纺织学报 ›› 2020, Vol. 41 ›› Issue (04): 161-166.doi: 10.13475/j.fzxb.20190101306

• 机械与器材 • 上一篇    下一篇

基于神经网络和遗传算法的锭子弹性管性能优化

莫帅1,2(), 冯战勇1,2, 唐文杰1,2, 党合玉1,2, 邹振兴1,2   

  1. 1.天津工业大学 机械工程学院, 天津 300387
    2.天津工业大学 天津市现代机电装备技术重点实验室, 天津 300387
  • 收稿日期:2019-01-08 修回日期:2020-01-12 出版日期:2020-04-15 发布日期:2020-04-27
  • 作者简介:莫帅(1987—),男,副教授。主要研究方向为现代纺织装备。E-mail: moshuai2010@163.com
  • 基金资助:
    国家自然科学基金项目(51805368);中国纺织工业联合会应用基础研究项目(J201806);中国科协青年人才托举工程项目(2018QNRC001);天津市自然科学基金项目(17JCQNJC04300)

Performance optimization of elastic spindle pipe based on neural network and genetic algorithm

MO Shuai1,2(), FENG Zhanyong1,2, TANG Wenjie1,2, DANG Heyu1,2, ZOU Zhenxing1,2   

  1. 1. School of Mechanical Engineering, Tiangong University, Tianjin 300387, China
    2. Tianjin Key Laboratory of Advanced Mechatronics Equipment Technology, Tiangong University, Tianjin 300387, China
  • Received:2019-01-08 Revised:2020-01-12 Online:2020-04-15 Published:2020-04-27

摘要:

为得到减振弹性管对下锭胆的支承弹性和锭子高速运动下的稳定性等性能的最优匹配效率,依据减振弹性管的等效抗弯刚度及底部等效刚度系数公式,利用MatLab数值分析软件构建弹性管抗弯刚度和底部挠度数学模型。首先,结合Isight优化软件基于径向基神经网络构建其近似模型,且使精度达到可接受水平,并以模型的关键结构参数弹性模量、螺距、槽宽、壁厚为设计变量,结合遗传算法对弹性管抗弯刚度和底部挠度进行多目标优化设计,得到Pareto最优解集和Pareto前沿图,确定出减振弹性管结构工艺参数的优化方案。通过对优化数据进行分析发现,该方案在保证减振弹性管弹性的同时,其底部振幅明显减弱。

关键词: 减振弹性管, 径向基神经网络, 遗传算法, 多目标优化, 锭子

Abstract:

The aim of this research is to improve the matching efficiency of the damping elastic tube to the support elasticity of the lower spindle and the stability of the spindle at high speeds. Using the formula of the damping equivalent bending stiffness and the equivalent stiffness coefficient of the bottom of the damping elastic tube, a mathematical model of the bending stiffness and the bottom deflection of the elastic tube was established and calculated using MatLab numerical analysis software. The approximate model of the elastic tube based on radial basis function neural network was combined with Isight optimization software attempting to increase the accuracy to an acceptable level. Taking the elastic modulus, pitch, slot width and wall thickness as the design variables, the multi-objective optimization design of the bending stiffness and bottom deflection of the elastic tube was combined with the genetic algorithm to obtain the Pareto optimal solution set and Pareto front map, leading to the determination of the vibration-damping elastic tube structure. The research results show that the vibration reduction of the elastic tube resulting in improved elastic performance, with a much reduced vibration amplitude at the base of the tube.

Key words: damping elastic tube, radial based neural network, genetic algorithm, multi-objective optimization, spindle

中图分类号: 

  • TP391

图1

弹性管实物及螺旋槽分析模型"

图2

弹性管底端振动示意图"

表1

不同卷绕比下应力系数β2值"

Φ 3.0 3.5 4.0 5.0
1.0 3.52 3.35 3.20 3.03
1.2 3.63 3.42 3.31 3.12
1.4 3.72 3.55 3.42 3.25
1.6 3.81 3.65 3.54 3.34
1.8 3.94 3.75 3.65 3.45
2.0 4.00 3.85 3.75 3.56
2.2 4.15 3.95 3.83 3.66
2.4 4.21 4.04 3.90 3.74
2.5 4.25 4.10 3.94 3.79

图3

弹性管抗弯刚度径向基神经网络模型"

图4

弹性管底部振幅径向基神经网络模型"

图5

刚度Jeq实际仿真值和近似模型预测值拟合对比"

图6

振幅A实际仿真值和近似模型预测值拟合对比"

表2

平均相对误差和R2值误差检验"

目标值 平均相对误差 R2
可接受水平 0.2 0.9
抗弯刚度Jeq 1.731 6×10-4 1
底部振幅A 0.015 87 0.990 67

图7

抗弯刚度Jeq和底部振幅A的Pareto前沿图"

表3

优化前后弹性管工艺参数对比"

状况 设计变量 目标响应
c/mm E/GPa h/mm p/mm Jeq/(N·m2) A/mm
优化前 1.00 207.0 1.850 9.00 0.46 0.388 7
优化后 1.51 208.2 1.602 9.53 0.52 0.119 9

图8

弹性管优化前后底部振幅的变化"

[1] 彭超英, 陈瑞琪, 朱均, 等. 纺纱锭子的研究和发展[J]. 纺织学报, 1995,16(6):54-55.
PENG Chaoying, CHEN Ruiqi, ZHU Jun, et al. Research and development of spinning spindles[J]. Journal of Textile Research, 1995,16(6):54-55.
[2] 吴文英, 相兴利, 蔡旭初. 锭子弹性管的刚度计算及其对动态性能的影响[J]. 东华大学学报(自然科学版), 2002,28(6):80-83.
WU Wenying, XIANG Xingli, CAI Xuchu. Calculation of stiffness of spindle elastic tube and its influence on dynamic performance[J]. Journal of Donghua University(Natural Science Edition), 2002,28(6):80-83.
[3] 王志勇, 张恒才. 锭子弹性管螺旋槽弹性的探讨[J]. 纺织器材, 2004,31(6):5-6.
WANG Zhiyong, ZHANG Hengcai. Discussion on the elasticity of spiral groove of spindle elastic tube[J]. Textile Accessories, 2004,31(6):5-6.
[4] 彭来深, 黄喜芝. 锭子弹性管同轴度与制造工艺的改进[J]. 纺织器材, 2015,42(3):12-14.
PENG Laishen, HUANG Xizhi. Improvement of concentricity and manufacturing process of spindle elastic tube[J]. Textile Accessories, 2015,42(3):12-14.
[5] 郝颖, 虞爱民. 层状复合材料矩形截面圆柱螺旋弹簧自由振动特性研究[J]. 振动与冲击, 2012,31(22):105-111.
HAO Ying, YU Aimin. Study on free vibration characteristics of cylindrical coiled spring with layered composites[J]. Journal of Vibration and Shock, 2012,31(22):105-111.
[6] 马彬彬, 谭继锦, 林彧群, 等. 基于径向基函数神经网络的车门轻量化设计[J]. 汽车工程学报, 2015,5(2):136-143.
MA Binbin, TAN Jijin, LIN Yuqun, et al. Lightweight design of vehicle door based on radial basis function neural network[J]. Chinese Journal of Automotive Engineering, 2015,5(2):136-143
[7] SAFIYE Ghasemi, ALIREZA Nazemi, SOLEIMAN Hosseinpour. Nonlinear fractional optimal control problems with neural network and dynamic optimization schemes[J]. Nonlinear Dynamics, 2017,89(4):2669-2682.
[8] 杨建国, 熊经纬, 徐兰, 等. 应用混合种群遗传神经网络的精梳毛纺工艺参数反演模型[J]. 纺织学报, 2016,37(7):149-154.
YANG Jianguo, XIONG Jingwei, XU Lan, et al. Inversion model of combed wool spinning process parameters using mixed population genetic neural network[J]. Journal of Textile Research, 2016,37(7):149-154.
[9] 谷有众, 高卫东, 卢雨正, 等. 应用遗传算法优化支持向量回归机的喷气涡流纺纱线质量预测[J]. 纺织学报, 2016,37(7):142-148.
GU Youzhong, GAO Weidong, LU Yuzheng, et al. Prediction of jet vortex spinning yarn quality using support vector regression machine with genetic algo-rithm[J]. Journal of Textile Research, 2016,37(7):142-148.
[10] CHOI Y H, KIM S T, YOON K C, et al. Optimization of a high speed spinning disk spindle system for minimum RRO NRRO, and Lightweight by using[J]. Journal of Xiamen University(Natural Science), 2002(S1):90-91.
[11] AK R, LI Y, VITELLI V, et al. NSGA-II-trained neural network approach to the estimation of prediction intervals of scale deposition rate in oil & gas equipment[J]. Expert Systems with Applications, 2013,40(4):1205-1212.
[12] 张笑, 唐敦兵, 杨俊, 等. 立式振动磨关键结构参数的多目标优化设计[J]. 机械科学与技术, 2018,37(6):821-827.
ZHANG Xiao, TANG Dunbing, YANG Jun, et al. Multi-objective optimization design of key structural parameters of vertical vibration mill[J]. Mechanical Science and Technology, 2018,37(6):821-827.
[1] 张卓, 丛洪莲, 蒋高明, 董智佳. 基于交互式遗传算法的Polo衫快速款式推荐系统[J]. 纺织学报, 2021, 42(01): 138-144.
[2] 李亮, 倪俊芳. 绗缝机花样加工代码自动生成算法[J]. 纺织学报, 2020, 41(11): 162-167.
[3] 谢子昂, 杜劲松, 赵国华. 衬衫吊挂流水线的自适应动态调度[J]. 纺织学报, 2020, 41(10): 144-149.
[4] 张晓侠, 刘凤坤, 买巍, 马崇启. 基于BP 神经网络及其改进算法的织机效率预测[J]. 纺织学报, 2020, 41(08): 121-127.
[5] 黄珍珍, 莫碧贤, 温李红. 基于遗传算法及仿真技术的服装生产流水线平衡[J]. 纺织学报, 2020, 41(07): 154-159.
[6] 郑小虎, 鲍劲松, 马清文, 周衡, 张良山. 基于模拟退火遗传算法的纺纱车间调度系统[J]. 纺织学报, 2020, 41(06): 36-41.
[7] 莫帅, 冯战勇, 党合玉, 邹振兴. 棉纺细纱锭子发展演变与研究展望[J]. 纺织学报, 2020, 41(06): 190-196.
[8] 莫帅, 冯战勇, 党合玉, 邹振兴, 王迪文, 朱红伟. 高速纺纱锭子弹性管减振机制与振动特性[J]. 纺织学报, 2020, 41(03): 148-153.
[9] 黄淇, 周其洪, 张倩, 王绍宗, 范伟, 孙会丰. 基于系统布置设计-遗传算法的纱线浸染生产线布局优化[J]. 纺织学报, 2020, 41(03): 84-90.
[10] 张旭靖, 王立川, 陈雁. 基于遗传算法的服装缝制生产线平衡优化[J]. 纺织学报, 2020, 41(02): 125-129.
[11] 王晓晖, 刘月刚, 孟婥, 孙以泽. 基于遗传算法和神经网络的3D增材印花工艺参数优化[J]. 纺织学报, 2019, 40(11): 168-174.
[12] 孟朔, 潘如如, 高卫东, 王静安, 周利军. 采用主目标进化遗传算法的织造排程研究[J]. 纺织学报, 2019, 40(08): 169-174.
[13] 闫琳琳 邹专勇 卫国 程隆棣. 基于螺旋导引槽空心锭子的喷气涡流纺加捻腔流场模拟[J]. 纺织学报, 2018, 39(09): 139-145.
[14] 扈昕瞳 张玉井 孟婥 孙以泽. 编织锭子放线速度对纱线张力调控的建模与影响[J]. 纺织学报, 2017, 38(06): 111-117.
[15] 宋楚平 李少芹. 应用改进遗传算法的自动配棉模型优化与应用[J]. 纺织学报, 2016, 37(09): 151-155.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!