针对舰船发电用柴油机增压器的润滑失效问题，提出一种改进多阈值方法来实现对多工况异常情况的实时预测。该方法包含两部分，首先参考滑动平均滤波法对比分析各机组的运行数据，实现对异常数据的提取；其次采用一种基于外部特性法的箱型图法对分析后提取的异常数据进行多阈值表达式的设定。为了验证方法的有效性，基于某发电用柴油机在发电机工作过程中的实际故障数据进行验证，利用C++和Qt建立了可视化的增压器润滑失效故障在线监测与预测系统。验证表明，依据改进多阈值方法建立的系统可以实现对增压器在发电机全负载工作过程中异常情况的判断和对润滑失效的预测。
In this paper, based on the lubrication failure of marine diesel generator supercharger, an improved multi-threshold method is proposed for solving the real-time prediction of abnormal situations. This method contains two points, firstly, the operating data of each unit were compared and analyzed by referring to the moving average filtering method,so as to achieve the extraction of abnormal data;secondly, a box graph method based on external characteristic method is used to set multi-threshold expressions for the extracted abnormal data after analysis. In order to verify the validity of the method，based on the actual failure data in the working process, the visually online monitoring and prediction system of the supercharger’s lubrication failure is established by using C++ and Qt. The verification shows that the system established by the multi-threshold method can realize the real-time judgment on abnormal circumstances and the prediction of the supercharger’s lubrication failure in the whole load working process of the generator.
2022,44(2): 145-150 收稿日期：2021-05-06
DOI：10.3404/j.issn.1672-7649.2022.02.026
分类号：U664.1
作者简介：杨天诣(1996-)，男，硕士，主要从事船舶轮机工程健康管理方面研究
参考文献：
[1] 叶朝阳, 宫国鹏. 从一起事故谈TCA66增压器的应急润滑[J]. 航海技术, 2011(3): 59–61
[2] 辛易达. 润滑供油压力对涡轮增压器转子稳定性影响[J]. 长春工业大学报, 2018, 39(3): 261–266
[3] 张健航, 储期祯, 傅则明. 分析与评价润滑系统的一种方法——用外部特性线法判别故障与匹配状况[J]. 内燃机工程, 1982(4): 10–20
[4] 童宝宏, 桂长林, 孙军, 等. 内燃机润滑系统主油道压力特性的多工况研究[J]. 车用发动机, 2008(2): 27–30
[5] 郭林山, 胡鹏, 孙平, 等. YZ485ZLQ柴油机润滑系统性能与主油道压力特性试验[J]. 内燃机, 2014(3): 50–53+57
[6] OMAR Trigui, SAWSAN Daoud, MOHAMED Ghorbel, et al. SSVEP enhancement using moving average filter controlled by phase features[J]. Computational Intelligence and Neuroscience, 2020
[7] 陈艳拢, 王晓岚, 李恩, 等. CEM的波段选择方法研究及应用[J]. 光谱学与光谱分析, 2020, 40(12): 3778–3783
[8] ZHANG Liu-ye, DING Ling-jie, DONG Li-yan, et al. Endpoint prediction of PSO-RBF converter steelmaking based on big data[J]. International Journal of Computational and Engineering, 2019, 4(1).
[9] 寇元宝, 汪崇建, 贠瑞光. 采煤机运行数据预处理算法研究. [J]煤矿机械, 2020, 41(10): 41−43.
