锻压技术

无缝钢管斜轧穿孔管形多目标预测

英文标题：Multi-objective prediction on cross-rolling and perforated pipe shape for seamless steel pipe

分类号：TP183

出版年,卷(期):页码：2022,47(10):169-175

摘要：

针对无缝钢管斜轧穿孔生产中工艺参数对毛管尺寸精度的影响问题，考虑生产工艺以及生产需求优化等因素，建立了基于最小二乘支持向量回归的多目标预测模型。通过灰色关联分析法对影响因素进行分析筛选，以前伸量、轧辊间距、导板间距、顶头直径、坯料直径5个工艺参数作为预测模型的输入，以毛管壁厚和外径2个管形参数作为预测模型的输出；考虑到数据样本小且输入和输出参数之间的交叉相关性问题，构建了多输入多输出最小二乘支持向量回归模型对毛管管形进行预测。将实际采集的数据作为训练样本，通过仿真实验证明了模型的有效性，研究结果可为无缝钢管斜轧穿孔生产过程中所需的工艺参数调整与优化提供参考。

In view of the influence of process parameters on the dimensional accuracy of capillaky in the cross-rolling and preforating production of seamless steel pipe, a multi-objective prediction model based on least squares support vector machine was established considering the factors of production process and production demand optimization, and the influencing factors were analyzed and screened by the grey correlation analysis method. Then, taking five process parameters of forward extension amount, roll spacing, guide plate spacing, plug diameter and blank diameter as inputs of the prediction model and the two pipe shape parameters of capillary wall thickness and outer diameter as outputs of the prediction model, considering the small data sample and the cross correlation between input and output parameters, a multi-input and multi-output least squares support vector regression model was constructed to predict the capillary shape. Furthermore, taking the actual data as training samples, the effectiveness of the model was proved by simulation experiments. And the research results provide reference for the adjustment and optimization of the process parameters required in the cross-rolling and preforating production process of seamless steel pipe.

基金项目：

山西省科技重大专项(20191102009)

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

参考文献：

[1]栾治伟, 张文新, 王柏琳, 等. 无缝钢管热轧生产过程中的轧辊孔型匹配问题[J]. 计算机集成制造系统, 2017,23(12): 2676-2682.

Luan Z W, Zhang W X, Wang B L, et al. Roller pass matching problem for hotrolled seamless steel tube [J]. Computer Integrated Manufacturing Systems, 2017, 23(12): 2676-2682.

[2]双远华, 王付杰, 王清华. 无缝钢管连续斜轧工艺与设备的探索[J]. 机械工程学报, 2017,53(10): 18-24.

Shuang Y H, Wang F J, Wang Q H. Explorative study of tandem skew rolling process and equipment for producing seamless steel tubes [J]. Journal of Mechanical Engineering, 2017, 53(10): 18-24.

[3]Zhang W Y, Ju D Y, Zhao H Y, et al. Fuzzy controller optimized by genetic algorithm for the molten metal level in the twin roll strip casting process[J]. Materials Science Forum, 2015, 833: 197-200.

[4]周华民, 高煌, 张云, 等. 注塑成型工艺参数自动设置与优化技术[J]. 精密成形工程, 2016,8(1): 7-13.

Zhou H M, Gao H, Zhang Y, et al. Automatic setting and optimization of injection molding process parameters[J]. Journal of Netshape Forming Engineering, 2016,8(1): 7-13.

[5]Son J, Lee D, Kim I, 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.

[6]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.

[7]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.

[8]Wang Z H, Liu Y M, Gong D Y, et al. A new predictive model for strip crown in hot rolling by using the hybrid AMPSOSVRbased approach[J]. Steel Research International, 2018,89(7): 1800003.

[9]Zhu X, Zhu Z. The generalized predictive control of bacteria concentration in marine lysozyme fermentation process[J]. Food Science & Nutrition, 2018,6(8): 2459-2465.

[10]Yusof Y, Kamaruddin S S, Husni H, et al. Forecasting model based on LSSVM and ABC for natural resource commodity[J]. International Journal of Computer Theory and Engineering, 2013,5(6): 906-909.

[11]Suykens J A K, Van Gestel T, De Brabanter J, et al. Least Square Support Vector Machine[M]. Singapore: World Scientific Publishing, 2002.

[12]Liu X, Zhu Q, Lu H. Modeling multiresponse surfaces for airfoil design with multiple-output-gaussian-process regression[J]. Journal of Aircraft, 2014, 51(3): 740-747.

[13]Xu S, An X, Qiao X, et al. Multi-output least-squares support vector regression machines[J]. Pattern Recognition Letters, 2013,34(9): 1078-1084.

[14]杨勇, 黄文波, 金裕成, 等. 基于MSVR和Arousal-Valence情感模型的表情识别研究[J]. 重庆邮电大学学报:自然科学版, 2016,28(6): 836-843.

Yang Y, Huang W B, Jin Y C, et al. A study of expression recognition based on MSVR and Arousal-Valence emotion model[J]. Journal of Chongqing University of Posts and Telecommunications: Natural Science Edition, 2016,28(6): 836-843.

[15]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.

服务与反馈：

【文章下载】【加入收藏】