基于车用发动机振动信号的状态参数研究

利用分形的特征参数——关联维数来表征发动机振动信号的分形性质。对多组不同状态的振动序列运用相空间重构法进行处理,计算出不同状态的关联维数,并探讨了关联维数与运行状态之间的内在联系,同时结合燃料敲缸系数、机械敲缸系数进一步判断发动机的运行状态,及时发现运行状态中的异常变化。实验结果表明,关联维数能定量评估发动机的状态演化,敏感地反应发动机的运行状态。     

关联维数及其在故障诊断中的应用研究

从工程实际问题出发,论述了分形维数的基本概念和性质,给出了定量描述分形特征的重要参数－－关联维数的计算方法,分析了发动机故障的特点,提出了将关联维数用于汽车发动机故障诊断的技术路线及方法。     

基于振动信号的车用发动机运行状态预测

考虑到车用发动机结构复杂、振源较多，振动信号为非平稳信号的特点，文中利用混沌与分形理论对多组不同运行状态的振动序列进行研究，探讨关联维数与运行状态之间的内在联系，并利用混沌与神经网络相结合的方法对主要状态参量进行单变量及多变量预测。实验结果表明，关联维数能敏感反应发动机的磨损状态，而多变量的预测效果比单变量效果理想。     

自回归谱的分形特性在状态监测中的应用研究

研究了机械设备在工作状态下噪声信号自回归谱的分形特性，提出可以用关联维数描述设备的工作状态特征，进而对工况进行识别，实验表明，机械设备在相同的工作状态下，噪声信号的自回归谱有相近的关联维数，而在不相同状态下则有明显不同的关键维数，关联维数可作为机械设备状态的重要依据，能够有效地补充其他特征提取方法的不足。     

汽车发动机曲轴和缸体再生新工艺的试验研究

通过对斯太尔汽车发动机曲轴和缸体磨损后采用新工艺进行试验研究，证明斯太尔曲轴和缸体是能够再生的，这对于延长汽车发动机寿命和降低用户成本有着重要意义。     

基于关联维数的滚动轴承故障诊断的研究

针对滚动轴承系统产生的非线性振动信号的特点,提出用关联维数来描述轴承振动信号的工作状态,进而对其进行故障诊断的方法。同时详细讨论了关联维数的计算方法,并对由轴承系统产生的非线性振动信号进行了关联维数的定量计算。实验表明,滚动轴承不同工作状态由不同的动力学机理产生,其关联维数明显不同。以关联维数作为滚动轴承的工作状态监测的依据,可以为提高滚动轴承故障诊断的准确率提供了一种有效的新方法。     

铣削过程中振动信号的关联维特征

采用关联维数定量刻画铣削过程中的不同工作状态的振动特征,估计出已加工表面的粗糙度.在计算关联维数中,对选择嵌入维数和延迟时间提出了一种改进的G-P算法,求解出在不同主轴转速、不同进给速度、不同切削深度的切削用量下铣削振动信号的关联维数.研究表明:在不同切削状态下,工件的振动信号的关联维数不同;且随着工件振动信号关联维数的增加,加工表面粗糙度也随之增加.因此,关联维数可以作为识别已加工表面粗糙度的特征量.     

汽车发动机气缸热喷涂涂层的现状及未来发展

汽车发动机是汽车的核心部件,对于汽车实际使用性能以及燃油消耗具有关键性的影响。汽车发动机气缸热喷涂涂层对于保护汽车发动机气缸,降低燃油消耗发挥着重要作用。因此,有必要加强对汽车发动机气缸热喷涂涂层的研究。本文浅析了汽车发动机气缸热喷涂涂层的现状,探究了汽车发动机气缸热喷涂涂层的未来发展,以期为汽车发动机气缸热喷涂涂层研究提供借鉴。     

分形维数在内燃机振动诊断中的应用

将分形理论引入内燃机的振动诊断中,根据内燃机的配气定时,着重研究了缸盖振动信号中对应燃烧段的数据,计算其关联维数,将关联维数用于刻划内燃机缸盖在气门不同状态时表现的非线性行为,从而进行故障诊断与分类。结果表明,当气门在不同状态时,缺盖振动信号中对应燃烧段数据的关联维数是不同的,可以将其作为判断气门漏气的一个诊断特征量。     

基于AR高阶谱及其关联维数分析的减压阀故障诊断

为了识别减压阀的工作状态,建立了减压阀不同工作状态采集信号的时间序列AR模型,绘制了AR三谱、双谱及其切片谱图,计算了各切片谱的关联维数,综合分析了不同工作状态系统的谱图及关联维数变化。分析结果表明,AR三谱、双谱、各切片谱及其关联维数各自对工作状态变化的敏感性不同,双谱对角切片的关联维数、三谱及其切片谱对工作状态变化较敏感,更适合用于减压阀故障诊断,同时AR三谱、双谱的一维切片谱及其关联维数在反映系统动力学特性方面分别存在对应关系,可以将切片谱和关联维数相结合对减压阀进行故障诊断分析。     

Diesel Engine Valve Clearance Fault Diagnosis Based on Features Extraction Techniques and FastICA-SVM

Numerous vibration-based techniques are rarely used in diesel engines fault diagnosis in a direct way, due to the surface vibration signals of diesel engines with the complex non-stationary and nonlinear time-varying features. To investigate the fault diagnosis of diesel engines,fractal correlation dimension, wavelet energy and entropy as features reflecting the diesel engine fault fractal and energy characteristics are extracted from the decomposed signals through analyzing vibration acceleration signals derived from the cylinder head in seven different states of valve train. An intelligent fault detector FastICA-SVM is applied for diesel engine fault diagnosis and classification.The results demonstrate that FastICA-SVM achieves higher classification accuracy and makes better generalization performance in small samples recognition. Besides,the fractal correlation dimension and wavelet energy and entropy as the special features of diesel engine vibration signal are considered as input vectors of classifier Fast ICASVM and could produce the excellent classification results.The proposed methodology improves the accuracy of feature extraction and the fault diagnosis of diesel engines.     

基于熵理论和BP神经网络的船舶柴油机磨损故障识别

磨损监测与故障诊断是保证船舶柴油机安全可靠运行的重要技术手段。随着船舶柴油机运行可靠性的要求增高,其磨损监测需要更加全面,数据呈高维化,无关数据和冗余数据增多,使故障诊断的复杂程度增大,且近年来,船舶柴油机故障诊断的智能化需求日益增高。针对以上问题和需求,基于信息熵理论,应用信息熵值与度量熵组合设计柴油机磨损监测与故障诊断特征属性约简算法,将某型柴油机润滑磨损故障诊断特征指标维度从16维降低至7维;应用设计的BP神经网络和磨损故障模式识别规则,以该型柴油机44个磨损故障诊断数据样本为对象,进行应用验证与研究分析。结果表明,构建的模型在保证数据集分类特性的基础上,有效实现其数据降维,且所构建的磨损故障识别BP神经网络在属性约简后,故障识别的准确性有明显提高。     

油田用柴油发动机常见故障分析与维修分析

柴油发动机属于电气设备中的往复性动力机械,由于其在运行过程中,经常需要进行持续性作业,且需要在恶劣的开采环境中运行.因此经常会不定期的出现一些故障.本文将以油田用柴油发动机作为研究主题,简要阐述油田用柴油机的工作原理,分析柴油发动机常见故障以及成因,最后探讨油田用柴油发动机常见的故障诊断与相应的维修策略.     

基于Wigner分布和分形维数的柴油机故障诊断

针对柴油机配气机构故障诊断问题,提出了一种基于Wigner分布和差分分形盒维数的故障诊断方法。首先,利用改进局部均值分解算法对柴油机缸盖振动信号进行分解,并采用相关性分析剔除噪声和伪分量;然后,分别对各相关分量进行Wigner时频分析,将结果线性叠加得到振动时频图,再提取图像的差分分形盒维数作为故障特征;最后,利用k-最近邻(k-NN)实现故障诊断。仿真结果表明,改进局部均值分解算法可以抑制Wigner分布交叉项的干扰。实验结果显示,差分分形盒维数优于其他6种典型故障特征,利用本研究提出的方法对配气机构进行故障诊断的正确率为97.2%,该方法可以用于柴油机配气机构故障诊断。     

基于可变风险SVM模型的柴油机故障诊断技术

针对传统故障模式识别方法不能区别不同误判所造成损失不同的问题,提出了可变风险支持向量机(SVM)模型,对传统SVM模型的最优分类面进行重新设计,在利用实际数据识别故障的同时融入专家经验,使故障识别结果更具可靠性,该方法已成功应用于柴油机故障诊断.     

A review of condition monitoring and fault diagnosis for diesel engines

Technical advances and environmental legislation in recent years have stimulated the development of a number of techniques for condition monitoring and fault diagnosis (CMFD) in diesel engines. This paper firstly summarises common faults, fault mechanisms and their effect on diesel engine performance. Corresponding measurands are presented. Standard CMFD methods for parameters and CMFD systems for diesel engines are reviewed. Finally, some advanced CMFD techniques, including neural networks and fuzzy logic, which may be more powerful, are discussed.     

基于LabVIEW的柴油机故障诊断虚拟仪器开发

开发了一套基于分形理论,使用柴油机声音信号进行故障诊断的虚拟仪器.介绍了其硬件平台的搭建,结合LabVIEW与MATLAB混合编程阐述了软件平台的设计,该平台由声音信号采集、信号预处理、故障特征提取、故障诊断4个模块构成.在故障特征提取模块中对分形关联维数的G-P算法进行了论述.结合柴油机故障实例测试表明:柴油机声音信号关联维数随工作状况改变有明显变化,能作为故障诊断的特征量,通过该虚拟仪器能迅速有效地识别出故障.     

Relation between particulate emissions and exhaust smoke level in premixed charge compression ignition engine

For simplicity in measurement, the smoke level or opacity of the exhaust gas is often measured in diesel engine tests for the purpose of estimating the level of particulate emissions in the belief that smoke level is proportional to the particulate emissions. Existence of the correlation between these two has been well established in conventional diesel engines, but it is not clear yet whether the linear relationship stays in PCCI engines, which are known to emit significantly less NOx but more hydrocarbons than the conventional diesel engines. The objective of this study was to investigate the existence of the correlation between the smoke level and particulate mass in a directly fuel-injected PCCI engine with a DOC in the exhaust system. The smoke and PM are simultaneously measured before and after the DOC, while the single-cylinder diesel engine is operated in either diesel or PCCI combustion mode under various operation conditions. The study reveals that many more hydrocarbons and particulates are emitted in PCCI combustion than in the diesel combustion, and the strong correlation between the engine-out smoke level and particulate emissions in the diesel combustion does not exist in PCCI combustion. The correlation, however, comes back in the post-DOC measurements where most of SOF contained in PM is removed by the DOC.     

Diagnosis and condition monitoring of medium-speed marine diesel engines

Diagnosis of diesel engines is not new and various methods have been proposed in the past for fault diagnosis. The problems relating to marine diesel engines, especially medium- and high-speed engines, are due mainly to their large size, which does not allow the use of trial and error methods, and their high operating speed. The most difficult problem occurs when the engine is not able to produce its maximum power, while there is no obvious fault or error. In the present work a method is described which attempts to offer a solution to such problems. The method is a thermodynamic one based on a simulation model and the processing of measured engine data. Presented is an application of the method to a medium-speed marine diesel engine, which suffered from low power output accompanied by high exhaust gas temperatures. The results from application of the method show that the problem is not a direct one, but is caused by many factors that result in improper operation. With this method, the current engine condition can be discovered, and suggestions made for proper tuning or repair. After conducting such an analysis, a vessel was able to achieve its maximum cruising speed, showing that the proposed method is a promising one.