纺织学报 ›› 2015, Vol. 36 ›› Issue (01): 23-29.

• 纤维材料 • 上一篇    下一篇

纺织材料设计反问题的贝叶斯统计推断方法

  

  • 收稿日期:2013-11-25 修回日期:2014-10-08 出版日期:2015-01-15 发布日期:2015-01-15
  • 通讯作者: 徐定华 E-mail:dhxu6708@263.net

Bayesian statistical inference method for inverse problems of textile material design

  • Received:2013-11-25 Revised:2014-10-08 Online:2015-01-15 Published:2015-01-15
  • Contact: Ding-Hua XU E-mail:dhxu6708@263.net

摘要:

针对具有不适定性纺织材料设计反问题,给出了利用贝叶斯蒙特卡洛方法求解纺织材料单参数各多参数反演问题的一种新方法。因织物稳态热湿传递模型的非线性性和反问题的不适定性,基于贝叶斯统计推断方法的纺织材料类型、厚度、孔隙率等参数的后验概率分布推断是一种有效的方法。这种方法将参数的先验信息描述为先验概率密度,构建了纺织材料设计反问题的数值算法。数值实验结果表明,与马尔科夫链蒙特卡洛抽样算法相匹配的贝叶斯推理可用来求解纺织材料设计反问题。

Abstract:

   Aiming at the ill-posed of the inverse problem of textile material design(IPTMD), a new approach based on Bayesian Markov Chain Monte Carlo(Bayesian-MCMC) method was proposed for solving the problem of single and multiple parameter determination. Since the heat and moisture transfer model is non-linear and the IPTMD is ill-posed, it proves an effective method to derive posterior distribution for the model parameters such as the heat conductivity, thickness and porosity of the material. This method describes prior information of parameters as prior probability density, constructing numerical algorithms of the IPTMD. The numerical results show that Bayesian inference method which agrees with Markov chain Monte Carlo sampling algorithm can be applied to solve the IPTMD.

[1] 徐定华,陈远波,程建新.低温环境下纺织材料类型设计反问题[J].纺织学报,2011(9):23-28. XU Dinghua, CHEN Yuanbo, CHENG Jianxin. Inverse problem of textile material design at low temperature[J] Journal of Textile Research. 2011(9):23-28.
[2] CUI Peng, XU Dinghua. Simultaneous determination of thickness and heat conductivity in fabric design: Steady -state modeling and PSO algorithms[J]. Journal of Fiber Bioengineering and Informatics. 2013(2) :195-204。
[3] Kaipio J, Somersalo E. Statistical and computational inverse problems. New York:Springer, 2004.
[4] 陈海洋,腾彦国 王金生等.基于Bayesian—MCMC方法的水体污染识别反问题[J].湖南大学学报(自然科学版).2012(6):74-78. CHEN Haiyang, TENG Yanguo, WANG Jinsheng. Event source identification of water pollution based on Bayesian-MCMC[J]. Journal of Hunan University(Natural Sciences). 2012(6):74-78.
[5] Jing Wang,Nicholas Zabaras. A Bayesian inference approach to the inverse heat conduction problem[J]. International Journal of Heat and Mass Transfer. 2004(47):3927-3914.
[6] Jing Wang, Nicholas Zabaras. Using Bayesian statistics in the estimation of heat source in radiation[J]. International Journal of Heat and Mass Transfer. 2005(48):15-29.
[7] 高思云,杨晨.利用贝叶斯模型进行热参数估计[J].系统仿真学报,2006(6):1462-1465. GAO Siyun, YANG Chen. Bayesian model to parameter estimation[J].Journal of System Simulation. 2006(6): 1462-1465.
[8] Xu Dinghua, Cheng Jianxin, Zhou Xiaohong. A model of heat and moisture transfer through parallel pore Textiles[C]. Proceeding of Textile Bioengineering and Informatics Symposium.Hong Kong:TBIS Limited Binary Information Press, 2010:1151—1156.
[9] 徐定华. 纺织材料热湿传递数学模型及设计反问题[M].北京:科学出版社,2013.   XU Dinghua. Mathematical model of heat and moisture transfer and inverse problems of textile material design[M]. Beijing Science press. 2013.
[10] Xu Dinghua, Ge Meibao.Thickness determination in textile meterial design:dynamic modeling and numerical algorithms[J]. Inverse Problems. 2012(28): 035011.
No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 吕柏祥;孙冰俏. 一些影响纤维静电因素的测定[J]. 纺织学报, 1984, 5(09): 5 -10 .
[2] 董秀洁;周光辉;张景昌. PVC基纳米SiO2复合材料电改性研究[J]. 纺织学报, 2004, 25(04): 16 -17 .
[3] 陈德平;李秀真;伍非;田建林. 络筒机数控卷绕装置控制系统的研究[J]. 纺织学报, 2000, 21(05): 31 -33 .
[4] 陈济刚. 提高短绒双针床拉舍尔机的生产效率(一)[J]. 纺织学报, 1991, 12(01): 16 -19 .
[5] 张欣;姚穆;李毅;杨国荣. 纺织品及服装力学性能工程设计的发展(Ⅰ)[J]. 纺织学报, 2003, 24(05): 116 -117 .
[6] 肖红;刘晶;施楣梧. 处理时间和介质对PET/PTT长丝性能的影响[J]. 纺织学报, 2008, 29(9): 16 -19 .
[7] . 上海——开展技术咨询服务[J]. 纺织学报, 1984, 5(08): 10 .
[8] 陈时若;程洪伟;金励征;张治禾;叶炳水. 蚕茧干燥时空气温湿度与茧质的关系[J]. 纺织学报, 1983, 4(10): 33 -37 .
[9] 张砚. 消灭粗纺机开关车细节装置鉴定[J]. 纺织学报, 1982, 3(10): 63 .
[10] 龚丽芳;倪人捷;黄煜;姚成. 双季铵盐表面活性剂对涤纶织物的抗静电性能[J]. 纺织学报, 2008, 29(5): 72 -74 .