本文基于声发射信号和迁移学习，提出一种新的柴油机燃烧室故障诊断方法。研究在TBD234V6型柴油机上模拟了喷油器堵塞、启阀压力减小和排气阀漏气故障等，用CompactRIO硬件进行信号采集，并针对燃烧室部件故障后声发射信号的特征进行分析。研究表明，以特征参数提取和迁移学习为基础的故障诊断方法能更准确地识别不同故障类型，相对于传统机器学习算法，其准确度更高，泛化能力也更强，对于数据样本较少和不同数据分布的情况下也有较好适应性。此研究对于保证柴油机燃烧室部件的健康状况、确保船舶安全航行具有重要意义。
Based on acoustic emission signal and transfer learning, a new fault diagnosis method for diesel combustion chamber is presented in this paper. In this paper, the oil injector blockage, valve pressure reduction and exhaust valve leakage fault are simulated on TBD234V6 diesel engine. CompactRIO hardware is used to collect signal, and the characteristics of AE signal after the failure of combustion chamber components are analyzed. Research shows that fault diagnosis method based on feature parameter extraction and transfer learning can identify different fault types more accurately. Compared with traditional machine learning algorithm, fault diagnosis method has higher accuracy, stronger generalization ability, and better adaptability to the case of fewer data samples and different data distribution. This study is of great significance to ensure the health of diesel combustion chamber components and safe navigation of ships.
2024,46(5): 80-85 收稿日期：2023-05-05
DOI：10.3404/j.issn.1672-7649.2024.05.015
分类号：U672
作者简介：夏敬停(1973-),男,工程师,研究方向为船舶轮机检验
参考文献：
[1] 文公立. 船舶柴油机虚拟拆装训练及评估系统研究[D]. 厦门: 集美大学, 2010.
[2] 余永华, 杨建国, 胡闹. 智能机舱关键部件状态监测诊断技术研究[J]. 船舶, 2018, 29(S1): 98-105.
[3] 柯赟, 宋恩哲, 姚崇, 等. 船舶柴油机故障预测与健康管理技术综述[J]. 哈尔滨工程大学学报, 2020, 41(1): 125-131.
[4] 雷亚国, 贾峰, 孔德同, 等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报, 2018, 54(5): 94-104.
[5] 郑怀亮, 王日新, 杨远涛, 等. 数据驱动故障诊断方法泛化性能的经验性分析[J]. 机械工程学报, 2020, 56(9): 102-117.
[6] 汪翔, 苏万华. 柴油高压喷嘴内部的压力波动与不稳定空化现象分析[J]. 内燃机学报, 2010, 28(3): 193-198.
[7] 黄荣基, 黄伟民. 柴油机燃油系统故障诊断的探讨[J]. 广州大学学报:自然科学版, 2005, 4(4): 362-365.
[8] SCRUBY C B. An introduction to acoustic emission[J]. Journal of Physics E Scientific Instruments, 1987, 20(8): 946.
[9] CAESARENDRA W, KOSASIH B, TIEU A K, et al. Acoustic emission-based condition monitoring methods: Review and application for low speed slew bearing[J]. Mechanical Systems and Signal Processing, 2016, 72: 134-159.
[10] GU D, KIM J, KELIMU T, et al. Evaluation of the use of envelope analysis and DWT on AE signals generated from degrading shafts[J]. Materials Science and Engineering, 2012, 177(19): 1683-1690.
[11] 刘喜武. 弹性波场理论基础[M]. 靑岛: 中国海洋大学出版社, 2008.
[12] CHEE K T, PHIL I, DAVID M. Mba a comparative experimental study on the use of acoustic emission and vibration analysis for bearing defect identification and estimation of defect size[J]. Mechanical System and Signal Processing, 2006, 20(1): 208-233.
[13] HAN Long, LI Chengwei, GUO Songlin, et al. Feature extraction method of bearing AE signal based on improved FAST-ICA and wavelet packet energy[J]. Mechanical Systems and Signal Processing, 2015, 62: 91-99.
[14] 楼狄明. 天然气制合成油(GTL)在轿车柴油机上的燃烧与排放特性研究[D]. 上海: 同济大学, 2007.
[15] 曹建伟. 催化装置烟机的故障分析和诊断[J]. 设备管理与维修, 2005(12): 29-30.
[16] 纪松林. 工程岩体损伤声发射源定位优化研究[D]. 重庆: 重庆大学, 2013.
[17] 高帆, 李洪元, 吴帆. 基于频谱分析的离心泵健康状态监测及故障诊断[J]. 自动化仪表, 2019(7): 24-28.
[18] 禹化民. Q235钢板腐蚀缺陷超声Lamb波检测研究[D]. 天津: 天津大学, 2014.
[19] BONDARENKO O, FUKUDA T. Potential of acoustic emission in unsupervised monitoring of gas-fuel led engines[J]. IFAC-Papers On Line, 2016, 49(23): 329-334.
[20] ZHANG B, YAN J, TIAN C. Study on fault diagnosis system of diesel engine fuel injection system based on bp neural network[C]//Isecs International Colloquium on Computing, Communication, Control, and Management. IEEE Computer Society, 2008: 108-112.
[21] DOUGLAS R M, STEEL J A, REUBEN R L. A study of the tribological behaviour of piston ring/cylinder liner interaction in diesel engines using acoustic emission[J]. Tribology International, 2006, 39(12): 1634-1642.
[22] 李智, 陈祥初, 刘政波, 等. 基于包络分析的灰色关联度诊断及在柴油机故障诊断中的应用[J]. 小型内燃机, 2000, 29(1): 42-46.
[23] LEI Yaguo, JIA Feng, LIN Jing, et al. An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data[J]. IEEE Transactions on Industrial Electronics, 2016, 63(5): 3137-3147.
[24] WOLD S, ESBENSEN K, GELADI P. Principal component analysis[J]. Chemometrics & Intelligent Laboratory Systems, 1987, 2(1–3): 37-52.
[25] YI Y, DORETTO G. Boosting for transfer learning with multiple sources[C]// The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010, San Francisco, CA, USA, 13-18 June 2010. IEEE, 2010.
[26] DAI Wenyuan, YANG Qiang, XUE Gui-rong, et al. Boosting for Transfer Learning. In Proceedings of the Twenty-Fourth International Conference on Machine Learning, 2007: 193- 200, Corvallis, Ore-gon, USA, 2007(6): 20-24.
