当船舶起锚机离合器出现故障时，需要采用有效的故障诊断技术判断其故障类型以及故障元器件。BP神经网络是一种具有自主学习能力的记忆网络，可以实现线性和非线性函数之间的映射，并以此为基础对网络中存储的记忆进行训练，从而提高起锚机离合器的精检测。本文从BP神经网络技术入手，论述其在船舶起锚机离合器故障信号检测的应用，为故障检测提供实用操作价值。
When the clutch fails, effective fault diagnosis technology is needed to judge its fault type and fault components. BP neural network is a kind of memory network with self-learning ability, which can realize the mapping between linear and nonlinear functions, and train the memory stored in the network on this basis, so as to improve the precision detection of ship windlass clutch. Therefore, this paper starts with the BP neural network technology and discusses its rapid application in the fault signal of the marine windlass clutch, which will bring practical operation value in the future fault detection.
2022,44(23): 165-168 收稿日期：2022-09-15
DOI：10.3404/j.issn.1672-7649.2022.23.034
分类号：U667.5
作者简介：耿瑞焕(1986-)，女，硕士，讲师，主要从事数据挖掘及信息处理研究
参考文献：
[1] 徐鹏, 杨海燕, 程宁, 等. 基于优化BP神经网络的船舶动力系统故障诊断[J]. 中国舰船研究, 2021, 16(1):8
XU Peng, YANG Hai-yan, CHENG Ning, et al. Fault diagnosis of ship power system based on optimized BP neural network[J]. China Ship Research, 2021, 16(1):8
[2] 蒋佳炜, 胡以怀, 方云虎, 等. 船舶动力装置智能故障诊断技术的应用与展望[J]. 中国舰船研究, 2020, 15(1):56-67
JIANG Jia-wei, HU Yi-huai, FANG Yun-hu, LI Fang-yu. Application and Prospect of Intelligent Fault Diagnosis Technology of Ship Power Plant[J]. Chinese Ship Research, 2020, 15(1):56-67
[3] 林驰, 陈军, 王波, 等. 浅析工程船舶动力机械状态监测与故障诊断现状及发展[J]. 中国设备工程, 2021(22):175-177
LIN Chi, CHEN Jun, WANG Bo, ZHAO Xin, CHEN Hai-feng. Analysis on the Status and Development of Condition Monitoring and Fault Diagnosis of Engineering Ship Power Machinery[J]. China Equipment Engineering, 2021(22):175-177
[4] 杨奕飞, 冯静. 基于HMM-SVR的船舶动力设备故障模式识别与状态预测研究[J]. 船舶工程, 2018, 40(3):68-72+97
YANG Yi-fei, FENG Jing. Research on Fault Mode Recognition and State Prediction of Ship Power Equipment Based on HMM-SVR[J]. Ship Engineering, 2018, 40(3):68-72+97
[5] 李乐, 舒越超, 吴健鹏, 等. 基于PSO-BP神经网络湿式摩擦元件损伤预测模型[J]. 北京理工大学学报自然版, 2022, 42:1-10
LI Le, SHU Yue-chao, WU Jian-peng, et al. Damage prediction model of wet friction elements based on PSO-BP neural network[J]. Journal of Beijing Institute of Technology, 2022, 42:1-10
