基于相似体系的民机结构超手册维修案例分析

doi:10.12305/j.issn.1001-506X.2022.09.34

摘要/Abstract

摘要：

为了解决超出手册范围的民机结构维修问题, 提出一种基于相似体系的民机结构超手册维修案例体系模型。通过提取航空公司现有民机结构案例的损伤信息和维修方案信息, 依据信息性质, 采用数值分析、层次法、属性度量、术语频率-逆文档频率(term frequency-inverse document frequency, TF-IDF)方法进行系统的相似度分析, 建立案例相似度指标体系。导入维修案例数据, 通过支持向量机(support vector machine, SVM)分类以及弹性网络回归对指标体系进行权重分配并验证其可靠度达到82%。最后通过实例深度分析了该体系的可行性, 实例证明, 案例相似度指标体系的权重分配与区分效果总体符合实际, 对民机结构超手册维修案例的制定有着重要参考意义。

关键词: 超手册, 结构维修案例, 特征指标, 相似度体系, 分类回归

Abstract:

In order to solve the problem of civil aircraft structure maintenance beyond the scope of the manual, a civil aircraft structure over manual maintenance case system model based on similar system is proposed. By extracting the damage information and maintenance scheme information of the existing civil aircraft structure cases of airlines, according to the nature of the information, the systematic similarity analysis is carried out by using numerical analysis, hierarchical method, attribute measurement and term frequency-inverse document frequency (TF-IDF) method, and the case similarity index system is established. Import the maintenance case data, distribute the weight of the index system through support vector machine (SVM) classification and elastic network regression, and verify that its reliability reaches 82%. Finally, the feasibility of the system is deeply analyzed through an example. The example shows that the weight distribution and differentiation effect of the case similarity index system are generally in line with the reality, which has important reference significance for the formulation of civil aircraft structure over manual maintenance cases.

Key words: over manual, structure maintenance cases, characteristic index, similarity system, classification regression

中图分类号:

V267+.41

王峻洲, 王华伟, 侯召国. 基于相似体系的民机结构超手册维修案例分析[J]. 系统工程与电子技术, 2022, 44(9): 2978-2985.

Junzhou WANG, Huawei WANG, Zhaoguo HOU. Case analysis of civil aircraft structure maintenance over manual based on similarity system[J]. Systems Engineering and Electronics, 2022, 44(9): 2978-2985.

图/表 22

表1

表2

表3

图1

图2

表4

表5

图3

图4

图5

图6

图7

图8

表6

图9

图10

表7

表8

表9

表10

表11

表12

参考文献 31

1	DALKILIC S . Improving aircraft safety and reliability by aircraft maintenance technician training[J]. Engineering Failure Analysis, 2017, 82, 687- 694. doi: 10.1016/j.engfailanal.2017.06.008
2	MOFOKENG T , MATIVENGA P T , MARNEWICK A . Ana-lysis of aircraft maintenance processes and cost[J]. Procedia CIRP, 2020, 90, 467- 472. doi: 10.1016/j.procir.2020.01.115
3	JIN X , CHEN S , JIA Z Y , et al. The research of compose method for removal/inst-all partin aircraft maintenance manual[J]. Applied Mechanics and Materials, 2016, 835, 828- 834. doi: 10.4028/www.scientific.net/AMM.835.828
4	AYDIN A . Aeroplane structural maint enance and corrosion prevention[J]. Aircraft Engineering and Aerospace Technology, 1996, 68 (3): 3- 7. doi: 10.1108/eb037632
5	AIRBUS. Test services[EB/OL]. [2020-12-22]. http://www.airbus.com/space/Services/testservices.html.
6	BOEING. Optimization of fleet performance and maintenance and operation[EB/OL]. [2020-12-22]. http://www.boeing.cn/productsandservices/cas/maintenance-engineering/index.Php.
7	蔡鹏. 飞机维修管理系统的设计与实现[D]. 成都: 电子科技大学, 2019.
	CAI P. Design and implementation of airc-raft maintenance management system[D]. Chengdu: University of Electronic Science and technology, 2019.
8	闫伟. 飞机维修技术状态管理系统的设计与实现[D]. 成都: 电子科技大学, 2018.
	YAN W. Design and implementation of aircraft maintenance technical condition management system[D]. Chengdu: University of Electronic Science and Technology, 2018.
9	刘树乾. 基于B/S的飞机维修管理系统的设计与实现[D]. 成都: 电子科技大学, 2017.
	LIU S Q. Design and implementation of aircraft maintenance management system b-ased on B/S[D]. Chengdu: University of Electronic Science and technology, 2017.
10	冯蕴雯, 严浩, 路成, 等. 基于B/S的民用飞机结构修理方案平台的设计与实现[J]. 航空工程进展, 2021, 12 (6): 117- 126.
	FENG Y W , YAN H , LU C , et al. Design and implementation of civil aircraft structural repair scheme platform based on B/S[J]. Aeronautical Engine-ering Progress, 2021, 12 (6): 117- 126.
11	SEBASTIANI F . Machine learning in automated text categorization[J]. ACM Computing Surveys, 2001, 34 (1): 1- 47.
12	PURWANDARI K, RAHUTOMO R, SIGALINGGING J, et al. Twitter-based text classification using SVM for weather information system[C]//Proc. of the International Conference on Information Management and Technology, 2021.
13	CHENG C X, XU W H, BAI X, et al. Maximum entropy re-gularization and Chinese text recognition[C]//Proc. of the International Workshop on Document Analysts Analysts Systems, 2020: 3-17.
14	LI I, LI T X, LI Y X, et al. Heterogeneous graph neural networks for multi-label textclassification[EB/OL]. [2021-12-17]. https://arXiv.org/abs/2103.14620.
15	SHAH K , PATEL H , SANGHVI D , et al. A comparative analysis of logistic regression, random forest and KNN models for the text classification[J]. Augmented Human: Research, 2020, 5, 12. doi: 10.1007/s41133-020-00032-0
16	ZHOU F G, ZHANG F, YANG B R. Research on Chinese text summarization algorithm based on statistics and rules[C]//Proc. of the International Conference on Asian Language Processing, 2009.
17	LI Y X, HU D. Study on the classificationof mixed text based on conceptual vector space model and Bayes[C]//Proc. of the International Conference on Asian Language Processing, 2009.
18	XU Y, CHEN L. Term frequency based feature selection methods for text categorization[C]//Proc. of the IEEE 4th International Conferenceon Genetic and Evolutionary Computing, 2010.
19	SCANLAN J , HIL T , MARSH R , et al. Cost modelling for aircraft design optimization[J]. Journal of Engineering Design, 2002, 13 (3): 261- 269. doi: 10.1080/09544820110108962
20	WU H Q , LIU Y , DING Y L , et al. Methods to reduce direct maintenance costs for comercial aircraft[J]. Aircraft Engineering and Aerospace Technology, 2004, 76 (1): 15- 18. doi: 10.1108/00022660410514964
21	XIA K W , LIU M X , ZHANG Z W , et al. An approach to attribute reduction base-d on attribute similarity[J]. Journal of Hebei University of Technology, 2005, 34 (4): 20- 30.
22	JURISICA I , GLASGOW J . Improving Performance of case-based classification using context-based relevance[J]. International Journal on Artificial Intelligence Tools, 1997, 6 (4): 511- 536. doi: 10.1142/S0218213097000268
23	XU D D , WU S B . An improved TF-IDFalgorithm in text classification[J]. Applied Mechanics and Materials, 2014, 651-653, 2258- 2261. doi: 10.4028/www.scientific.net/AMM.651-653.2258
24	WU H G , LI D Y , CHENG M , et al. Chinese text classification based on character-level CNN and SVM[J]. International Journal of Intelligent Information and Database Systems, 2019, 986, 227- 238.
25	KIM S W , GIL J M . Research paper systems based on TF-IDF and LDA schemes[J]. Humancentric Computing and Information Sciences, 2019, 9 (1): 1- 21. doi: 10.1186/s13673-018-0162-5
26	石晶. 文本分割综述[J]. 计算机工程与应用, 2006, 42 (35): 159- 163.159-163, 175
	SHI J . Overview of text segmentation[J]. Computer Engineering and Applications, 2006, 42 (35): 159- 163.159-163, 175
27	XIA H , SHENG C , HARRIS C J . Elastic-net prefiltering for two-class classification[J]. IEEE Trans.on Cybernetics, 2013, 43 (1): 286- 295. doi: 10.1109/TSMCB.2012.2205677
28	THUKARAM D , KHINCHA H P , VIJAYNARASIMHA H P . Artificial neural network and sup-port vector machine approach for locating faults in radial distribution systems[J]. IEEE Trans.on Power Delivery, 2005, 20 (2): 710- 721. doi: 10.1109/TPWRD.2005.844307
29	WANG P , YAN M , ZHAN X P , et al. Predicting self-reported proactive personality classification with weibo text and short answer text[J]. IEEE Access, 2021, 9, 77203- 77211. doi: 10.1109/ACCESS.2021.3078052
30	HAN H , DAWSON K J . Applying elasticnetregression to identify the best models predicting changes in civic purpose during the emergeng adulthood[J]. Journal of adolescence, 2021, 93, 20- 27. doi: 10.1016/j.adolescence.2021.09.011
31	XU Y L , YANG Z J . Elastic-net regression al-gorithm based on multi-scale Gaussian kernel[J]. Scientific Journal of Information Engineering, 2014, 4 (1): 19- 25.

维度	元素	说明
飞机信息	飞机型号飞机注册号飞机序列号	描述飞机本身的属性特点, 对手册有巨大影响
运行信息	飞行时长飞行循环运行维修记录	描述飞机运行情况以及维修历史
手册信息	章节号部位零部件标号	描述在手册中的表现形式
损伤细节信息	损伤结构损伤类型损伤成因损伤尺寸损伤位置	描述了损伤的具体情况, 具体化信息便于工程分析
其他信息	材料损伤发现方法	-

指标	内容
飞机机型	机型属性
飞行循环	飞行循环记录
手册信息	章节号部位零件号编号
损伤结构	结构描述
损伤类型	损伤成因损伤描述
其他	损伤发现方法材料

特征指标	相似度计算方法
飞机机型	属性度量决策
飞行循环	数值区间计算
手册信息	布尔赋值, 层次法
损伤结构	布尔赋值
损伤类型	属性度量决策
其他指标	布尔赋值
维修方案	术语频率-逆文档频率计算

运行阶段	循环数值
初步运行阶段	0~2 000
稳定运行阶段	2 000~10 000
中期运行阶段	10 000~40 000
长期运行阶段	40 000以上

属性	特征
损伤成因	环境损伤、偶然损伤、疲劳损伤
损伤数量	1, 2, …, n
损伤尺寸维度	1, 2, …, n