﻿ 多传感器融合下船舶机电系统多发故障信号监测
 舰船科学技术  2024, Vol. 46 Issue (5): 149-152    DOI: 10.3404/j.issn.1672-7649.2024.05.027 PDF

Multiple fault signal monitoring of ship electromechanical system under multi-sensor fusion
LI Lie-xiong, DAI Li-qing
Fujian Chuanzheng Communications College, Fuzhou 350007, China
Abstract: In order to improve the efficiency of ship maintenance, a multi-sensor fusion based monitoring method for multiple fault signals in ship electromechanical systems is proposed. Based on the frequency of the signal in the fault state, the wavelet transform method is used to extract the characteristic parameters of the fault signal as input for the ant colony algorithm to optimize the BP neural network, achieve multi fault diagnosis, and complete multi-sensor data fusion through DS evidence theory to obtain the fault diagnosis results, realizing the monitoring of multi fault signals in the ship's electromechanical system. The experimental results show that this method can determine the type of faults in ship electromechanical systems through multi-sensor fusion. Even if one sensor fails, it does not affect the diagnostic effect. The average accuracy of diagnosing multiple faults in ship electromechanical systems is as high as 97.02%, which can achieve more accurate monitoring of multiple faults in ship electromechanical systems.
Key words: multi-sensor fusion     ship electromechanical system     fault monitoring     wavelet transform     ant colony algorithm     DS evidence theory
0 引　言

1 船舶机电系统多发故障监测 1.1 故障信号特征提取

 ${f_t} = \left( {1 \pm 2s} \right)f。$ (1)

 $\alpha \left( {{f_t}} \right) = \sum\limits_{i = 1}^k {{g_i}\left( {{f_t}} \right) + {d_z}\left( {{f_t}} \right)}，$ (2)

 ${\beta _{pq}}^w\left( t \right) = \left\{ \begin{split} &{\gamma _{pq}}^\varsigma \left( t \right){\kappa _{pq}}^\tau \left( t \right)/{\gamma _{pr}}^\varsigma \left( t \right){\kappa _{pr}}^\tau \left( t \right)\begin{array}{*{20}{c}} ,&{q \in R} ，\end{array} \\ & 0\begin{array}{*{20}{c}} ,&{{\mathrm{else}}} 。\end{array} \end{split} \right.$ (4)

 $y = h\left( {best} \right)\left( {\sum\limits_{u = 0}^u {{\omega _{uv}}{x_u} - \delta } } \right)。$ (6)

1.3 多发故障信号监测的实现

 ${2^\varphi } = \left\{ {{x_1}} \right\},\left\{ {{x_2}} \right\}, \cdots ,\left\{ {{x_1},{x_2}} \right\}, \cdots ,\varphi。$ (7)

 $\eta \left( H \right) = \varphi \eta \left( \xi \right)\left( {1 - \iota } \right)。$ (8)

 $\eta \left( H \right) = \varphi \eta \left( \xi \right)。$ (9)

 图 1 故障监测系统结构图 Fig. 1 Structural diagram of fault monitoring system

2 实验分析

 图 2 不同故障类型监测准确率 Fig. 2 Monitoring accuracy for different types of faults

3 结　语

 [1] 陈福兰. 船舶机电系统故障信号远程通信容错诊断方法[J]. 舰船科学技术, 2021, 43(20): 115-117. CHEN Fulan. Fault tolerant diagnosis method of remote communication for fault signal of marine electromechanical system[J]. Ship Science and Technology, 2021, 43(20): 115-117. [2] 李青, 李钊阳, 王天钦, 等. 基于DS证据理论融合油液振动多参数的故障诊断方法研究[J]. 机械强度, 2023, 45(3): 534-540. LI Qing, LI Zhaoyang, WANG Tianqin, et al. Research on fault diagnosis method of oil vibration based on ds evidence theory and multi-parameter fusion[J]. Journal of Mechanical Strength, 2023, 45(3): 534-540. [3] 王向阳, 李自良. 基于模糊神经网络的信号维护监测子系统故障预测研究[J]. 自动化仪表, 2022, 43(4): 59-62. WANG Xiangyang, LI Ziliang. Research on fault prediction of signal maintenance support subsystem based on fuzzy neural network[J]. Process Automation Instrumentation, 2022, 43(4): 59-62. [4] 孙思琦, 崔英英, 梁雅博, 等. 自适应传输技术在风机故障监测中的应用研究[J]. 计算机测量与控制, 2023, 31(3): 43-48,55. SUN Siqi, CUI Yingying, LIANG Yabo, et al. Research on application of adaptive transmission technology in fan fault monitoring[J]. Computer Measurement & Control, 2023, 31(3): 43-48,55. [5] 马标, 贾俊铖, 董国柱, 等. WAGAN: 基于小波变换和注意力机制的工控传感器数据异常检测方法[J]. 小型微型计算机系统, 2023, 44(1): 168-176. MA Biao, JIA Juncheng, DONG Guozhu, et al WAGAN: Industrial control sensor data anomaly detection method based on wavelet trans form and attention mechanism [J]. Journal of Chinese Computer Systems, 2023, 44(1): 168-176. [6] 王骁贤, 陆思良, 何清波, 等. 变转速工况下基于多传感器信号深度特征融合的电机故障诊断研究[J]. 仪器仪表学报, 2022, 43(3): 59-67. WANG Xiaoxian, LU Siliang, HE Qingbo, et al. Motor fault diagnosis based on deep feature fusion of multi-sensor data under variable speed condition[J]. Chinese Journal of Scientific Instrument, 2022, 43(3): 59-67. [7] 周洋, 罗棋, 孙伶俐, 等. 基于局部线性模型的传感器故障检测仿真[J]. 计算机仿真, 2022, 39(6): 490-495. ZHOU Yang, LUO Qi, SUN Lingli , et al. Simulation of sensor fault detection based on local linear model [J]. Computer Simulation, 2022, 39(6): 490-495. [8] 陈书辉, 章猛, 刘辉, 等. 一种1D-CNN与多传感器信息融合的液压系统故障诊断方法[J]. 机械科学与技术, 2023, 42(5): 715-723. CHEN Shuhui, ZHANG Meng, LIU Hui, et al. A method for diagnosing faults of hydraulic pump and accumulator with 1D-CNN and multi-sensor information fusion[J]. Mechanical Science and Technology for Aerospace Engineering, 2023, 42(5): 715-723.