摘 要：为避免电子系统关键电路发生故障导致生命财产问题，提出了基于变分模式分解 (Variational Mode Decomposition, VMD) 和门控循环单元 (Gate Recurrent Unit, GRU) 的电子系统健康状态识别方法，并设计了一款基于 Linux的电子系统健康状态识别平台，用于解决现有维护策略经济成本高、安全性较差的问题。首先，通过 VMD 方法计算故障信号的瞬时能量构建电子系统健康状态因子，其次 , 利用此特征训练 GRU 网络用于识别电子系统健康状态，并基于 Linux 系统设计硬件平台。最后，经过实验证明，平台具有较高准确性和可靠性。
关键词：VMD；GRU；Linux；健康状态识别；故障诊断
DOI:10.19850/j.cnki.2096-4706.2022.19.004
基金项目：江西省教育厅科技研究项目(GJJ210816)
中图分类号：TP316.8 文献标识码：A 文章编号：2096-4706（2022）19-0018-05
Design and Implementation of Health Status Recognition Platform for Electronic System Based on Linux
ZHOU Wu, XU Feiyang, JIANG Xu, LI Yuxiao
(School of Science, Jiangxi University of Science and Technology, Ganzhou 341000, China)
Abstract: In order to avoid life and property problems caused by key circuit fault of electronic system, a method of electronic system health status recognition based on Variational Mode Decomposition (VMD) and Gate Recurrent Unit (GRU) is proposed, and an electronic system health status recognition platform is designed to solve the problems of high economic cost and poor security of existing maintenance strategies. Firstly, the instantaneous energy of fault signal is calculated by VMD method to construct the health status factor of electronic system. Secondly, this feature is used to train GRU network to identify the health status of electronic system, and the hardware platform is designed based on Linux system. Finally, experiments prove that the platform has higher accuracy and reliability.
Keywords: VMD; GRU; Linux; health status recognition; fault diagnosis
参考文献：
[1] 陆宁云，陈闯，姜斌，等.复杂系统维护策略最新研究进展：从视情维护到预测性维护 [J]. 自动化学报，2021，47(1)：1-17.
[2] 潘巍巍 . 故障严重程度识别的有序分类特征分析方法 [D].哈尔滨：哈尔滨工业大学，2013.
[3] SOOTHER D K，UJJAN S M，DEV K，et al.Towards Soft Real-Time Fault Diagnosis for Edge Devices in Industrial IoT Using Deep Domain Adaptation Training Strategy [J].Journal of Parallel and Distributed Computing，2022，160：90-99.
[4] LIAO L X，KÖTTIG F.Review of Hybrid Prognostics Approaches for Remaining Useful Life Prediction of Engineered Systems，and an Application to Battery Life Prediction [J].IEEE Transactions on Reliability，2014，63(1)：191-207.
[5] DRAGOMIRETSKIY K，ZOSSO D.Variational Mode Decomposition [J].IEEE transactions on signal processing，2014，62(3)：531-544.
[6] ZHANG Y H，ZHOU T T，HUANG X F，et al.Fault Diagnosis of Rotating Machinery Based on Recurrent Neural Networks [J].Measurement，2021，171：108774.
[7] LI Y X，ZHOU X L，LI S.A Intermittent Fault Injection Strategy for Electronic Equipment Health Status Recognition [C]//2020 11th International Conference on Prognostics and System Health Management (PHM-2020 Jinan).Jinan：IEEE，2020：68-73.
作者简介：周武 (2001—)，男，汉族，江西宜春人，本科在读，研究方向：信号与信息处理、智能系统。