基于特征差异增强的工程装备知识跨项目多源域迁移学习研究

徐进, 赵慧祺, 张泽慧, 刘盾

系统工程理论与实践 ›› 2024, Vol. 44 ›› Issue (3) : 1097-1113.

PDF(4483 KB)
中国科学院数学与系统科学研究院期刊网
PDF(4483 KB)
系统工程理论与实践 ›› 2024, Vol. 44 ›› Issue (3) : 1097-1113. DOI: 10.12011/SETP2023-0971
论文

基于特征差异增强的工程装备知识跨项目多源域迁移学习研究

    徐进1,2, 赵慧祺1,2, 张泽慧1,2, 刘盾1,2
作者信息 +

A multi-source transfer learning study based on feature difference enhancement for inter-project knowledge transfer of construction equipment

    XU Jin1,2, ZHAO Huiqi1,2, ZHANG Zehui1,2, LIU Dun1,2
Author information +
文章历史 +

摘要

工程装备智能化是发展智能建造的重要基础, 项目知识是工程装备智能化的知识源泉, 因此, 工程装备知识跨项目的有效共享与利用是实现智能建造的重要环节. 为了增强工程装备知识的跨项目利用效率与效果, 本文提出了一种基于特征差异增强的多源域迁移学习框架. 该框架利用混合深度神经网络提取源项目的通用时空特征表示, 基于项目相似度度量筛选可迁移源项目, 通过所设计的特征差异增强方法挖掘多源域的域特殊特征表示并进行集成, 在避免负迁移的同时实现工程装备知识的跨项目有效转移. 本文使用多个隧道工程项目的数据进行了实验, 在六个盾构设备姿态预测知识转移任务的两个预测目标上, 该框架相较于基线模型的预测准确性平均提升度分别为86. 48%、117. 01%, 并具有良好的稳健性和情景适应性. 实验结果表明:本文所设计的新框架可以挖掘多个源域项目的特性知识并整合其共性知识, 通过集成多源域迁移学习的知识来提高知识利用率, 为大型工程装备知识的跨项目转移提供了有效的方法和工具, 有助于提升施工项目的知识管理与智能建造水平.

Abstract

Engineering equipment intelligence is an important basis for the development of intelligent construction, and project knowledge is the knowledge source of engineering equipment intelligence. Therefore, the effective sharing and utilization of engineering equipment knowledge across projects is an important link to realize intelligent construction. In order to enhance the effciency and effectiveness of cross-project utilization of engineering equipment knowledge, this paper proposes a multi-source domain transfer learning framework based on feature difference enhancement. The framework uses a hybrid deep neural network to extract the common spatiotemporal feature representation of source items, screens transferable source items based on the project similarity measurement, and mines the domain special feature representation of multiple source domains through the designed feature difference enhancement method and integrates it, so as to avoid negative transfer and realize effective cross-project transfer of engineering equipment knowledge. In this paper, the data of several tunnel engineering projects are used to carry out experiments. In the two prediction objectives of six shield equipment attitude prediction knowledge transfer tasks, the average accuracy improvement of the framework compared with the baseline model is 86.48% and 117.01%, respectively, and it has good robustness and situational adaptability. Experiments show that the new framework designed in this paper can mine the characteristic knowledge of multiple source domain projects and integrate their common knowledge, improve the knowledge utilization rate by integrating the knowledge of multi-source domain transfer learning, provide an effective method and tool for the cross-project transfer of large-scale engineering equipment knowledge, and help improve the level of knowledge management and intelligent construction of construction projects.

关键词

工程项目 / 项目知识转移 / 工程装备知识 / 多源域迁移学习 / 深度学习

Key words

construction project / project knowledge transfer / construction equipment knowledge / multi-source domain transfer learning / deep learning

引用本文

EndNote

Ris (Procite)

Bibtex

导出引用
徐进 , 赵慧祺 , 张泽慧 , 刘盾. 基于特征差异增强的工程装备知识跨项目多源域迁移学习研究. 系统工程理论与实践, 2024, 44(3): 1097-1113 https://doi.org/10.12011/SETP2023-0971
XU Jin , ZHAO Huiqi , ZHANG Zehui , LIU Dun. A multi-source transfer learning study based on feature difference enhancement for inter-project knowledge transfer of construction equipment. Systems Engineering - Theory & Practice, 2024, 44(3): 1097-1113 https://doi.org/10.12011/SETP2023-0971
中图分类号： C931.6   

参考文献

[1] 杨青, 武高宁, 王丽珍. 大数据:数据驱动下的工程项目管理新视角[J]. 系统工程理论与实践, 2017, 37(3):710-719. Yang Q, Wu G N, Wang L Z. Big data:A new perspective of the engineering project management driven by data[J]. Systems Engineering-Theory & Practice, 2017, 37(3):710-719.
[2] Chapman R J. A framework for examining the dimensions and characteristics of complexity inherent within rail megaprojects[J]. International Journal of Project Management, 2016, 34(6):937-956.
[3] 陈珂, 丁烈云. 我国智能建造关键领域技术发展的战略思考[J]. 中国工程科学, 2021, 23(4):64-70. Cheng K, Ding L Y. Development of key domain-relevant technologies for smart construction in China[J]. Strategic Study of CAE, 2021, 23(4):64-70.
[4] Singh V, Mirzaeifar S. Assessing transactions of distributed knowledge resources in modern construction projects-A transactive memory approach[J]. Automation in Construction, 2020, 120:103386.
[5] 倪国栋, 黄付帅, 路飞月, 等. 多项目环境下工程管理组织内部知识共享影响因素识别[J]. 工程管理学报, 2015, 29(2):96-100. Ni G D, Huang F S, Lu F Y, et al. Recognition about the knowledge sharing influencing factors in the project management organization under the multi-project environment[J]. Journal of Engineering Management, 2015, 29(2):96-100.
[6] Ren X, Deng X, Liang L. Knowledge transfer between projects within project-based organizations:The project nature perspective[J]. Journal of Knowledge Management, 2018, 22(5):1082-1103.
[7] Almeida M V, Soares A L. Knowledge sharing in project-based organizations:Overcoming the informational limbo[J]. International Journal of Information Management, 2014, 34(6):770-779.
[8] 刘常乐, 任旭, 郝生跃. 项目型企业知识转移的障碍与动机研究[J]. 情报理论与实践, 2015, 38(3):40-44. Liu C L, Ren X, Hao S Y. Research on the barriers and motivation of knowledge transfer in project-driven enterprise[J]. Information Studies:Theory & Application, 2015, 38(3):40-44.
[9] Aerts G, Dooms M, Haezendonck E. Knowledge transfers and project-based learning in large scale infrastructure development projects:An exploratory and comparative ex-post analysis[J]. International Journal of Project Management, 2017, 35(3):224-240.
[10] Xu J, He M, Jiang Y. A novel framework of knowledge transfer system for construction projects based on knowledge graph and transfer learning[J]. Expert Systems with Applications, 2022, 199:116964.
[11] 高明, 陈玉涵, 张泽慧, 等. 基于新型空间注意力机制和迁移学习的垃圾图像分类算法[J]. 系统工程理论与实践, 2021, 41(2):498-512. Gao M, Chen Y H, Zhang Z H, et al. Classification algorithm of garbage images based on novel spatial attention mechanism and transfer learning[J]. Systems Engineering-Theory & Practice, 2021, 41(2):498-512.
[12] Weiss K, Khoshgoftaar T M, Wang D. A survey of transfer learning[J]. Journal of Big Data, 2016, 3(1):9. https://doi.org/10.1186/s40537-016-0043-6.
[13] Wang J, Mo Z, Zhang H, et al. Ensemble diagnosis method based on transfer learning and incremental learning towards mechanical big data[J]. Measurement, 2020, 155:107517.
[14] Yu Z, Shen D, Jin Z, et al. Progressive transfer learning[J]. IEEE Transactions on Image Processing, 2022, 31:1340-1348.
[15] Zhu Y, Zhuang F, Wang D. Aligning domain-specific distribution and classifier for cross-domain classification from multiple sources[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1):5989- 5996.
[16] Liu J, Zhang C, Jiang X. Imbalanced fault diagnosis of rolling bearing using improved MsR-GAN and feature enhancement-driven CapsNet[J]. Mechanical Systems and Signal Processing, 2022, 168:108664.
[17] Zhang W, Fu C, Chang X, et al. A more compact object detector head network with feature enhancement and relational reasoning[J]. Neurocomputing, 2022, 499:23-34.
[18] 欧阳桃花, 曾德麟. 拨云见日——揭示中国盾构机技术赶超的艰辛与辉煌[J]. 管理世界, 2021, 37(8):194-207. Ouyang T H, Zeng D L. Dispel the clouds and see the sun:Reveal the hardship and glory of China's shield machine technology catch-op[J]. Journal of Management World, 2021, 37(8):194-207.
[19] Xu J, Zhang Z, Zhang L, et al. Predicting shield position deviation based on double-path hybrid deep neural networks[J]. Automation in Construction, 2023, 148:104775.
[20] 陈中. 富水砂卵石地层盾构施工引起地面塌陷的原因及建议[J]. 都市快轨交通, 2014, 27(6):87-91. Chen Z. Causes and countermeasures:Typical cases of ground collapse in shield tunneling in water-rich sandy cobble stratum[J]. Urban Rapid Rail Transit, 2014, 27(6):87-91.
[21] Liu X, Wang W, Wang Y, et al. Coordinated optimization control of shield machine based on dynamic fuzzy neural network direct inverse control[J]. Transactions of the Institute of Measurement and Control, 2021, 43(6):1445-1451.
[22] 马腾, 曹吉鸣, 王立强. 项目型组织成员知识转移动机实证研究——与组织情境的跨层次作用[J]. 科研管理, 2017, 38(11):126-136. Ma T, Cao J M, Wang L Q. An empirical research on knowledge transfer motivation in project-based organizations based on the inter-hierarchical role of organizational context[J]. Science Research Management, 2017, 38(11):126-136.
[23] Wang F, Jiang Z, Li X, et al. Cognitive factors of the transfer of empirical engineering knowledge:A behavioral and fNIRS study[J]. Advanced Engineering Informatics, 2021, 47:101207.
[24] Lin L, MÜLLER R, Zhu F, et al. Choosing suitable project control modes to improve the knowledge integration under different uncertainties[J]. International Journal of Project Management, 2019, 37(7):896-911.
[25] Zhang L, Li X. How to reduce the negative impacts of knowledge heterogeneity in engineering design team:Exploring the role of knowledge reuse[J]. International Journal of Project Management, 2016, 34(7):1138-1149.
[26] 贾广社, 曹丽. 工程项目的知识转化模式研究[J]. 科技进步与对策, 2008(10):166-169. Jia G S, Cao L. Research on knowledge transfer models for engineering projects[J]. Science & Technology Progress and Policy, 2008(10):166-169.
[27] Cheng M. Research on the knowledge transfer in construction projects[C]//200916th International Conference on Industrial Engineering and Engineering Management, 2009:2035-2039.
[28] 舒昌俊, 方俊, 官波. 嵌入社会网络的工程项目内部知识转移研究[J]. 科技进步与对策, 2012, 29(18):53-57. Shu C J, Fang J, Guan B. Research on knowledge transfer of construction project embedded in social networks[J]. Science & Technology Progress and Policy, 2012, 29(18):53-57.
[29] 任佳妮, 周立秋, 杨阳, 等. 大型装备MRO知识管理系统研究[J]. 现代情报, 2013, 33(5):56-59. Ren J N, Zhou L Q, Yang Y, et al. Research of large equipment MRO knowledge management system[J]. Journal of Modern Information, 2013, 33(5):56-59.
[30] Zhong B, Wu H, Ding L, et al. Mapping computer vision research in construction:Developments, knowledge gaps and implications for research[J]. Automation in Construction, 2019, 107:102919.
[31] 王晓莉. 新产品开发中用户隐性知识转移壁垒与路径创新——以装备制造企业为例[J]. 企业经济, 2017, 36(12):117-123. Wang X L. The barriers to user implicit knowledge transfer and path innovation in new product development-Take equipment manufacturing enterprises as an example[J]. Enterprise Economy, 2017, 36(12):117-123.
[32] Zhong W, Liu S, Wan F, et al. Equipment selection knowledge base system for industrial styrene process[J]. Chinese Journal of Chemical Engineering, 2018, 26(8):1707-1712.
[33] Li Z, Li J, Wang Y, et al. A deep learning approach for anomaly detection based on SAE and LSTM in mechanical equipment[J]. The International Journal of Advanced Manufacturing Technology, 2019, 103(1):499-510.
[34] Yang B, Xu S, Lei Y, et al. Multi-source transfer learning network to complement knowledge for intelligent diagnosis of machines with unseen faults[J]. Mechanical Systems and Signal Processing, 2022, 162:108095.
[35] Duan L, Xu D, Tsang I W H. Domain adaptation from multiple sources:A domain-dependent regularization approach[J]. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(3):504-518.
[36] Liu H, Shao M, Ding Z, et al. Structure-preserved unsupervised domain adaptation[J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 31(4):799-812.
[37] 方匡南, 李晶茂, 范新妍, 等. 基于多源域知识迁移学习的小微企业信用评分[J]. 系统工程理论与实践, 2023, 43(5):1320-1330. Fang K N, Li J M, Fan X Y, et al. Credit scoring of small and micro enterprises using multi-source information transfer learning[J]. Systems Engineering-Theory & Practice, 2023, 43(5):1320-1330.
[38] Xu R, Chen Z, Zuo W, et al. Deep cocktail network:Multi-source unsupervised domain adaptation with category shift[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018:3964-3973.
[39] Mancini M, Porzi L, Bulò S R, et al. Boosting domain adaptation by discovering latent domains[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018:3771-3780.
[40] Tong G, Li Y, Zhang H, et al. A fine-grained channel state information-based deep learning system for dynamic gesture recognition[J]. Information Sciences, 2023, 636:118912.
[41] Xu D, Zhang S, Zhang H, et al. Convergence of the RMSProp deep learning method with penalty for nonconvex optimization[J]. Neural Networks, 2021, 139:17-23.
[42] Zhou C, Xu H, Ding L, et al. Dynamic prediction for attitude and position in shield tunneling:A deep learning method[J]. Automation in Construction, 2019, 105:102840.
[43] Cocchi M. Data fusion methodology and applications[M]. Amsterdam, Netherlands; Cambridge, MA:Elsevier, 2019.
[44] Zhang D, Shen Y, Huang Z, et al. Auto machine learning-based modelling and prediction of excavation-induced tunnel displacement[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2022, 14(4):1100-1114.
[45] Jiang W, Qiu S, Liang T, et al. Cross-project clone consistent-defect prediction via transfer-learning method[J]. Information Sciences, 2023, 635:138-150.
[46] Nicholson M, Agrahari R, Conran C, et al. The interaction of normalisation and clustering in sub-domain definition for multi-source transfer learning based time series anomaly detection[J]. Knowledge-Based Systems, 2022, 257:109894.
[47] Peng C, Tao Y, Chen Z, et al. Multi-source transfer learning guided ensemble LSTM for building multi-load forecasting[J]. Expert Systems with Applications, 2022, 202:117194.
[48] Lu H, Wu J, Ruan Y, et al. A multi-source transfer learning model based on LSTM and domain adaptation for building energy prediction[J]. International Journal of Electrical Power and Energy Systems, 2023, 149. https://doi.org/10.1016/j.ijepes.2023.109024.
[49] Peng S, Zeng R, Cao L, et al. Multi-source domain adaptation method for textual emotion classification using deep and broad learning[J]. Knowledge-Based Systems, 2023, 260:110173.

基金

国家自然科学基金(72171197,62276217)；四川省自然科学基金面上项目(2023NSFSC0364)
PDF(4483 KB)

514

Accesses

0

Citation

Detail
段落导航
相关文章

/

〈 〉