通过仿真分析研究发动机故障下的热工参数变化规律，针对稳态工况建立较优的故障诊断模型，为后续训练复杂工况下的故障诊断模型提供依据。基于Modelica语言构建中船动力M320DM-PFI甲醇/柴油双燃料中速机工作过程模型，随后模拟喷油正时异常、单缸供油减少及压缩机/涡轮机效率下降、空气滤清器堵塞等故障，并用最小冗余最大相关算法（MRMR）筛选参数，优化稳态工况下故障诊断模型。经实验数据标定后，建立的中速机模型误差小于5%，仿真数据值得参考。各故障的仿真结果符合理论规律，仿真结果可靠。基于分数最高的8、6、4、2种特征参数训练故障诊断模型，测试的准确率分别为100%、100%、98.02%、87.86%。建立的modelica仿真模型可以为建立各类故障诊断模型提供数据参考。若针对研究的6种故障进行故障诊断，宜选用MRMR评分最高的4～6种特征参数来训练模型，可以在保障准确率的前提下缩减工作量。
Through simulation analysis, this study investigates the variation patterns of thermodynamic parameters under engine faults, aiming to establish an optimized fault diagnosis model for steady-state conditions and provide a basis for training fault diagnosis models under complex conditions. A working process model of the M320DM-PFI methanol/diesel dual-fuel medium-speed engine from CPGC was built using Modelica language. Faults such as abnormal fuel injection timing, reduced single-cylinder fuel supply, decreased compressor/turbine efficiency, and air filter blockage were simulated. The Minimum Redundancy Maximum Relevance (MRMR) algorithm was used to screen parameters and optimize the fault diagnosis model for steady-state conditions. After calibration with experimental data, the medium-speed engine model achieved an error rate of less than 5%, making the simulation data reliable. The simulation results for each fault align with theoretical patterns, ensuring their validity. Fault diagnosis models were trained using the top 8, 6, 4, and 2 feature parameters based on MRMR scores, achieving test accuracies of 100%, 100%, 98.02%, and 87.86%, respectively. The Modelica simulation model established in this study can serve as a data reference for developing various fault diagnosis models. For diagnosing the six proposed faults, selecting 4～6 feature parameters with the highest MRMR scores is recommended, as it ensures accuracy while reducing workload.
2026,48(2): 94-101 收稿日期：2025-5-9
DOI：10.3404/j.issn.1672-7649.2026.02.016
分类号：U664.12
作者简介：吴唐奕(2001-),男,硕士研究生,研究方向为内燃机仿真与故障诊断
参考文献：
[1] 刘长铖. 基于Modelica语言的柴油机建模仿真研究[D]. 哈尔滨: 哈尔滨工程大学, 2017
[2] 李方玉, 汪翔, 陆轶, 等. 大型动力装置的故障模拟及分析[J]. 机电工程技术, 2022, 51(2): 102-105.
LI F Y, WANG X, LU Y, et al. Fault Simulation and Analysis of Large-Scale Power Equipment[J]. Mechanical & Electrical Engineering Technology, 2022, 51(2): 102-105.
[3] 张海涛. 船舶双燃料发动机故障诊断系统优化研究[J]. 舰船科学技术, 2020, 42(4): 76-78.
ZHANG H T. Research on the optimization of fault diagnosis system for marine dual fuel engine[J]. Ship Science and Technology, 2020, 42(4): 76-78.
[4] 何雨谦, 陈于涛. 大功率舰用柴油机Modelica建模与故障模拟[J]. 舰船科学技术, 2022, 44(9): 92-97.
HE Y Q, CHEN Y T. Modelica-based modeling and fault simulation of high-power marine diesel engines[J]. Ship Science and Technology, 2022, 44(9): 92-97.
[5] 郭晓成. 甲醇/柴油双燃料发动机健康评估与故障诊断方法研究[D]. 镇江: 江苏科技大学, 2024.
[6] 张振京, 曹石, 窦全礼, 等. 深度学习与异常信息融合的内燃机燃油系统智能诊断方法[J]. 北京化工大学学报(自然科学版), 2025, 52(2): 76-87.
ZHANG Z J, CAO S, DOU Q L, et al. A deep learning and anomaly information fusion intelligent diagnosis method for the fuel system in internal combustion engine[J]. Journal of Beijing University of Chemical Technology(Natural Science), 2025, 52(2): 76-87.
[7] 毛荣珍, 米洁, 甄真, 等. 基于数据增强的多输出分类旋转机械复合故障诊断[J]. 北京信息科技大学学报(自然科学版), 2025, 40(1): 94-101.
MAO R Z, MI J, ZHEN Z, et al. Multi-output classification fault diagnosis of rotating machinery based on data augmentation[J]. Journal of Beijing Information Science and Technology University (Natural Science Edition), 2025, 40(1): 94-101.
[8] 唐杰烽, 张佳, 龙锦益. 基于全局冗余最小的快速多标签特征选择方法[J/OL]. 山东大学学报(工学版). 2025, (2025-05-23) [2025-06-23].
TANG J F, ZHANG J, LONG J Y. A fast multi-label feature selection method based on global redundancy minimization [J/OL]. Journal of Shandong University (Engineering Science), 2025, (2025–05–23) [2025–06–23].
[9] 岳广阔. 基于Matlab /Simulink的船用柴油/天然气双燃料发动机建模与燃烧特性研究[D]. 哈尔滨: 哈尔滨工程大学, 2020.
[10] 李文辉, 刘长铖, 马修真, 等. 基于Modelica语言建模的柴油机稳动态性能仿真与试验[J]. 农业工程学报, 2016, 32(21): 87-94.
LI W H, LIU C C, MA X Z, et al. Steady-state and dynamic performance simulation and testing of diesel engine based on modelica language modeling[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(21): 87-94.
[11] 李兆华. 基于Modelica语言的柴油机热动力学耦合建模及仿真分析[D]. 哈尔滨: 哈尔滨工程大学, 2019.
[12] 黄加亮, 乔英志, 王丹, 等. 船用四冲程增压柴油机整机建模与故障模拟[J]. 大连海事大学学报, 2013, 39(1): 93-98.
HUANG J L, QIAO Y Z, WANG D, et al. Whole engine modeling and fault simulation of a marine four-stroke turbocharged diesel engine[J]. Journal of Dalian Maritime University, 2013, 39(1): 93-98.
[13] 高伟冲. 船用柴油机典型故障分析与诊断技术研究[D]. 哈尔滨: 哈尔滨工程大学, 2016.
[14] 赵震宇, 朱军超, 温华兵, 等. 船用涡轮增压器典型故障特征参数的敏感性研究[J]. 舰船科学技术, 2023, 45(10): 121-126.
ZHAO Z Y, ZHU J C, WEN H B, et al. Sensitivity study of characteristic parameters for typical faults in marine turbochargers[J]. Ship Science and Technology, 2023, 45(10): 121-126.
[15] 王林. 基于性能参数的船用柴油机健康状态评估及故障诊断研究[D]. 哈尔滨: 哈尔滨工程大学, 2023.
[16] 仲国强. 基于数据驱动的船舶柴油机智能故障诊断研究[D]. 大连: 大连海事大学, 2020.
[17] 朱向利. 基于KNN算法的柴油机故障诊断方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2016.
[18] 林新通, 詹玉龙, 周薛毅, 等. 支持向量机在船舶柴油机废气涡轮增压器故障诊断中的应用[J]. 上海海事大学学报, 2012(2): 18-21.
LIN X T, ZHAN Y L, ZHOU X Y, et al. Application of support vector machine in fault diagnosis of marine diesel engine turbochargers[J]. Journal of Shanghai Maritime University, 2012(2): 18-21.
[19] 王涛, 崔岗, 刘阳江, 等. 空气滤清器与空气预滤器的匹配[J]. 工程机械. 2011, 42(6): 45–47.
WANG T, CUI G, LIU Y J, et al. Matching of Air Filters and Air Pre-filters[J]. Construction Machinery, 2011, 42(6): 45–47.
[20] 李方玉, 杨雷, 胡以怀. 某双燃料动力装置整机仿真与故障模拟分析[J]. 舰船科学技术. 2025, 47(3): 95–100.
LI F Y, YANG L, HU Y H. Whole-engine simulation and fault simulation analysis of a dual-fuel power plant[J]. Ship Science and Technology, 2025, 47(3): 95–100.
[21] 晏飞, 杜雨辰, 张建, 等. 船用柴油机喷油器故障分析及维护方法[J]. 机械工程师. 2015(12): 208–210.
YAN F, DU Y C, ZHANG J, et al. Fault analysis and maintenance methods of marine diesel engine fuel injectors[J]. Mechanical Engineer, 2015(12): 208–210.
[22] 李海庆, 解永辉, 殷海红, 等. 某中速柴油机工作不均匀原因分析及试验研究[J]. 内燃机与配件, 2021(13): 1-2.
LI H Q, XIE Y H, YIN H H, et al. Analysis and experimental study on the causes of uneven operation of a medium-speed diesel engine[J]. Internal Combustion Engine & Parts, 2021(13): 1-2.
[23] 王海翔. 谈柴油机喷油正时的影响因素及检查[J]. 农机使用与维修, 2018(10): 58.
WANG H X. Discussion on influencing factors and inspection of diesel engine fuel injection timing[J]. Agricultural Machinery Use & Maintenance, 2018(10): 58.
[24] 刘鑫龙. 基于数据的船舶柴油机故障诊断研究[D]. 大连: 大连海事大学, 2022.
[25] 赵震宇. 船用柴油机典型故障模拟分析与诊断方法研究[D]. 镇江: 江苏科技大学, 2022.
