe, 2013,42(1):55-58.

[3]李连诗. 钢管塑性变形原理(上册)[M]. 北京：冶金工业出版社, 1985.

Li L S. Plastic Deformation Principle of Steel Pipe (Volume I) [M]. Beijing: Metallurgical Industry Press,1985.

[4]双远华, 李国祯. 钢管斜轧理论及生产过程的数值模拟 [M]. 北京: 冶金工业出版社, 2001.

Shuang Y H,Li G Z. Numerical Simulation of Steel Pipe Slant Rolling Theory and Production Process[M]. Beijing:Metallurgical Industry Press, 2001.

[5]曹卫华, 李熙, 吴敏, 等. 基于极限学习机的热轧薄板轧制力预测模型[J]. 信息与控制, 2014,43(3): 270-275.

Cao W H,Li X,Wu M,et al.A rolling force prediction model for hot rolled sheets based on extreme learning machine [J].Information and Control,2014,43(3):270-275.

[6]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.

[7]Son J S, 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.

[8]高山凤, 刘鸿飞, 郗安民, 等. 热轧板带横向厚度分布的预测与控制[J].哈尔滨工业大学学报, 2016,48(1): 180-183.

Gao S F,Liu H F,Xi A M,et al.Prediction and control of thickness transverse distribution in hot rolling strip[J]. Journal of Harbin Institute of Technology,2016,48(1):180-183.

[9]双远华, 赖明道. 人工神经网络在预测斜轧穿孔毛管偏差中的应用[J]. 中国有色金属学报, 2001,(5): 862-866.

Shuang Y H,Lai M D.Application of artificial neural networks on predicting deviation of tube in cross piercing process[J].The Chinese Journal of Nonferrous Metals,2001,(5):862-866.

[10]肖冬, 潘孝礼, 毛志忠, 等. 基于步进子时段MICR方法的毛管质量预报[J]. 仪器仪表学报, 2007,28(12): 2190-2196.

Xiao D,Pan X L,Mao Z Z,et al. Quality prediction of tube hollow based on step-by-step staged MICR [J]. Chinese Journal of Scientific Instrument,2007,28(12):2190-2196.

[11]陈鑫, 朱明杰, 吴敏, 等. 结合机理计算与神经网络预测的无缝钢管轧制力建模[J].冶金自动化, 2015,39(4): 32-37.

Chen X,Zhu M J,Wu M,et al. Rolling force modeling for seamless steel pipe combining mechanism model and neural network prediction[J]. Metallurgical Industry Automation,2015,39(4):32-37.

[12]魏子茹, 卢延辉, 王鹏宇, 等. 基于CRITIC法的灰色关联理论在无人驾驶车辆测试评价中的应用[J]. 机械工程学报, 2021,57(12): 99-108.

Wei Z R,Lu Y H,Wang P Y,et al. Application of grey correlation theory based on CRITIC method in autonomous vehicles test and evaluation [J]. Journal of Mechanical Engineering,2021,57(12):99-108.

[13]Larkiola J, Myllykoski P, Korhonen A S, et al. The role of neural networks in the optimisation of rolling processes[J]. Journal of Materials Processing Technology, 1998,80-81: 16-23.

[14]Sun W, Xu Y F. Financial security evaluation of the electric power industry in China based on a back propagation neural network optimized by genetic algorithm[J]. Energy, 2016,101: 366-379.

[15]夏维, 刘新学, 范阳涛, 等. 基于混合遗传BP神经网络的城市系统作战能力评估[J]. 系统工程与电子技术, 2017,39(1): 107-113.

Xia W,Liu X X,Fan Y T,et al. Combat capability evaluation of city system based on mix-genetic algorithm BP neural network[J]. Systems Engineering and Electronics,2017,39(1):107-113.

[16]Wang J L, Shi P, Jiang P, et al. Application of BP neural network algorithm in traditional hydrological model for flood forecasting[J]. Water, 2017,9(1): 48.

[17]Yang Y Y, Linkens D A, Talamantes-silva J. Roll load prediction-Data collection, analysis and neural network modelling[J]. Journal of Materials Processing Technology, 2004,152(3): 304-315.

[18]Chen K, Yang S J, Batur C. Effect of multi-hidden-layer structure on performance of BP neural network: Probe[A]. Proceedings of 2012 8th International Conference on Natural Computation[C]. IEEE, 2012.

[19]Khan S U, Yang S Y, Wang L Y, et al. A modified particle swarm optimization algorithm for global optimizations of inverse problems[J]. IEEE Transactions on Magnetics, 2016,52(3): 1-4.

[20]毛志翔, 鲁世红, 李正芳, 等. 电加热渐进成形工艺参数优化及成形温度预测[J]. 热加工工艺, 2019,48(19): 100-103.

Mao Z X,Lu S H,Li Z F,et al.Optimization of process parameters and prediction of forming temperature for electro-heating incremental forming[J]. Hot Working Technology,2019,48(19):100-103.

服务与反馈：

【文章下载】【加入收藏】