基于联邦学习框架的制造服务个性化推荐方法研究

doi:10.3901/JME.2023.12.149

机械工程学报 ›› 2023, Vol. 59 ›› Issue (12): 149-161.doi: 10.3901/JME.2023.12.149

• 特邀专栏：制造大数据分析与决策 • 上一篇下一篇

扫码分享

基于联邦学习框架的制造服务个性化推荐方法研究

王磊¹, 金校¹, 唐红涛¹, 李西兴², 李益兵¹, 郭顺生¹, 官思佳^3,4

1. 武汉理工大学机电工程学院武汉 430070;
2. 湖北工业大学机械工程学院武汉 430068;
3. 航天科工空间工程发展有限公司北京 100854;
4. 中国航天科工集团空间工程总体部北京 100854

收稿日期:2022-12-07 修回日期:2023-03-20 出版日期:2023-06-20 发布日期:2023-08-15
通讯作者: 唐红涛(通信作者),男,1987年出生,博士,副教授,博士研究生导师。主要研究方向为车间调度理论及智能优化算法,智能制造系统。E-mail:tanghongtaozc@163.com
作者简介:王磊,男,1988年出生,博士,副教授,硕士研究生导师。主要研究方向为智能制造服务协作优化与管理。E-mail:wanglei9455@whut.edu.cn
基金资助:
国家自然科学基金资助项目(51905396，51805152)。

Personalized Manufacturing Service Recommendation Method Based on Federated Learning Framework

WANG Lei¹, JIN Xiao¹, TANG Hongtao¹, LI Xixing², LI Yibing¹, GUO Shunsheng¹, GUAN Sijia^3,4

1. School of Mechanical and Electronic Engineering, Wuhan University of Technology, Wuhan 430070;
2. School of Mechanical Engineering, Hubei University of Technology, Wuhan 430068;
3. CASIC Space Engineering Development Co., Ltd., Beijing 100854;
4. General Space Engineering Department of China Aerospace Science and Industry Corporation, Beijing 100854

Received:2022-12-07 Revised:2023-03-20 Online:2023-06-20 Published:2023-08-15

摘要/Abstract

摘要： 针对工业云平台中海量的制造服务使得用户难以进行服务选择，以及推荐算法的使用使得平台存在泄露用户数据风险的问题，提出一种基于联邦学习框架的制造服务个性化推荐方法。采用基于模型的协同过滤推荐算法，在矩阵分解中考虑用户和服务的评分偏置项以提高推荐准确度。推荐算法所用的数据被分类存储于用户端与服务器端，其中包含用户隐私的数据留存至用户本地。本地数据经加密算法进行脱敏后，与服务器端的数据结合以共同训练模型。最终，用户对制造服务的不同属性的评分被预测得出。根据制造服务质量的特点，在多属性预测评分的基础上进一步量化用户个性化倾向。通过个性化倾向因子对预测评分的干预得到服务的Pareto非支配解集，生成制造服务的推荐列表。实例验证表明，该推荐方法能够在保护用户隐私的前提下获得良好的预测准确度，在考虑用户个性化偏好的情况下保证推荐服务的预测评分均值较高，从而帮助用户进行制造服务选择。

Abstract: To solve the problem of the massive manufacturing services in the industrial cloud platform make it difficult for users to select services and the use of recommendation algorithm makes the platform have the risk of divulging user data, a personalized recommendation method of manufacturing services based on Federated Learning framework is proposed. The model-based Collaborative Filtering recommendation algorithm is adopted, and the scoring bias of users and services is considered in the matrix decomposition to improve the recommendation accuracy. Data used in the recommendation algorithm is classified and stored in the client and server, of which data containing users' privacy is retained locally. Local data is combined with data in the server to train the model after being desensitized by the encryption algorithm. Finally, users' scores on different attributes in manufacturing service are predicted. Users’ personalization tendency is further quantified by multi-attribute prediction scores according to the characteristics of manufacturing service quality. Pareto non-dominant solution set of the service is obtained through the intervention of the personalization tendency factor on the prediction score, and the recommended list of the manufacturing service is generated. The experiment shows that the recommendation method can obtain good prediction accuracy without compromising users’ privacy and the average prediction score of the recommendation service is high with users’ personalized preferences being considered, thus helping users better choose manufacturing services.

Key words: manufacturing service recommendation, federated learning, collaborative filtering, quality of service, multi-attribute rating

中图分类号:

TP391

王磊, 金校, 唐红涛, 李西兴, 李益兵, 郭顺生, 官思佳. 基于联邦学习框架的制造服务个性化推荐方法研究[J]. 机械工程学报, 2023, 59(12): 149-161.

WANG Lei, JIN Xiao, TANG Hongtao, LI Xixing, LI Yibing, GUO Shunsheng, GUAN Sijia. Personalized Manufacturing Service Recommendation Method Based on Federated Learning Framework[J]. Journal of Mechanical Engineering, 2023, 59(12): 149-161.

参考文献

[1] 李伯虎,张霖,王时龙,等. 云制造——面向服务的网络化制造新模式[J]. 计算机集成制造系统,2010,16(1):8. LI Bohu,ZHANG Lin,WANG Shilong,et al. Cloud manufacturing:A new service-oriented networked manufacturing model[J]. Computer Integrated Manufacturing System,2010,16(1):8.
[2] 陶飞,戚庆林. 面向服务的智能制造[J]. 机械工程学报,2018,54(16):11-23. TAO Fei,QI Qinglin. Service-oriented smart manufacturing[J]. Journal of Mechanical Engineering,2018,54(16):11-23.
[3] 郝予实,范玉顺. 基于场景识别的云制造服务推荐[J]. 计算机集成制造系统,2020,26(8):13. HAO Yushi,FAN Yushun. Cloud manufacturing service recommendation based on scenario recognition[J]. Computer Integrated Manufacturing System,2020,26(8):13.
[4] 方辉,谭建荣,谭颖,等. 基于Web的制造信息主动推荐服务研究[J]. 计算机集成制造系统,2008,14(11):2253-2260. FANG Hui,TAN Jianrong,TAN Ying,et al. Manufacturing information active recommendation based on Web services[J]. Computer Integrated Manufacturing System,2008,14(11):2253-2260.
[5] ADOMAVICIUS G,TUZHILIN A. Toward the next generation of recommender systems:A survey of the state-of-the-art and possible extensions[J]. IEEE Transactions on Knowledge and Data Engineering,2005,17(6):734-749.
[6] CAO Y,WANG S,KANG L,et al. Study on machining service modes and resource selection strategies in cloud manufacturing[J]. International Journal of Advanced Manufacturing Technology,2015,81(1-4):597-613.
[7] 冯长利,马睿泽. 基于服务化的制造企业与服务提供商的演化博弈分析[J]. 中国管理科学,2022,30(6):263-274. FENG Changli,MA Ruize. Analysis of evolutionary game between manufacturing enterprises and service providers based on servitization[J]. Chinese Journal of Management Science,2022,30(6):263-274.
[8] 胡业发,陶飞,周祖德. 制造网格资源服务Trust-QoS评估及其应用[J]. 机械工程学报,2007,43(12):203-211. HU Yefa,TAO Fei,ZHOU Zude. Manufacturing grid resource service trust-qos evaluation and application[J]. Journal of Mechanical Engineering,2007,43(12):203-211.
[9] 张映锋,郭振刚,钱成,等. 基于过程感知的底层制造资源智能化建模及其自适应协同优化方法研究[J]. 机械工程学报,2018,54(16):1-10. ZHANG Yingfeng,GUO Zhengang,QIAN Cheng,et al. Investigation on process-aware based intelligent modeling of bottom layer manufacturing resources and self-adaptive collaborative optimization methodology[J]. Journal of Mechanical Engineering,2018,54(16):1-10.
[10] 许海玲,吴潇,李晓东,等. 互联网推荐系统比较研究[J].软件学报,2009,20(2):350-362. XU Hailing,WU Xiao,LI Xiaodong,et al. Comparison study of internet recommendation system.[J]. Journal of Software,2009,20(2):350-362.
[11] YANG Q,LIU Y,CHEN T,et al. Federated machine learning:Concept and applications[J]. ACM Transactions on Intelligent Systems and Technology,2019,10(2):1-19.
[12] 孙光浩,刘丹青,李梦云. 个性化推荐算法综述[J]. 软件,2017,38(7):70-78. SUN GuangHao,LIU Danqing,LI Mengyun. A survey of personalized recommendation algorithms[J]. Software,2017,38(7):70-78.
[13] LATHA R. Enhancing recommendation competence in nearest neighbour models[J]. Physica a-Statistical Mechanics and Its Applications,2022,59,592.
[14] KANT S,MAHARA T. Nearest biclusters collaborative filtering framework with fusion[J]. Journal of Computational Science,2018,25:204-212.
[15] SENG D,CHEN G,ZHANG Q. Item-based collaborative memory networks for recommendation[J]. IEEE Access,2020(8):213027-213037.
[16] KIM D,PARK C,OH J,et al. Deep hybrid recommender systems via exploiting document context and statistics of items[J]. Information Sciences,2017,417:72-87.
[17] LI M,SHENG L,SONG Y,et al. An enhanced matrix completion method based on non-negative latent factors for recommendation system[J]. Expert Systems with Applications,2022,201:116985.
[18] WANG R,CHENG H K,JIANG Y,et al. A novel matrix factorization model for recommendation with LOD-based semantic similarity measure[J]. Expert Systems with Applications,2019,123:70-81.
[19] SATTLER F,WIEDEMANN S,MUELLER K R,et al. Robust and communication-efficient federated learning from non-i.i.d. data[J]. IEEE Transactions on Neural Networks and Learning Systems,2020,31(9):3400-3413.
[20] JIAO Y,WANG P,NIYATO D,et al. Toward an automated auction framework for wireless federated learning services market[J]. IEEE Transactions on Mobile Computing,2021,20(10):3034-3048.
[21] KHAN L U,PANDEY S R,TRAN N H,et al. Federated learning for edge networks:Resource optimization and incentive mechanism[J]. IEEE Communications Magazine,2020,58(10):88-93.
[22] MILLS J,HU J,MIN G. Communication-efficient federated learning for wireless edge intelligence in IoT[J]. IEEE Internet of Things Journal,2020,7(7):5986-5994.
[23] KAISSIS G,ZILLER A,PASSERAT-PALMBACH J,et al. End-to-end privacy preserving deep learning on multi-institutional medical imaging[J]. Nature Machine Intelligence,2021,3(6):473-484.
[24] 鲜征征,李启良,黄晓宇,等. 基于差分隐私和SVD++的协同过滤算法[J].控制与决策,2019,34(1):43-54. XIAN Zhengzheng,LI Qiliang,HUANG Xiaoyu,et al. Collaborative filtering via SVD++ with differential privacy[J]. Control and Decision,2019,34(1):43-54.
[25] CHAI D,WANG L,CHEN K,et al. Secure federated matrix factorization[J]. Intelligent Systems,IEEE,2021,36(5):11-19.
[26] WANG Y,TIAN Y,YIN X,et al. A trusted recommendation scheme for privacy protection based on federated learning[J]. CCF Transactions on Networking,2020,3(3-4):218-228.
[27] ZHOU P,WANG K,GUO L,et al. A privacy-preserving distributed contextual federated online learning framework with big data support in social recommender systems[J]. IEEE Transactions on Knowledge and Data Engineering,2021,33(3):824-838.
[28] FENG Y,HUANG B. Cloud manufacturing service QoS prediction based on neighbourhood enhanced matrix factorization[J]. Journal of Intelligent Manufacturing,2020,31(7):1649-1660.
[29] FENG Y,HUANG B. A hierarchical and configurable reputation evaluation model for cloud manufacturing services based on collaborative filtering[J]. The International Journal of Advanced Manufacturing Technology,2018,94(9):3327-3343.
[30] ZHANG S,YANG W,XU S,et al. A hybrid social network-based collaborative filtering method for personalized manufacturing service recommendation[J]. International Journal of Computers,Communications & Control (IJCCC),2017,12(5):728.
[31] LIU J,CHEN Y. A personalized clustering-based and reliable trust-aware QoS prediction approach for cloud service recommendation in cloud manufacturing[J]. Knowledge-Based Systems,2019,174(15):43-56.
[32] ZHANG W,ZHANG S,CHEN Y G,et al. Combining social network and collaborative filtering for personalised manufacturing service recommendation[J]. International Journal of Production Research,2013,51(22):6702-6719.
[33] ZHANG W,GUO S,ZHANG S. Personalized manufacturing service recommendation using semantics-based collaborative filtering[J]. Concurrent Engineering,2015,23(2):166-179.
[34] ZHANG W,ZHANG S,ZHANG S,et al. A novel method for MCDM and evaluation of manufacturing services using collaborative filtering and IVIF theory[J]. Journal of Algorithms and Computational Technology,2016,10(1):40-51.
[35] 马文龙,朱李楠,王万良. 云制造环境下基于QoS感知的云服务选择模型[J]. 计算机集成制造系统,2014,20(5):1246-1254. MA Wenlong,ZHU Linan,WANG Wanliang. Cloud service selection model based on QoS-aware in cloud manufacturing environment[J]. Computer Integrated Manufacturing System,2014,20(5):1246-1254.
[36] 赵道致,李锐. 考虑主体心理预期的云制造资源双边匹配机制[J]. 控制与决策,2017,32(5):871-878. LI Daozhi,LI Rui. Two-sided matching mechanism with agents'expectation for cloudmanufacturing resource[J]. Control and Decision,2017,32(5):871-878.
[37] 任磊,任明仑. 基于加权协同网络的制造服务组合方法[J]. 机械工程学报,2018,54(16):70-78. REN Lei,REN Minglun. Manufacturing service composition method based on service weighted synergy network[J]. Journal of Mechanical Engineering,2018,54(16):70-78.
[38] 任磊,任明仑. 基于情景感知的制造组合服务自适应决策机制[J]. 控制与决策,2019,34(6):1277-1285. REN Lei,REN Minglun. Situation aware-adaptive decision-making mechanism of manufacturing composition service[J]. Control and Decision,2019,34(6):1277-1285.
[39] LI H,WEI W,FAN R. Deep Learning-based QoS prediction for manufacturing cloud service[C]//Proceedings of the 38th Chinese Control Conference (CCC). Guangzhou:IEEE,2019:2719-2724.
[40] LIU Z,WANG L,LI X,et al. A multi-attribute personalized recommendation method for manufacturing service composition with combining collaborative filtering and genetic algorithm[J]. Journal of Manufacturing Systems,2021,58:348-364.
[41] ZHAO S,ZHANG Q,PENG Z,et al. Personalized manufacturing service composition recommendation:Combining combinatorial optimization and collaborative filtering[J]. Journal of Combinatorial Optimization,2020,40(3):733-756.
[42] ZHENG H,FENG Y,TAN J. A fuzzy QoS-aware resource service selection considering design preference in cloud manufacturing system[J]. The International Journal of Advanced Manufacturing Technology,2016,84(1-4):371-379.
[43] CHEN F,DOU R,LI M,et al. A flexible QoS-aware Web service composition method by multi-objective optimization in cloud manufacturing[J]. Computers & Industrial Engineering,2016,99:423-431.
[44] KOREN Y,BELL R,VOLONSKY C. Matrix factorization techniques for recommender systems[J]. Computer,2009,42(8):30-37.
[45] PHONG L,AONO Y,HAYASHI T,et al. Privacy-preserving deep learning via additively homomorphic encryption[J]. IEEE Transactions on Information Forensics and Security,2018,13(5):1333-1345.

基于联邦学习框架的制造服务个性化推荐方法研究

Personalized Manufacturing Service Recommendation Method Based on Federated Learning Framework

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	李响, 付春霖, 雷亚国, 李乃鹏, 杨彬. 保证数据隐私的装备协同智能故障诊断联邦迁移学习方法[J]. 机械工程学报, 2023, 59(6): 1-9.
[2]	邵海东, 肖一鸣, 闵志闪, 韩淞宇, 张海舟. 区块链和边缘计算赋能的联邦学习故障诊断框架[J]. 机械工程学报, 2023, 59(21): 283-292.
[3]	华丰, 王亚森, 金骏阳, 袁烨. 一种数据隐私保护下多方无损线性模型学习方法[J]. 机械工程学报, 2023, 59(12): 17-27.
[4]	宰红斌, 刘建国, 唐保国, 马建国, 上官明霞, 单荣荣. 基于WSN的输电线路状态监测与数据采集跨层优化方法^*[J]. 电气工程学报, 2021, 16(3): 161-169.