为有效滤除舰船动力电路信号内的噪声和干扰，提取出有用的故障特征，并在复杂多变的运行环境中，准确诊断各种未知故障类型，研究基于神经网络的舰船动力电路故障诊断方法。利用栈式稀疏自编码器在舰船动力电路信号内，提取有用的电路故障特征，利用其稀疏性滤除电路信号内的噪声和干扰，减少故障特征之间的冗余；通过K-means算法，优化概率神经网络结构；在优化后的概率神经网络内，输入有用的故障特征，输出舰船动力电路故障诊断结果，依据其强大的在线学习能力，提升其对未知故障诊断的适应性。实验证明该方法可有效提取舰船动力电路故障特征；在不同噪声强度的运行环境下，该方法均可精准诊断电路故障。
In order to effectively filter out the noise and interference in the signal of ship power circuit, extract the useful fault characteristics, and accurately diagnose various unknown fault types in the complex and variable operating environment, a fault diagnosis method of ship power circuit based on neural network is studied. The stack sparse auto encoder is used to extract useful circuit fault features from ship power circuit signals, and the noise and interference in circuit signals are filtered by its sparsity to reduce the redundancy between fault features. The structure of probabilistic neural network is optimized by K-means algorithm. In the optimized probabilistic neural network, useful fault features are input and the fault diagnosis results of ship power circuit are output. According to its powerful online learning ability, its adaptability to unknown fault diagnosis is improved. Experimental results show that this method can extract the fault characteristics of ship power circuit effectively. The method can accurately diagnose circuit faults under different noise intensity operating environment.
2024,46(18): 118-121 收稿日期：2024-2-12
DOI：10.3404/j.issn.1672-7649.2024.18.020
分类号：TP391
基金项目：辽宁省教育科学“十四五”规划2022年度立项课题（JG22EB040）
作者简介：霍艳飞(1972-),女,硕士,高级实验师,研究方向为电力控制技术
参考文献：
[1] 王匀, 钱鑫, 翁业翠, 等. 分数阶时滞忆阻混沌电路的动力学分析及电路仿真[J]. 舰船电子工程, 2021, 41(2): 88-91+158.
WANG Yun, QIAN Xin, WENG Yecui, et al. Dynamic analysis and circuit simulation of fractional-order memristive time-delay chaotic system[J]. Ship Electronic Engineering, 2021, 41(2): 88-91+158.
[2] 陈晓娟, 刘禹盟, 曲畅, 等. 基于FSSA-ELM的模拟电路故障诊断方法[J]. 半导体技术, 2024, 49(1): 77-84.
CHEN Xiaojuan, LIU Yumeng, QU Chang, et al. Analog circuit fault diagnosis method based on FSSA-ELM[J]. Semiconductor Technology, 2024, 49(1): 77-84.
[3] 夏玲, 姜媛媛, 张杰, 等. 基于数字孪生的Buck电路故障诊断方法[J]. 工矿自动化, 2021, 47(2): 88-92, 115.
XIA Ling, JIANG Yuanyuan, ZHANG Jie, et al. Buck circuit fault diagnosis method based on digital twin[J]. Industry and Mine Automation, 2021, 47(2): 88-92, 115.
[4] 刘美容, 刘津涛, 何怡刚. 基于EMD复合多尺度熵的模拟电路故障诊断方法[J]. 电子测量技术, 2021, 44(4): 51-56.
LIU Meirong, LIU Jintao, HE Yigang. Simulation circuit fault diagnosis method based on EMD composite multi-scale entropy[J]. Electronic Measurement Technology, 2021, 44(4): 51-56.
[5] 李楠, 邓威, 王晨, 等. 基于K-means聚类与概率神经网络的模拟电路故障诊断方法[J]. 中国测试, 2021, 47(3): 98-103, 109.
LI Nan, DENG Wei, WANG Chen, et al. Analog circuit fault diagnosis method based on K-means and probabilistic neural network[J]. China Measurement & Testing Technology, 2021, 47(3): 98-103, 109.
[6] 刘沛霖, 刘美容, 何怡刚, 等. 基于改进的VMD和SVM的模拟电路故障诊断方法的研究[J]. 微电子学与计算机, 2022, 39(11): 85-94.
LIU Peilin, LIU Meirong, HE Yigang, et al. Research on fault diagnosis method of analog circuit based on improved VMD and SVM[J]. Microelectronics & Computer, 2022, 39(11): 85-94.
