服装智能制板中的结构特征参数模型设计  被引量:2

Design of structural characteristic parameter model in garment intelligent pattern

在线阅读下载全文

作  者:姚好 谢红[1] YAO Hao;XIE Hong(Fashion College,Shanghai University of Engineering Science,Shanghai 201620,China)

机构地区:[1]上海工程技术大学纺织服装学院,上海201620

出  处:《毛纺科技》2020年第9期55-60,共6页Wool Textile Journal

基  金:上海市科委项目(18030501400);上海工程技术大学创新项目(0293-E3-0903-19-01185)。

摘  要:为了简化服装制板中结构特征参数的获取过程,建立款式、结构特征参数的映射关系。基于服装款式、结构的特征,以西装领为研究对象,通过二维款式图、结构图确定其特征参数,并以PyTorch深度学习框架为基础,利用BP神经网络算法建立预测模型,拟合款式特征参数与结构特征参数的非线性关系,最终均方误差达到0.000019,完成了服装结构特征参数的智能化确定过程。利用55组测试数据,对该模型进行测试,其测试结果表明:55组测试数据的相对误差均在-0.04%~0.04%之间,预测模型精确度较高。利用该预测模型,通过给定的款式特征参数能得到与其映射的结构特征参数,将所获参数输入到自动绘图系统中即得到相应的样板。该模型的设计有利于提高服装制板速度,减少制板师工作量。In order to simplify the process of the structural characteristic parameters obtaining in garment pattern,the relationship between style and structural characteristic parameters was established.Based on the characteristics of the garment pattern and structure chart,the suit collar was taken as the research object and the characteristic parameters of the two-dimensional pattern and structure chart were determined.Based on PyTorch deep learning framework,BP neural network algorithm was used to establish a prediction model to fit the nonlinear relationship between style characteristic parameters and structural characteristic parameters,and the final mean square error could reach 0.000019,the intelligent process of determining the structural characteristic parameters of clothing was completed.The model was tested with 55 groups of testing data,and the results show that the relative error of the 55 groups of prediction parameters was between-0.04%-0.04%,indicating a high accuracy of the prediction model.By using this model,the structural characteristic parameters can be mapped by given style characteristic parameters,and then the obtained parameters can be input into the automatic drawing system to obtain the corresponding template.The design of this model is conducive to improve the speed of garment pattern making and reducing the workload of pattern makers..

关 键 词:智能制板 结构特征参数 人工智能 款式特征参数 西装领 

分 类 号:TS941.2[轻工技术与工程—服装设计与工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象