纺织学报 ›› 2025, Vol. 46 ›› Issue (01): 154-162.doi: 10.13475/j.fzxb.20240500701

• 服装工程 • 上一篇    下一篇

基于标准工时预测的衬衣部件模块生产编排优化

盛锡彬1, 赵崧灵1, 顾冰菲1,2,3()   

  1. 1.浙江理工大学 服装学院, 浙江 杭州 310018
    2.浙江理工大学 数智风格与创意设计研究中心, 浙江 杭州 310018
    3.丝绸文化传承与产品设计数字化技术文化和旅游部重点实验室, 浙江 杭州 310018
  • 收稿日期:2024-05-06 修回日期:2024-09-26 出版日期:2025-01-15 发布日期:2025-01-15
  • 通讯作者: 顾冰菲(1987—),女,副教授,博士。主要研究方向为数字化服装技术。E-mail: gubf@zstu.edu.cn。
  • 作者简介:盛锡彬(1998—),男,硕士生。主要研究方向为数字化服装技术。
  • 基金资助:
    国家自然科学基金项目(61702461);中国纺织工业联合会应用基础研究项目(J202007);中国纺织工业联合会科技指导性项目(2018079);浙江理工大学科研业务费专项资金资助项目(2020Q051)

Production scheduling optimization of shirt component module based on standard man-hour prediction

SHENG Xibin1, ZHAO Songling1, GU Bingfei1,2,3()   

  1. 1. School of Fashion Design & Engineering, Zhejiang Sci-Tech University, Hangzhou, Zhejiang 310018, China
    2. Digital Intelligence Style and Creative Design Research Center, Zhejiang Sci-Tech University, Hangzhou, Zhejiang 310018, China
    3. Key Laboratory of Silk Culture Heritage and Products Design Digital Technology,Ministry of Culture and Tourism, Hangzhou, Zhejiang 310018, China
  • Received:2024-05-06 Revised:2024-09-26 Published:2025-01-15 Online:2025-01-15

RichHTML

5

PDF (PC)

23

摘要： 针对模块化智能特性下多品种小批量服装生产系统的快速重构需求,提出一种基于反向传播(BP)神经网络进行模块族工时预测,并用于混合模式部件模块生产编排优化的方法。以企业近几年生产的550款典型衬衫款式为例,基于11类衬衣模块族,通过对标准工时影响因素权重分析,构建BP神经网络预测模型。最终对标准工时模型预测效果进行验证,并基于模块族针对2款衬衣实现混合生产线的工序分配。结果表明:各模块族平均绝对误差均在9 s内,且其中8个模块族的误差值未超过5 s;混款生产模式相较于单款式生产编制的效率均在90%以上,采用模块优化的编制效率可达95.55%,且平滑指数降低了50.09%,说明工时预测及模块化工序分配应用效果较好。本文研究结果可一定程度上满足企业混款组合加工的应用要求,为快速报价、制定生产计划提供参考。

关键词: 衬衣, BP神经网络, 标准工时, 工时预测, 模块生产, 流水编排

Abstract:

Objective For the rapid reconfiguration requirement of multi-variety and small-batch clothing production system under the characteristics of modular intelligence. A method based on back propagation (BP) neural network was proposed to predict module man-hours and optimize the application of mixed mode component module production scheduling. The research results can be utilized to optimize production scheduling, predict man-hours and assign processes, and provide reference for quick quotation and production planning.

Method shirt; Taking shirts produced by an enterprise as the research object, a sample set of shirt module man-hour was established, and the influence factors of standard man-hour were analyzed to build a man-hour prediction model. Production of two shirts of the same color and different styles was taken as an example to achieve the arrangement of production by using modules in the mixed assembly line, and the arrangement effect was analyzed.

Results In order to measure the accuracy of prediction results more intuitively, the man-hour prediction model was constructed for all module groups and verified one by one. Based on each evaluation index, the prediction accuracy of the model was evaluated, and the prediction results of 11 types of module groups were obtained. From the perspective of model fitting effect, the accuracy of fit of all module groups was above 0.81. From the perspective of the prediction time value of test samples, the average absolute error of each module group was within 9 s and the error value of 8 module groups was not more than 5 s. The model prediction accuracy rate reached more than 90% peaking at 94.89%. Taking the combinatorial splitter module of class 8 module group as an example, the scatter plot was adopted to compare the real value and predicted value data of the test set samples. The values of the two samples were close to each other for most samples, and the error was within the range of ±10 s. The paired sample T test was adopted to analyze the error between the actual value and the predicted value of the class 8 main process, and the significance Sig. value was greater than 0.05, indicating no significant difference between the two, and the multidimensional proof model achieved good results in the prediction of standard man-hour. Finally, the process allocation of the hybrid production line was achieved based on the module group for the two shirts. The results showed that the average absolute error of each module group was within 9 s and the error value of class 8 module group was not more than 5 s. Compared with single-style production, the efficiency of mixed production mode was more than 90%, the efficiency of modular optimization reached 95.55%, the balance delay rate was reduced by 44.04%, and the smoothing index was reduced by 50.09%.

Conclusion A method based on BP neural network is proposed to predict the man-hour of module group and apply it to the production scheduling optimization of mixed mode components. Based on the 11 types module group of shirt parts, the BP neural network prediction model is built through the weight analysis of the influence factors of standard man-hour. In order to verify the accuracy of the prediction results, the man-hour prediction model was constructed for all module groups, and the optimal network structure was obtained by verifying one by one. The paired sample T-test was conducted for the actual and predicted values of each process of the class 8 module group, and the results showed that Sig. values were all greater than 0.05, indicating no significant difference between them. Finally, based on the module group, the process allocation of the hybrid production line is realized for the two shirts. The results of this study can be used for production scheduling optimization, man-hour prediction and process allocation, which can meet the application requirements of mixed model processing in enterprises to a certain extent, and provide reference for rapid quotation and production planning.

Key words: shirt, BP neural network, standard man-hour, man-hour prediction, module production, flow arrangement

中图分类号: 

  • TS941.17

表1

基于工艺相似性的衬衣部件模块族划分"

编号 各模块族中部件(部位)类别
1 E-01贴袋
2 g-01褶位
3 g-02省位
4 f-02绲边袖衩、J-04绲边衣摆
5 G-03卷边袖口、J-03卷边衣摆、I-01侧衩
6 H-01前中、A-01领圈、G-01拼接袖口
7 a-01主唛及尺码唛、a-02洗唛、a-03挂耳
8 C-01袖窿、B-01肩缝、F-01侧缝、D-01袖底缝、
K-01后过肩、g-03分割位
9 e-02口袋、d-04连裁前襟、d-05连裁暗门襟、
G-02折边袖口、J-02折边衣摆
10 h-01一片式克夫、d-01一片式装襟、d-03装暗门襟、
f-02大小袖衩、i-01下摆贴、i-02袖口贴、i-03前襟贴
11 b上级领、c下级领、h-02两片式克夫、
e-01袋盖、e-02两片式装襟、H-01贴边前襟、
G-01贴边袖口、J-01贴边衣摆

表2

第8类模块族工序原始样本示例"

样本
工序编号		 针步
类型		 机器
种类		 工艺
难度		 长度尺寸/
cm		 缝纫
形状		 缝纫
数量		 面料
等级		 面料
层数		 纹样
图案		 标准
工时/s
0001 合 拷边机 Y 85 直 2 低等级 2 无 58.68
0002 合 平车 W 50 圆 2 中低等级 2 无 119.16
0003 合 平车 Y 18 直 1 低等级 2 条纹 32.58
0004 修 刀车 Y 42 直 1 低等级 1 无 14.04
0005 明缉 平车 X 56 弧 2 低等级 1 无 77.64
0006 烫倒 烫台 Z 18 直 2 中等级 1 无 13.74
0007 拷边 拷边机 Y 50 圆 2 低等级 1 无 48.60

表3

第8类模块9种影响因素权重计算结果"

因素大类 具体因素 标准差 相关系数 信息量 权重/%
工艺要求 工艺难度 0.130 5.526 0.716 4.69
机器种类 0.380 5.761 2.191 14.36
针步类型 0.335 5.518 1.848 12.11
缝纫结构 长度尺寸 0.171 7.480 1.281 8.40
缝纫形状 0.363 7.262 2.637 17.27
缝纫数量 0.150 8.575 1.286 8.43
缝纫对象 面料等级 0.171 7.786 1.333 8.73
面料层数 0.349 6.314 2.205 14.45
纹样图案 0.224 7.874 1.766 11.57

图1

第8类模块各因素相关系数热力图"

图2

训练误差曲线"

表4

各模块族标准工时预测模型结果评价"

模块族
编号		 模块
类别		 拟合
优度		 平均绝对
误差/s		 平均相对
误差/%		 预测
准确率/%
1 E-01 0.91 7.10 9.39 90.61
2 g-01 0.95 2.70 8.86 91.14
3 g-02 0.90 2.06 7.98 92.02
4 f-02、J-04 0.92 1.39 5.11 94.89
5 G-03、J-03、I-01 0.83 7.05 10.19 89.81
6 H-01、A-01、G-01 0.81 8.12 7.55 92.45
7 a-01、a-02、a-03 0.97 1.13 5.70 94.30
8 C-01、B-01、
F-01、D-01、
K-01、g-03		 0.95 3.21 6.55 93.45
9 e-02、d-04、d-05、
G-02、J-02		 0.86 4.83 10.76 89.24
10 h-01、d-01、
d-03、f-02、i-01、
i-02、i-03		 0.92 4.41 9.62 90.38
11 b、c、h-02、e-01、
e-02、H-01、
G-01、J-01		 0.96 2.32 9.56 90.44

图3

第8类模块族测试样本预测结果"

图4

2款衬衣款式图"

图5

A、B 2款衬衣工艺路线"

表5

2款衬衣模块流程分布"

模块族编号 模块 优化前工位分配 优化后分配工位 工序编号 设备
9 d-05连裁暗门襟 1,2 1,2 26,28 IR/SN
d-04连裁里襟 1,2 1,2 27,29 IR/SN
6 g-02省位 2,3 1,2 30,31 IR/SN
10 h-01一片式克夫 3 1,2 12,13,14,15 IR/SN
4 g-01褶位 3 4 18 SN
5 B-01肩缝 3,4 3 32,33,34,35 SN/OL
F-01侧缝 4 3 36,37 SN/OL
D-01袖底缝 4 4,6 20,21 SN/OL
C-01袖窿 6 6 38,39 SN/OL
11 b-01衬衫上领、c-01衬衫下领 1,7,8,9 5,6,7 2,3,4,5,6,8,9,10,11 IR/SN
a-04领飘带 2,7,8 5,6,7 48,49,50 IR/SN
3 f-02绲边袖衩 2,6 6 16,17 SN
C-02绲边袖窿 5,8 6,7 40,41,42 SN/OL
1 a-02洗唛 1,5 2,5,8 22,23,24,25 SN
a-01主唛及尺码唛 7,8 8 44 SN
a-03挂耳 5 8 25,46 SN
7 G-01拼接袖口 6 8 19 SN
A-01领圈 9 9 43 SN
2 J-03卷边衣摆 10 10 47 SN

图6

不同生产编制方式负荷情况 注:t1表示节拍上限(256.40 s);t2表示标准平均节拍(245 s);t3表示节拍下限(232.75 s)。"

表6

2款衬衣不同编排方式生产指标"

编排
方式		 标准生产
节拍/s		 编制
效率/%		 平滑
指数		 平衡延
迟率/%
A 166 87. 98 75.79 12.02
B 126 79.23 89.96 20.77
A-B混合款式 262 93.59 87.23 6.41
模块优化A-B
混合款式		 257 95.55 43.54 4.45
[1] LONGO F, PADOVANO A, CIMMINO B, et al. Towards a mass customization in the fashion industry: an evolutionary decision aid model for apparel product platform design and optimization[J]. Computers & Industrial Engineering, 2021. DOI:10.1016/j.cie.2021.107742.
[2] DOLL W J, VONDEREMBSE M A. The evolution of manufacturing systems: towards the post-industrial enterprise[J]. Omega, 1991, 19(5): 401-411.
[3] 郑路, 颜伟雄, 胡觉亮, 等. 基于模块化的服装混合流水线平衡优化[J]. 纺织学报, 2022, 43(4): 140-146.
ZHENG Lu, YAN Weixiong, HU Jueliang, et al. Balanced optimization of garment hybrid assembly line based on modularization[J]. Journal of Textile Research, 2022, 43(4):140-146.
[4] 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(7): 154-159.
HUANG Zhenzhen, MOK Pikyin, WEN Lihong. Garment production line balance based on genetic algorithm and simulation[J]. Journal of Textile Research, 2020, 41(7): 154-159.
[5] 钱存华, 黄宇博. 基于遗传算法的服装生产混合流水线平衡设计[J]. 毛纺科技, 2021, 49(5): 75-79.
QIAN Cunhua, HUANG Yubo. Balanced design of mixed-model production line of garment production based on genetic algorithm[J]. Wool Textile Journal, 2021, 49(5):75-79.
[6] KUMARI A. Statistical analysis of standard allowed minute on sewing efficiency in apparel industry[J]. Autex Research Journal, 2020, 20(4): 359-365.
[7] JALIL M A, HOSSAIN T, ISLAM M, et al. To estimate the standard minute value of a polo-shirt by work study[J]. Global Journal of Research in Engineering, 2015, 15(2): 25-30.
[8] NCHALALA A, ALEXANDER T, TAIFA I W. Establishing standard allowed minutes and sewing efficiency for the garment industry in Tanzania[J]. Research Journal of Textile and Apparel, 2023, 27(2): 246-263.
[9] KIM E T, KIM S. Development of smart insole for cycle time measurement in sewing process[J]. Fashion and Textiles, 2021, 8: 1-11.
[10] KHATUN M M. Effect of time and motion study on productivity in garment sector[J]. International Journal of Scientific & Engineering Research, 2014, 5(5): 825-833.
[11] ZHANG Y, XUN P, DU J, et al. Sewing time optimization based on predetermined time system method[C]//13th Textile Bioengineering and Informatics Symposium Proceedings (TBIS 2020). New York: Textile Bioengineering & Informatics Society, 2020: 239-245.
[12] KIRIN S, SAJATOVIC A H. Determination of working methods and normal times of technological sewing operation using MTM system[J]. Tekstilec, 2020, 63(3): 203-215.
[13] 赵小燕, 宋栓军. 一种基于案例推理的集成式工时估算方法[J]. 机械制造, 2016, 54(12): 1-5.
ZHAO Xiaoyan, SONG Shuanjun. An integrated time estimation method based on case-based reasoning[J]. Machinery, 2016, 54(12):1-5.
[14] XU Y N, THOMASSEY S, ZENG X Y. Garment mass customization methods for the cutting-related processes[J]. Textile Research Journal, 2021, 91(7/8): 802-819.
[15] 颜伟雄, 胡觉亮, 韩曙光. 资源约束的模块化服装生产工序编排优化模型与算法[J]. 计算机集成制造系统, 2024, 30(6): 2148-2158.
YAN Weixiong, HU Jueliang, HAN Shuguang. Optimization model andalgorithm of modular garment production process scheduling with resource constraints[J]. Computer Integrated Manufacturing Systems, 2024, 30(6): 2148-2158.
[16] 邵一兵. 服装制造系统的生产调度建模和优化研究[D]. 杭州: 浙江理工大学,2022: 39-144.
SHAO Yibing. Research on modeling and optimization for production scheduling of garment manufacturing system[D]. Hangzhou: Zhejiang Sci-Tech University, 2022: 39-144.
[17] 胡飞. 一种面向服装大规模定制的柔性生产线设计[D]. 郑州: 中原工学院, 2022: 23-45.
HU Fei. A flexible production line design for garment mass customization[D]. Zhengzhou: Zhongyuan University of Technology, 2022: 23-45.
[18] GIANNAKIDOU C, DIAKOULAKI D, MEMOS C D. Vulnerability to coastal flooding of industrial urban areas in Greece[J]. Environmental Processes: An International Journal, 2020, 7: 749-766.
[19] 严凯, 姚凯学, 杨玥倩, 等. 基于PCA-GA-BP神经网络的茶园环境预测研究[J]. 数学的实践与认识, 2019, 49(9): 180-187.
YAN Kai, YAO Kaixue, YANG Yueqian, et al. Prediction of tea garden environment based on PCA-GA-BP neural network[J]. Journal of Mathematics in Practice and Theory, 2019, 49(9):180-187.
[20] 苏高利, 邓芳萍. 论基于MatLab语言的BP神经网络的改进算法[J]. 科技通报, 2003(2): 130-135.
SU Gaoli, DENG Fangping. On the improving backpropagation on algorithms of the neural networks based on MatLab language: a review[J]. Bullein of Science and Technology, 2003(2): 130-135.
[21] YANG A M, ZHUANSUN Y X, LIU C, et al. Design of intrusion detection system for internet of things based on improved BP neural network[J]. IEEE Access, 2019, 7: 106043-106052.
[1] 齐育宝, 汝欣, 李建强, 周悦欣, 彭来湖. 基于随机共振-反向传播算法的压电选针器渐变失效检测[J]. 纺织学报, 2024, 45(03): 202-208.
[2] 肖伯祥, 刘正东, 郭昱成, 王渊霞. 基于三维人体扫描模型的衬衣版型生成方法[J]. 纺织学报, 2022, 43(12): 151-159.
[3] 庹武, 王哓玉, 高雅昆, 于媛媛, 郝潇潇, 刘永亮, 郭鑫. 基于改进边缘检测算法的服装款式识别[J]. 纺织学报, 2021, 42(10): 157-162.
[4] 许雪梅. 基于模拟退火算法改进遗传算法的织物智能配色[J]. 纺织学报, 2021, 42(07): 123-128.
[5] 张苏宁, 王泽, 马大力. 基于改进蚁群算法的Flexsim衬衣流水线仿真优化[J]. 纺织学报, 2021, 42(03): 155-160.
[6] 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.
[7] 金守峰, 林强强, 马秋瑞, 张浩. 基于BP神经网络的织物表面绒毛质量的检测方法[J]. 纺织学报, 2020, 41(02): 69-76.
[8] 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.
[9] 周捷, 马秋瑞. 基于BP神经网络的运动文胸肩带属性与乳房振幅的函数关系[J]. 纺织学报, 2019, 40(09): 186-191.
[10] 周捷, 马秋瑞. BP神经网络在塑身内衣压力预测中的应用[J]. 纺织学报, 2019, 40(04): 111-116.
[11] 查刘根, 谢春萍. 应用四层BP神经网络的棉纱成纱质量预测[J]. 纺织学报, 2019, 40(01): 52-56.
[12] 杜劲松　郑梦林　戴玉芳　李依璇. 服装模板工序的动作编码[J]. 纺织学报, 2018, 39(09): 109-114.
[13] 巫莹柱　单颖法　黄伯熹　林广茂　梁家豪　张晓利. 聚对苯二甲酸丙二醇酯与聚对苯二甲酸丁二醇酯混纺纤维的智能识别[J]. 纺织学报, 2018, 39(09): 169-175.
[14] 刘巧丽 王俊. 库存服装再设计系统研究[J]. 纺织学报, 2018, 39(06): 125-130.
[15] 张宁 潘如如 高卫东. 采用图像处理的织物缝纫平整度自动评估[J]. 纺织学报, 2017, 38(04): 145-150.
Viewed
Full text
28
HTML PDF
Just accepted Online first Issue Just accepted Online first Issue
0 0 5 0 0 23

  From Others local
  Times 9 19
  Rate 32% 68%

Abstract
69
Just accepted Online first Issue
0 0 69
  From Others local
  Times 50 19
  Rate 72% 28%

Cited
Web of Science  Crossref   ScienceDirect  Search for Citations in Google Scholar >>
 
This page requires you have already subscribed to WoS.
  Shared   
  Discussed   
No Suggested Reading articles found!
京ICP备14006648号　 京公网安备11010502044800号
版权所有 © 2021 《纺织学报》编辑部
地址： 北京市朝阳区延静里中街3号主楼6层《纺织学报》杂志社　邮政编码：100025　
电话：010-65017711,65917740　传真：010-65016539　Email:fangzhixuebao@vip.126.com
本系统由北京玛格泰克科技发展有限公司设计开发