您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2026, Vol. 56 ›› Issue (4): 65-74.doi: 10.6040/j.issn.1672-3961.0.2025.113

• 机器学习与数据挖掘 • 上一篇    

面向工业物联网基于区块链的高效安全联邦学习框架

何腾远1,王基书2,王敏1,唐明靖1,3*   

  1. 1.云南师范大学信息学院, 云南 昆明 650500;2.云南大学信息学院, 云南 昆明 650500;3.云南省马铃薯生物学重点实验室(云南师范大学), 云南 昆明 650500
  • 发布日期:2026-08-12
  • 作者简介:何腾远(2002— ),男,河南平顶山人,硕士研究生,主要研究方向为人工智能安全. E-mail:hetengyuan@ynnu.edu.cn. *通信作者简介:唐明靖(1978— ),男,湖南沅陵人,教授,硕士生导师,博士,主要研究方向为深度学习、图神经网络和生物信息. E-mail:tmj@ynnu.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(61862067);云南省基础研究专项重点资助项目(202501AS070007)

Efficient and secure blockchain-based federated learning framework for industrial Internet of Things

He Tengyuan1, Wang Jishu2, Wang Min1, Tang Mingjing1,3*   

  1. He Tengyuan1, Wang Jishu2, Wang Min1, Tang Mingjing1, 3*(1. School of Information Science and Technology, Yunnan Normal University, Kunming 650500, Yunnan, China;
    2. School of Information Science and Engineering, Yunnan University, Kunming 650500, Yunnan, China;
    3. Yunnan Provincial Key Laboratory of Potato Biology, Yunnan Normal University, Kunming 650500, Yunnan, China
  • Published:2026-08-12

摘要： 针对工业物联网设备计算性能异质性导致的联邦学习训练效率显著下降问题,提出基于区块链的高效安全联邦学习框架。设计动态客户端选择算法和信誉管理机制,筛选出可靠的高性能设备参与每轮训练;设计基于主副链的区块链架构,提高区块链交易验证效率,降低区块链交易存储开销;使用基于深度学习的方法动态调整区块大小,平衡区块链在联邦学习不同阶段的性能,使区块链运行更稳定、更高效。在公开数据集上的试验表明,客户端选择算法性能接近理论最优,区块链存储开销优化至传统方法的66%以下,延迟预测性能优于现有方法。试验评估与结果分析证明了所提框架的有效性和可行性,该框架同样适用于其他设备计算性能异质性的应用场景。

关键词: 工业物联网, 联邦学习, 区块链系统, 客户端选择, 主副链架构, 区块链性能优化

Abstract: To address the significant decline in federated learning training efficiency caused by computational heterogeneity among industrial Internet of Things devices, an efficient and secure blockchain-based federated learning framework was proposed. The dynamic client selection algorithm and reputation management mechanism were designed to screen out reliable and high-performance devices to participate in each round of training. The main-subchain blockchain architecture was introduced to enhance transaction verification efficiency while reducing storage costs. A deep learning-based method was utilized to dynamically adjust the block size to balance blockchain performance across different federated learning phases, thereby enabling more stable and efficient blockchain operations. Experiments on public datasets demonstrated that the client selection algorithm achieved near-optimal performance, blockchain storage costs were optimized to less than 66% of conventional approaches, and latency prediction performance outperformed existing approaches. Experimental evaluations and result analyses demonstrated the effectiveness and feasibility of the proposed framework, which was equally applicable to other application scenarios characterized by device computational heterogeneity.

Key words: industrial Internet of Things, federated learning, blockchain system, client selection, main-subchain architecture, blockchain performance optimization

中图分类号: 

  • TP181
[1] Rahman M A, Hossain M S, Showail A J, et al. AI-enabled IIoT for live smart city event monitoring[J]. IEEE Internet of Things Journal, 2023, 10(4): 2872-2880.
[2] 曹宇慧, 黄昱泽, 冯北鹏, 等. 基于深度强化学习的物联网服务协同卸载方法[J]. 山东大学学报(工学版), 2024, 54(1): 83-90. Cao Yuhui, Huang Yuze, Feng Beipeng, et al. A collaborative service offloading approach for Internet of Things based on deep reinforcement learning[J]. Journal of Shandong University(Engineering Science), 2024, 54(1): 83-90.
[3] Chen B T, Wan J F, Lan Y T, et al. Improving cognitive ability of edge intelligent IIoT through machine learning[J]. IEEE Network, 2019, 33(5): 61-67.
[4] Yang Q, Liu Y, Chen T J, et al. Federated machine learning: concept and applications[J]. ACM Transactions on Intelligent Systems and Technology, 2019, 10(2): 12.
[5] 乐俊青, 谭州勇, 张迪, 等. 面向车联网数据持续共享的安全高效联邦学习[J]. 计算机研究与发展, 2024, 61(9): 2199-2212. Le Junqing, Tan Zhouyong, Zhang Di, et al. Secure and efficient federated learning for continuous IoV data sharing[J]. Journal of Computer Research and Development, 2024, 61(9): 2199-2212.
[6] 唐晓岚, 梁煜婷, 陈文龙. 面向非独立同分布数据的车联网多阶段联邦学习机制[J]. 计算机研究与发展, 2024, 61(9): 2170-2184. Tang Xiaolan, Liang Yuting, Chen Wenlong. Multi-stage federated learning mechanism with non-IID data in Internet of Vehicles[J]. Journal of Computer Research and Development, 2024, 61(9): 2170-2184.
[7] Zhang W, Li X, Ma H, et al. Federated learning for machinery fault diagnosis with dynamic validation and self-supervision[J]. Knowledge-Based Systems, 2021, 213: 106679.
[8] Liu Y, Yu J J Q, Kang J W, et al. Privacy-preserving traffic flow prediction: a federated learning approach[J]. IEEE Internet of Things Journal, 2020, 7(8): 7751-7763.
[9] Adnan M, Kalra S, Cresswell J C, et al. Federated learning and differential privacy for medical image analysis[J]. Scientific Reports, 2022, 12(1): 1953.
[10] Fantauzzo L, Fanì E, Caldarola D, et al. FedDrive: generalizing federated learning to semantic segmentation in autonomous driving[C] //2022 IEEE/RSJ Interna-tional Conference on Intelligent Robots and Systems(IROS). Kyoto, Japan: IEEE, 2022: 11504-11511.
[11] Tabassum N, Chow K H, Wang X Y, et al. On the efficiency of privacy attacks in federated learning[C] //2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE, 2024: 4226-4235.
[12] Sun G, Cong Y, Dong J H, et al. Data poisoning attacks on federated machine learning[J]. IEEE Internet of Things Journal, 2021, 9(13): 11365-11375.
[13] 张宝晨, 黄月, 孔兰菊, 等. 一种支持自适应联邦学习任务的可信公平区块链框架[J]. 计算机研究与发展, 2023, 60(11): 2504-2519. Zhang Baochen, Huang Yue, Kong Lanju, et al. A trustworthy and fair blockchain framework supporting adaptive federated learning task[J]. Journal of Computer Research and Development, 2023, 60(11): 2504-2519.
[14] 施宏建, 马汝辉, 张卫山, 等. 基于区块链辅助的半中心化联邦学习框架[J]. 计算机研究与发展, 2023, 60(11): 2567-2582. Shi Hongjian, Ma Ruhui, Zhang Weishan, et al. Blockchain-assisted semi-centralized federated learning framework[J]. Journal of Computer Research and Development, 2023, 60(11): 2567-2582.
[15] Yang Z P, Shi Y M, Zhou Y, et al. Trustworthy federated learning via blockchain[J]. IEEE Internet of Things Journal, 2023, 10(1): 92-109.
[16] Nishio T, Yonetani R. Client selection for federated learning with heterogeneous resources in mobile edge[C] //ICC 2019-2019 IEEE International Conference on Communications(ICC). Shanghai, China: IEEE, 2019: 8761315.
[17] Ma C, Li J, Shi L, et al. When federated learning meets blockchain: a new distributed learning paradigm[J]. IEEE Computational Intelligence Magazine, 2022, 17(3): 26-33.
[18] Kang J W, Xiong Z H, Niyato D, et al. Incentive mechanism for reliable federated learning: a joint optimization approach to combining reputation and contract theory[J]. IEEE Internet of Things Journal, 2019, 6(6): 10700-10714.
[19] Abdulrahman S, Tout H, Mourad A, et al. FedMCCS: multicriteria client selection model for optimal IoT federated learning[J]. IEEE Internet of Things Journal, 2021, 8(6): 4723-4735.
[20] Wang W L, Wang Y J, Huang Y, et al. Privacy protection federated learning system based on blockchain and edge computing in mobile crowdsourcing[J]. Computer Networks, 2022, 215: 109206.
[21] Lu Y L, Huang X H, Dai Y Y, et al. Blockchain and federated learning for privacy-preserved data sharing in industrial IoT[J]. IEEE Transactions on Industrial Informatics, 2020, 16(6): 4177-4186.
[22] Jin X J, Ma C, Luo S, et al. Distributed IIoT anomaly detection scheme based on blockchain and federated learning[J]. Journal of Communications and Networks, 2024, 26(2): 252-262.
[23] Feng L, Zhao Y Q, Guo S Y, et al. BAFL: a blockchain-based asynchronous federated learning framework[J]. IEEE Transactions on Computers, 2022, 71(5): 1092-1103.
[24] Gao N J, Huo R, Wang S, et al. Sharding-Hashgraph: a high-performance blockchain-based framework for industrial Internet of Things with Hashgraph mechanism[J]. IEEE Internet of Things Journal, 2022, 9(18): 17070-17079.
[25] Xu J, Xie Q Y, Peng S, et al. AdaptChain: adaptive scaling blockchain with transaction deduplication[J]. IEEE Transactions on Parallel and Distributed Systems, 2023, 34(6): 1909-1922.
[26] Li M Z, Wang W, Zhang J. LB-Chain: load-balanced and low-latency blockchain sharding via account migration[J]. IEEE Transactions on Parallel and Distributed Systems, 2023, 34(10): 2797-2810.
[27] Wang S P, Sun S M, Wang X J, et al. Secure crowdsensing in 5G Internet of Vehicles: when deep reinforcement learning meets blockchain[J]. IEEE Consumer Electronics Magazine, 2021, 10(5): 72-81.
[28] Wang J S, Zhu C, Miao C, et al. BPR: blockchain-enabled efficient and secure parking reservation framework with block size dynamic adjustment method[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(3): 3555-3570.
[29] Liu Z M, Wang Y X, Vaidya S, et al. KAN: Kolmogorov-Arnold networks[PP/OL]. V5.(2025-02-09)[2025-06-25]. https://arxiv.org/abs/2404.19756
[30] Xiao H, Rasul K, Vollgraf R. Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms[PP/OL]. V2.(2017-09-15)[2025-02-20]. https://arxiv.org/abs/1708.07747
[31] Singh I. Ethereum transaction dataset(Raw)[DS/OL]. V2. Kaggle(2024-04-18)[2025-03-10]. https://www.kaggle.com/datasets/ikjotsingh221/ethereum-transaction-dataset-raw
[1] 刘冬兰,刘新,刘家乐,赵鹏,常英贤,王睿,姚洪磊,罗昕. 基于分解式Transformer的联邦长期时间序列预测算法[J]. 山东大学学报 (工学版), 2024, 54(5): 101-110.
[2] 刘新,刘冬兰,付婷,王勇,常英贤,姚洪磊,罗昕,王睿,张昊. 基于联邦学习的时间序列预测算法[J]. 山东大学学报 (工学版), 2024, 54(3): 55-63.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发