基于VMD-RCMFE的船用柴油机故障特征提取方法

Fault Feature Extraction for Marine Diesel Engines Based on VMD-RCMFE

柴油机作为船舶的核心动力来源,一旦发生故障将严重影响船舶安全,为保证船舶及船员安全,需要对船舶柴油机进行故障诊断研究。本文以WP6型船用6缸柴油机为研究对象,对失火、进气滤器堵塞、进气门间隙过大及排气门间隙过大多种故障进行研究。针对船舶柴油机缸盖振动信号的非线性和非平稳特性,提出一种基于变分模态分解(Variational Mode Decomposition,VMD)、精细化复合多尺度模糊熵(Refined Composite Multiscale Fuzzy Entropy,RCMFE)、支持向量机(Support Vector Machines,SVM)的柴油机故障诊断方法。该方法首先利用VMD方法对缸盖振动信号进行降噪处理,然后利用RCMFE方法提取柴油机缸盖振动信号中隐含的故障特征,最后采用SVM模型进行诊断,诊断精度高达99.2%。

Diesel engine is the core power source of the ship,its failure will seriously affect the safety of the ship.In order to ensure the safety of the ship and crew members,it is necessary to study the fault diagnosis method for marine diesel engines.In this paper,a 6-cylinder diesel engine of WP6 ship was taken as the research object,and the multiple faults such as misfire,intake filter blockage,excessive intake valve clearance and excessive exhaust valve clearance were researched.Aiming at the non-linear and non-smooth characteristics of the vibration signal of the cylinder head of the marine diesel engine,a method based on variational mode decomposition(VMD),refined composite multiscale fuzzy entropy(RCMFE)and support vector machines(SVM)was proposed for diesel engine fault diagnosis.Firstly,the VMD method was used to reduce the noise of the cylinder head vibration signal.Then,the RCMFE method was applied to extract the fault features implied in the cylinder head vibration signal of the diesel engine Finally,the SVM model was adopted for diagnosis.It was found that the diagnostic accuracy can be up to 99.2%.