基于知识图谱的直升机部件装配序列规划方法

doi:10.11996/JG.j.2095-302X.2024051062

图学学报 ›› 2024, Vol. 45 ›› Issue (5): 1062-1070.DOI: 10.11996/JG.j.2095-302X.2024051062

基于知识图谱的直升机部件装配序列规划方法

蒋明杰¹(), 张炜才², 荣浩明², 张俊起², 黄少华¹()

1.南京航空航天大学机电学院，江苏南京 210016
2.航空工业昌河飞机工业(集团)有限责任公司，江西景德镇 333002

收稿日期:2024-04-18 修回日期:2024-06-28 出版日期:2024-10-31 发布日期:2024-10-31
通讯作者:黄少华(1990-)，男，讲师，博士。主要研究方向为数字化设计与制造等。E-mail：shaohuah@nuaa.edu.cn
第一作者:蒋明杰(2000-)，男，硕士研究生。主要研究方向为数字化设计与制造。E-mail：jiang_mingjie@nuaa.edu.cn

A knowledge graph-based sequence planning method for helicopter components assembly

JIANG Mingjie¹(), ZHANG Weicai², RONG Haoming², ZHANG Junqi², HUANG Shaohua¹()

1. College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing Jiangsu 210016 China
2. AVIC Changhe Aircraft Industrial (Group) Co., Ltd., Jingdezhen Jiangxi 333002, China

Received:2024-04-18 Revised:2024-06-28 Published:2024-10-31 Online:2024-10-31
Contact: HUANG Shaohua (1990-), lecturer, Ph.D. His main research interests cover digital design and manufacturing, etc. E-mail：shaohuah@nuaa.edu.cn
First author：JIANG Mingjie (2000-), master student. His main research interests cover digital design and manufacturing. E-mail：jiang_mingjie@nuaa.edu.cn

摘要/Abstract

摘要：

由于直升机组件数量多且组件之间约束关系复杂，传统的装配序列规划方法存在指数爆炸和易陷入局部最优解的问题。为了应对装配序列求解时间随组件数量指数增长和多约束关系矩阵运算复杂的难点，引入知识图谱(KG)建立直观的语义装配信息模型，并提出了一种基于KG的直升机部件装配序列规划方法。首先，基于三维模型解析和知识推理技术实现结构信息和约束关系等关键装配信息的提取。其次，基于本体构建KG形式的装配信息模型。最后，利用带反馈的图规划算法从KG中求解直升机部件的装配序列。KG提供的优先关系减少了算法搜索空间，在优先关系的约束下，带反馈的图规划算法以装配方向改变次数最小和装配工具变化次数最少为目标，逐步规划序列并反馈规划结果以避免重复搜索。直升机的中机身中段部件被作为实验对象以验证该方法的有效性，对比启发式算法能获得更高适应度值的装配序列且求解时间更短。

关键词: 知识图谱, 直升机部件, 装配序列规划, 语义信息模型, 图算法, 三维模型解析

Abstract:

Due to the large number of helicopter components and the complex constraint relationships between them, traditional assembly sequence planning methods encounter the problems of exponential explosion and local optimal solution. To address the difficulties posed by the exponential increase of running time with the number of components and complex calculations of multi-constraint relationship matrix, knowledge graphs (KG) were introduced to establish intuitive semantic assembly information models. A KG -based method for planning the assembly sequence of helicopter components was proposed. Firstly, key assembly information such as structure information and constraint relationships was extracted based on 3D model analysis and knowledge reasoning. Secondly, an assembly information model in the form of KG was constructed based on ontology. Finally, a graph planning algorithm with feedback was employed to determine the assembly sequence of helicopter components from the KG. The priority relationships provided in the KG reduced the search space of the algorithm. Under the constraint of these priority relationships, the graph planning algorithm with feedback aimed to minimize the number of assembly direction changes and the number of assembly tool changes. It gradually planned the sequence, and fed back the planning results to avoid repeated searches. The middle piece of the helicopter mid-fuselage was used as an experimental object to verify the effectiveness of the proposed method. The proposed method achieved higher fitness for the assembly sequence and shorter solution times compared to heuristic algorithms.

Key words: knowledge graph, helicopter component, assembly sequence planning, semantic information model, graph algorithm, 3D model analysis

中图分类号:

蒋明杰, 张炜才, 荣浩明, 张俊起, 黄少华. 基于知识图谱的直升机部件装配序列规划方法[J]. 图学学报, 2024, 45(5): 1062-1070.

JIANG Mingjie, ZHANG Weicai, RONG Haoming, ZHANG Junqi, HUANG Shaohua. A knowledge graph-based sequence planning method for helicopter components assembly[J]. Journal of Graphics, 2024, 45(5): 1062-1070.

图/表 12

参考文献 22

[1]	王发麟, 郭宇, 查珊珊. 复杂机电产品线缆虚实融合装配体系构建及其关键技术[J]. 图学学报, 2018, 39(1): 75-84. DOI
	WANG F L, GUO Y, ZHA S S. Assembly system construction and its key techniques of cable harness under virtual and real scene fusion for complex mechatronic products[J]. Journal of Graphics, 2018, 39(1): 75-84 (in Chinese).
[2]	张嘉城, 朱阅訸, 罗亚中. 基于指针网络的空间目标遍历交会序列规划[J]. 航空学报, 2023, 44(15): 420-432.
	ZHANG J C, ZHU Y H, LUO Y Z. Space target rendezvous sequence planning via pointer networks[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(15): 420-432 (in Chinese).
[3]	于嘉鹏, 王成恩, 张闻雷. 复杂产品装配关系矩阵自动生成方法[J]. 计算机集成制造系统, 2010, 16(2): 249-255, 270.
	YU J P, WANG C E, ZHANG W L. Automatic acquiring method for assembly relation matrix of complex product[J]. Computer Integrated Manufacturing Systems, 2010, 16(2): 249-255, 270 (in Chinese).
[4]	张闻雷, 曲蓉霞, 许美蓉, 等. 复杂产品装配干涉矩阵自动生成方法[J]. 机械工程学报, 2016, 52(1): 139-148. DOI
	ZHANG W L, QU R X, XU M R, et al. Method for automatic generation of assembly interference matrix of complex products[J]. Journal of Mechanical Engineering, 2016, 52(1): 139-148 (in Chinese). DOI
[5]	ZHANG W L, MA M X, LI H Y, et al. Generating interference matrices for automatic assembly sequence planning[J]. The International Journal of Advanced Manufacturing Technology, 2017, 90(1): 1187-1201.
[6]	刘晓阳, 刘恩福, 靳江艳. 基于蚁群算法的异步并行装配序列规划方法[J]. 机械工程学报, 2019, 55(9): 107-119. DOI
	LIU X Y, LIU E F, JIN J Y. Asynchronous parallel assembly sequence planning based on ant colony algorithm[J]. Journal of Mechanical Engineering, 2019, 55(9): 107-119 (in Chinese). DOI
[7]	ZHENG Y, CHEN L, WU D L, et al. Assembly sequence planning method for optimum assembly accuracy of complex products based on modified teaching-learning based optimization algorithm[J]. The International Journal of Advanced Manufacturing Technology, 2023, 126(3): 1681-1699.
[8]	郝博, 徐东平, 王明阳, 等. 基于改进遗传算法的机翼装配序列智能规划[J]. 组合机床与自动化加工技术, 2021(6): 135-137, 140. DOI
	HAO B, XU D P, WANG M Y, et al. Intelligent planning of aircraft wing assembly sequence based on improved genetic algorithm[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2021(6): 135-137, 140 (in Chinese).
[9]	胡志强, 潘鑫瑜, 文思捷, 等. 结合多模态知识图谱与大语言模型的风机装配工艺问答系统[J]. 机械设计, 2023, 40(S2): 20-26.
	HU Z Q, PAN X Y, WEN S J, et al. Fan assembly process question answering system based on multimodal knowledge map and large language model[J]. Journal of Machine Design, 2023, 40(S2): 20-26 (in Chinese).
[10]	张海涛, 苏琳. 结合知识图谱的变分自编码器零样本图像识别[J]. 计算机工程与应用, 2023, 59(1): 236-243. DOI
	ZHANG H T, SU L. Variational auto-encoder combined with knowledge graph zero-shot learning[J]. Computer Engineering and Applications, 2023, 59(1): 236-243 (in Chinese). DOI
[11]	许慧, 廖桧铭. 基于知识图谱的建筑工程施工事故智能分析[J]. 中国安全生产科学技术, 2023, 19(3): 46-52.
	XU H, LIAO H M. Intelligent analysis of construction accidents in construction engineering based on knowledge graph[J]. Journal of Safety Science and Technology, 2023, 19(3): 46-52 (in Chinese).
[12]	姜文明, 齐立忠, 张苏, 等. 基于知识图谱的电网工程建筑信息模型质量检查方法[J]. 吉林大学学报: 工学版, 2024, 54(3): 807-814.
	JIANG W M, QI L Z, ZHANG S, et al. Quality inspection method of electric power engineering building information model based on knowledge graph[J]. Journal of Jilin University: Engineering and Technology Edition, 2024, 54(3): 807-814 (in Chinese).
[13]	王刚锋, 张寰, 刘思濛, 等. 基于语义工艺知识的驱动桥装配序列规划研究[J]. 图学学报, 2024, 45(3): 564-574. DOI
	WANG G F, ZHANG H, LIU S M, et al. Research on drive axle assembly sequence planning based on semantic process knowledge[J]. Journal of Graphics, 2024, 45(3): 564-574 (in Chinese). DOI
[14]	CHEN J H, JIA X L. An approach for assembly process case discovery using multimedia information source[J]. Computers in Industry, 2020, 115: 103176.
[15]	耿育科, 孙荟博. 粒子群算法在装配序列规划中的应用方法研究[J]. 航空制造技术, 2016, 59(9): 66-69.
	GENG Y K, SUN H B. Study on application method of particle swarm optimization algorithm on assembly sequence planning[J]. Aeronautical Manufacturing Technology, 2016, 59(9): 66-69 (in Chinese).
[16]	XIA L Y, LU J F, LU Y Q, et al. Semantic knowledge-driven A-GASeq: a dynamic graph learning approach for assembly sequence optimization[J]. Computers in Industry, 2024, 154: 104040.
[17]	ZHOU H, LU Q, QIAN J W. A Graph-based framework for assembly sequence planning of a cable harness[J]. Journal of Manufacturing Systems, 2024, 73: 39-51.
[18]	王昊, 曾鸿, 张均东, 等. 基于目标拆卸的虚拟拆装过程建模[J]. 图学学报, 2015, 36(6): 903-908. DOI
	WANG H, ZENG H, ZHANG J D, et al. Modeling of virtual assembly and disassembly process based on selective disassembly[J]. Journal of Graphics, 2015, 36(6): 903-908 (in Chinese).
[19]	罗建军, 王嘉文, 王明明, 等. 机器人在轨构建空间桁架结构的装配序列规划方法[J]. 宇航学报, 2021, 42(4): 437-449.
	LUO J J, WANG J W, WANG M M, et al. Sequence planning method for robotic on-orbit assembly of space truss structure[J]. Journal of Astronautics, 2021, 42(4): 437-449 (in Chinese).
[20]	ZHU X J, XU Z G, WANG J Y, et al. Graph-based assembly sequence planning algorithm with feedback weights[J]. The International Journal of Advanced Manufacturing Technology, 2023, 125(7): 3607-3617.
[21]	黄丰云, 熊雄, 周铮, 等. 遗传帝国竞争混合算法在装配序列规划中的研究与应用[J]. 机械设计与制造, 2022(3): 266-271, 275.
	HUANG F Y, XIONG X, ZHOU Z, et al. Research and application of hybrid genetic imperial competition algorithms in assembly sequence planning[J]. Machinery Design & Manufacture, 2022(3): 266-271, 275 (in Chinese).
[22]	QIAN J H, ZHANG Z J, SHAO C, et al. Assembly sequence planning method based on knowledge and ontostep[J]. Procedia CIRP, 2021, 97: 502-507.

关系	定义
有	一种结构层级关系，描述部件与组件之间的关系
使用	一种装配资源关系，描述组件与装配工具之间的关系
按照	一种技术要求关系，描述组件与装配方向之间的关系
优先于	一种装配优先关系，描述组件与组件的初步装配顺序关系
在···之前	一种装配顺序关系，描述组件与组件的详细装配顺序关系

关系	定义
有	一种结构层级关系，描述部件与组件之间的关系
使用	一种装配资源关系，描述组件与装配工具之间的关系
按照	一种技术要求关系，描述组件与装配方向之间的关系
优先于	一种装配优先关系，描述组件与组件的初步装配顺序关系
在···之前	一种装配顺序关系，描述组件与组件的详细装配顺序关系

组件名称	类型	关系	组件名称	类型
4框	组件	优先于	左前过渡减安装梁	组件
4框	组件	优先于	右前过渡减安装梁	组件
5框	组件	优先于	5A下半框	组件
5A下半框	组件	优先于	Y-270下中梁	组件
5A下半框	组件	优先于	Y+742下中梁	组件
左前过渡减安装梁	组件	优先于	5框	组件
右前过渡减安装梁	组件	优先于	5框	组件

组件名称	类型	关系	组件名称	类型
4框	组件	优先于	左前过渡减安装梁	组件
4框	组件	优先于	右前过渡减安装梁	组件
5框	组件	优先于	5A下半框	组件
5A下半框	组件	优先于	Y-270下中梁	组件
5A下半框	组件	优先于	Y+742下中梁	组件
左前过渡减安装梁	组件	优先于	5框	组件
右前过渡减安装梁	组件	优先于	5框	组件

编号	组件名称	方向	工具	编号	组件名称	方向	工具
1	4框	Xn	T1	17	Y+742下中梁	Yp	T4
2	5框	Xn	T1	18	左前发动机支撑梁	Yn	T5
3	5A下半框	Xn	T1	19	右前发动机支撑梁	Yp	T5
4	5A左上半框	Xp	T1	20	中机身中部平台	Zn	T6
5	5A右上半框	Xp	T1	21	4-6框左侧蒙皮	Yp	T1
6	6框	Xn	T1	22	4-6框右侧蒙皮	Yn	T1
7	主减下隔框	Zp	T2	23	左发动机蒙皮	Yp	T7
8	左前过渡减安装梁	Yp	T3	24	右发动机蒙皮	Yn	T7
9	右前过渡减安装梁	Yn	T3	25	底部蒙皮	Zp	T8
10	Y-375上中梁	Yp	T3	26	地板左水平件	Zn	T2
11	Y+375上中梁	Yn	T3	27	地板右水平件	Zn	T2
12	Y-702上中梁	Yp	T3	28	Z+1650左水平件	Zn	T9
13	Y+702上中梁	Yn	T3	29	Z+1650右水平件	Zn	T9
14	Y-270下中梁	Yn	T4	30	Z+700左水平件	Zn	T9
15	Y+270下中梁	Yp	T4	31	Z+700右水平件	Zn	T9
16	Y-742下中梁	Yn	T4

基于知识图谱的直升机部件装配序列规划方法

A knowledge graph-based sequence planning method for helicopter components assembly

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 22

相关文章 6

编辑推荐

Metrics

本文评价

算法	个体数量	最大迭代次数	平均迭代次数	优先关系数量	装配方向维持次数	装配工具维持次数	目标函数值	运行时间/s
GA	31	300	>150	79	11	14	39.1	2.735 38
PSO	31	300	>150	78	10	15	39.1	1.517 93
GPAF	1	31	31	80	15	15	41.0	0.801 32
OAS	-	-	-	80	9	15	39.2	-

[1]	王刚锋, 张寰, 刘思濛, 岳萍, 张栋. 基于语义工艺知识的驱动桥装配序列规划研究[J]. 图学学报, 2024, 45(3): 564-574.
[2]	何柳, 安然, 刘姝妍, 李润岐, 陶剑, 曾照洋. 基于知识图谱的航空多模态数据组织与知识发现技术研究[J]. 图学学报, 2024, 45(2): 300-307.
[3]	陈逸天, 张玮, 谭思危, 朱融晨, 王毅超, 朱闽峰, 陈为. 历史人物群体对比可视化[J]. 图学学报, 2023, 44(6): 1227-1238.
[4]	王文亮, 陈纯毅, 胡小娟, 于海洋, 田野. 融合阴影图和深度划分阴影体的阴影渲染算法[J]. 图学学报, 2022, 43(3): 478-485.
[5]	汪玉金, 谢诚, 余蓓蓓, 向鸿鑫, 柳青. 属性语义与图谱语义融合增强的零次学习图像识别[J]. 图学学报, 2021, 42(6): 899-907.
[6]	宋建炜 , 邓逸川 , 苏成 , . 基于预训练语言模型的建筑施工安全事故文本的命名实体识别研究[J]. 图学学报, 2021, 42(2): 307-315.