用联邦学习与区块链提升工业设备剩余寿命预测的隐私与透明度。
A new framework for prognostics in decentralized industries: Enhancing fairness, security, and transparency through Blockchain and Federated Learning
- 通过联邦学习在多站点本地训练模型，避免数据集中上传。
- 结合区块链确保数据不可篡改，提升预测结果可信度。
- 开源代码支持协作创新，适合关注工业5.0安全的开发者。
随着全球产业向工业5.0演进，预测性维护（PM）在智能制造环境中对降低成本、提升韧性及减少停机至关重要。传统集中式数据方法面临隐私、安全与可扩展性挑战，尤其在人工智能驱动的智能制造场景下更为突出。本文提出一种融合联邦学习（FL）与区块链（BC）的技术框架，实现分布式制造环境中的设备剩余使用寿命（RUL）预测。该框架利用联邦学习在多个站点进行本地模型训练，通过区块链保障网络中数据的可信、透明与完整性。实验基于NASA CMAPSS数据集验证了模型在真实场景下的有效性，结果表明该方法显著提升了预测精度，同时增强了数据隐私与安全性，促进了去中心化网络中的公平协作。研究通过GitHub开源代码，鼓励社区协同开发，推动工业5.0领域的持续创新。
原文摘要 · Abstract (English)
As global industries transition towards Industry 5.0 predictive maintenance PM remains crucial for cost effective operations resilience and minimizing downtime in increasingly smart manufacturing environments In this chapter we explore how the integration of Federated Learning FL and blockchain BC technologies enhances the prediction of machinerys Remaining Useful Life RUL within decentralized and human centric industrial ecosystems Traditional centralized data approaches raise concerns over privacy security and scalability especially as Artificial intelligence AI driven smart manufacturing becomes more prevalent This chapter leverages FL to enable localized model training across multiple sites while utilizing BC to ensure trust transparency and data integrity across the network This BC integrated FL framework optimizes RUL predictions enhances data privacy and security establishes transparency and promotes collaboration in decentralized manufacturing It addresses key challenges such as maintaining privacy and security ensuring transparency and fairness and incentivizing participation in decentralized networks Experimental validation using the NASA CMAPSS dataset demonstrates the model effectiveness in real world scenarios and we extend our findings to the broader research community through open source code on GitHub inviting collaborative development to drive innovation in Industry 5.0
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。