留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于机器学习的船舶机舱设备状态监测方法

王瑞涵 陈辉 管聪

王瑞涵, 陈辉, 管聪. 基于机器学习的船舶机舱设备状态监测方法[J]. 中国舰船研究, 2021, 16(1): 158–166, 192 doi: 10.19693/j.issn.1673-3185.02150
引用本文: 王瑞涵, 陈辉, 管聪. 基于机器学习的船舶机舱设备状态监测方法[J]. 中国舰船研究, 2021, 16(1): 158–166, 192 doi: 10.19693/j.issn.1673-3185.02150
WANG R H, CHEN H, GUAN C. Condition monitoring method for marine engine room equipment based on machine learning[J]. Chinese Journal of Ship Research, 2021, 16(1): 158–166, 192 doi: 10.19693/j.issn.1673-3185.02150
Citation: WANG R H, CHEN H, GUAN C. Condition monitoring method for marine engine room equipment based on machine learning[J]. Chinese Journal of Ship Research, 2021, 16(1): 158–166, 192 doi: 10.19693/j.issn.1673-3185.02150

基于机器学习的船舶机舱设备状态监测方法

doi: 10.19693/j.issn.1673-3185.02150
基金项目: 工信部“绿色智能内河船舶创新专项”资助项目;国家重点研发计划资助项目(2019YFE0104600);国家自然科学基金资助项目(51909200)
详细信息
    作者简介:

    王瑞涵,男,1994年生,博士生。研究方向:船舶设备的健康管理与智能运维。E-mail:rhan_wang@163.com

    陈辉,男,1962年生,博士,教授。研究方向:船舶动力系统建模与控制及船舶智能化技术。E-mail:hchen@whut.edu.cn

    管聪,男,1987年生,博士,副教授。研究方向:船舶动力系统建模、仿真及控制技术。E-mail:guancong2008@126.com

    通信作者:

    陈辉

  • 中图分类号: U676.4+2

Condition monitoring method for marine engine room equipment based on machine learning

知识共享许可协议
基于机器学习的船舶机舱设备状态监测方法王瑞涵,等创作,采用知识共享署名4.0国际许可协议进行许可。
  • 摘要:   目的  为实现船舶机舱设备的智能状态监测,引入机器学习算法,提出一种结合流形学习和孤立森林的船舶机舱设备状态监测方法。  方法  由于船舶机舱设备的状态监测数据是多维度数据,基于该监测系统,通过流形学习来提取有效的数据特征,实现对原始数据的降维,减少数据复杂度。基于孤立森林算法,在仅利用正常工况数据集的情况下,训练并构建多个子森林检测器,用于实现对目标设备的故障监测。在Matlab/Simulink环境下建立大型船舶二冲程柴油机模型,对其正常工况和故障工况下的数据进行仿真,以验证该方案的有效性。  结果  通过状态仿真数据对不同故障监测方案性能的比较,验证了所提故障监测方案具有98.5%的故障检测率和3%的故障虚警率。  结论  所提方法能显著提高船舶机舱设备的故障监测性能。
  • 图  1  基于流形学习和孤立森林的故障监测流程图

    Figure  1.  Procedures of the manifold learning-iforest monitoring scheme

    图  2  7K98MC船用柴油机仿真模型

    Figure  2.  The simulation model of 7l98MC marine diesel engine

    图  3  不同流形学习方法的降维效果

    Figure  3.  The dimensionality reduction effect of different manifold learning methods

    图  4  不同故障监测方案的FDR与FAR值

    Figure  4.  Comparison of FDR and FAR under different hybrid fault monitoring schemes

    图  5  不同故障监测方案的阈值

    Figure  5.  Thresholds of different hybrid fault monitoring schemes

    表  1  7K98MC船用柴油机技术指标

    Table  1.   Technical parameters of 7K98MC marine diesel engine

    技术指标数值技术指标数值
    缸径/mm980最大额定转速/(r·min−1)94
    行程/mm2 660最大平均指示压力/bar18.2
    活塞面积/m20.754 3最高爆发压力/bar140.1
    整机重量/t2 100涡轮增压器3×TPL85-B11
    最大功率/kW40 055发火顺序1-7-2-5-4-3-6
    下载: 导出CSV

    表  2  不同负荷下柴油机模型仿真值与台架实验值的比较

    Table  2.   Comparison between simulation results and shop test data

    柴油机
    负荷/%
    结果功率/
    kW
    油耗/
    (g·kW−1·h−1
    气缸最高爆发
    压力/bar
    气缸压缩
    压力/bar
    涡轮转速/
    (r ·min−1
    扫气箱
    压力/bar
    排气管
    温度/K
    25仿真值10 105186.0474.0447.9544851.33579.29
    实验值10 014186.3773.6047.4042911.32577.17
    误差/%0.92−0.180.591.164.530.540.37
    50仿真值20 226179.6099.4372.6278962.07593.68
    实验值20 028179.4698.0072.0077822.05600.17
    误差/%0.990.081.460.861.470.89−1.08
    75仿真值30345175.03127.91100.139 7102.86611.63
    实验值30041176.01128.0099.909 6702.87614.57
    误差/%1.01−0.55−0.070.230.41−0.40−0.48
    100仿真值40462177.69138.40125.6710 9433.58660.83
    实验值40055177.98139.40126.7010 9463.63663.90
    误差/%1.02−0.16−0.71−0.81−0.03−1.39−0.46
    下载: 导出CSV

    表  3  仿真数据集

    Table  3.   Simulation datasets

    类别工况特征个数数量
    1正常15400
    2压缩机故障15100
    3空冷机故障15100
    4喷油定时错误15100
    下载: 导出CSV

    表  4  不同故障监测方案的平均FDR与FAR值

    Table  4.   The accuracy FDR and FAR under different hybrid fault monitoring schemes

    方法FDR/%FAR/%
    PCA-OS81.21.63
    PCA-RC81.11.62
    PCA-iforest81.31.6
    MDS-OS851.24
    MDS-RC85.51.23
    MDS-iforest87.11.2
    LLE-OS92.11.1
    LLE-RC93.18.5
    LLE-iforest93.49
    TSNE-OS94.97.5
    TSNE-RC96.16
    TSNE-iforest98.53
    下载: 导出CSV
  • [1] ELAMIN F, FAN Y B, GU F S, et al. Diesel engine valve clearance detection using acoustic emission[J]. Advances in Mechanical Engineering, 2010, 2: 495741. doi: 10.1155/2010/495741
    [2] KOWALSKI J, KRAWCZYK B, WOŹNIAK M. Fault diagnosis of marine 4-stroke diesel engines using a one-vs-one extreme learning ensemble[J]. Engineering Applications of Artificial Intelligence, 2017, 57: 134–141. doi: 10.1016/j.engappai.2016.10.015
    [3] CHEN H, ZHANG Z H, GUAN C, et al. Optimization of sizing and frequency control in battery/supercapacitor hybrid energy storage system for fuel cell ship[J]. Energy, 2020, 197: 117285.
    [4] 宫文峰, 陈辉, 张泽辉, 等. 基于改进卷积神经网络的滚动轴承智能故障诊断研究[J]. 振动工程学报, 2020, 33(2): 400–413.

    GONG W F, CHEN H, ZHANG Z H, et al. Intelligent fault diagnosis for rolling bearing based on improved convolutional neural network[J]. Journal of Vibration Engineering, 2020, 33(2): 400–413 (in Chinese).
    [5] 宫文峰, 陈辉, 张美玲, 等. 基于深度学习的电机轴承微小故障智能诊断方法[J]. 仪器仪表学报, 2020, 41(1): 195–205.

    GONG W F, CHEN H, ZHANG M L, et al. Intelligent diagnosis method for incipient fault of motor bearing based on deep learning[J]. Chinese Journal of Scientific Instrument, 2020, 41(1): 195–205 (in Chinese).
    [6] 尚前明, 王瑞涵, 陈辉, 等. 多信息融合技术在船舶柴油机故障诊断中的应用[J]. 中国航海, 2018, 41(3): 26–31. doi: 10.3969/j.issn.1000-4653.2018.03.006

    SHANG Q M, WANG R H, CHEN H, et al. Application of multi-information fusion technology for fault diagnosis in marine diesel engine[J]. Navigation of China, 2018, 41(3): 26–31 (in Chinese). doi: 10.3969/j.issn.1000-4653.2018.03.006
    [7] GONG W F, CHEN H, ZHANG Z H, et al. A data-driven-based fault diagnosis approach for electrical power DC-DC inverter by using modified convolutional neural network with global average pooling and 2-D feature image[J]. IEEE Access, 2020(8): 73677–73697. doi: 10.1109/ACCESS.2020.2988323
    [8] 仲国强, 贾宝柱, 肖峰, 等. 基于深度信念网络的船舶柴油机智能故障诊断[J]. 中国舰船研究, 2020, 15(3): 136–142, 184.

    ZHONG G Q, JIA B Z, XIAO F, et al. Intelligent fault diagnosis of marine diesel engine based on deep belief network[J]. Chinese Journal of Ship Research, 2020, 15(3): 136–142, 184 (in Chinese).
    [9] 刘国强, 林叶锦, 张志政, 等. 基于粗糙集和优化DAG-SVM的船舶主机故障诊断方法[J]. 中国舰船研究, 2020, 15(1): 68–73.

    LIU G Q, LIN Y J, ZHANG Z Z, et al. Main marine engine fault diagnosis method based on rough set theory and optimized DAG-SVM[J]. Chinese Journal of Ship Research, 2020, 15(1): 68–73 (in Chinese).
    [10] KONAR P, CHATTOPADHYAY P. Bearing fault detection of induction motor using wavelet and support vector machines (SVMs)[J]. Applied Soft Computing, 2011, 11(6): 4203–4211. doi: 10.1016/j.asoc.2011.03.014
    [11] BICEGO M, FIGUEIREDO M A T. Soft clustering using weighted one-class support vector machines[J]. Pattern Recognition, 2009, 42(1): 27–32. doi: 10.1016/j.patcog.2008.07.004
    [12] DIEZ-OLIVAN A, PAGAN J A, SANZ R, et al. Data-driven prognostics using a combination of constrained K-means clustering, fuzzy modeling and LOF-based score[J]. Neurocomputing, 2017, 241: 97–107. doi: 10.1016/j.neucom.2017.02.024
    [13] ZHANG L W, LIN J, KARIM R. An angle-based subspace anomaly detection approach to high-dimensional data: with an application to industrial fault detection[J]. Reliability Engineering & System Safety, 2015, 142: 482–497.
    [14] 李新鹏, 高欣, 阎博, 等. 基于孤立森林算法的电力调度流数据异常检测方法[J]. 电网技术, 2019, 43(4): 1447–1456.

    LI X P, GAO X, YAN B, et al. An approach of data anomaly detection in power dispatching streaming data based on isolation forest algorithm[J]. Power System Technology, 2019, 43(4): 1447–1456 (in Chinese).
    [15] 张俊, 王杨, 李坤豪, 等. 基于流形学习的多源传感器体域网数据融合模型[J]. 计算机科学, 2020, 47(8): 323–328.

    ZHANG J, WANG Y, LI K H, et al. Multi-source sensor body area network data fusion model based on manifold learning[J]. Computer Science, 2020, 47(8): 323–328 (in Chinese).
    [16] MALM L A, ENSTRM J, HULTMAN A. Main engine damage study[EB/OL]. [2020-10-16]. http://www.swedishclub.com.
    [17] GUAN C, THEOTOKATOS G, ZHOU P L, et al. Computational investigation of a large containership propulsion engine operation at slow steaming conditions[J]. Applied Energy, 2014, 130: 370–383. doi: 10.1016/j.apenergy.2014.05.063
  • ZG2150_en.pdf
  • 加载中
图(5) / 表(4)
计量
  • 文章访问数:  798
  • HTML全文浏览量:  251
  • PDF下载量:  151
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-10-20
  • 修回日期:  2020-11-16
  • 网络出版日期:  2021-01-19
  • 刊出日期:  2021-02-28

目录

    /

    返回文章
    返回