某型涡轴航空发动机磨损状态及趋势预测研究

联合采用发射光谱和铁谱技术对某型航空涡轴发动机进行了磨损状态的分析研究,结果表明:发射光谱技术可准确预测发动机的损坏情况,铁谱技术通过分析磨粒特征,可判断发动机的运行状况、磨损机理及磨损类型,而发射光谱和铁谱技术的联合运用可以较准确地确定发动机润滑部件的磨损状态,诊断磨损故障及预测磨损趋势.     

基于D-S证据理论的航空发动机磨损故障智能融合诊断方法

油样分析方法目前已成为航空发动机磨损故障诊断的重要手段,但单一油样分析技术的诊断准确率均有限,为了提高故障诊断的精度,本文提出了基于D-S证据理论的发动机磨损故障智能融合诊断方法。首先用BP神经网络实现发动机磨损故障的单项智能诊断,然后,充分利用神经网络诊断结果,用D-S证据理论实现了磨损故障的融合诊断。最后,算例验证了本文方法的有效性。     

发动机零部件磨损量的光谱测量数值分析与试验研究

建立新发展的分析模型,采用适当的数值计算方法,对光谱分析数据进行处理,以得到发动机各零部件在运行过程中的实际磨损量,并将这一技术应用于发动机零部件磨损试验。初步验证了这一技术应用于发动机摩擦、磨损分析、试验研究和运行监测、故障预测诊断的可能性,为今后发动机摩擦、磨损分析、试验研究和运行监测及故障预测、诊断提供了有益的途径。     

航空发动机机械磨损的故障探析

本文从航空发动机机械磨损原理入手,着重分析机械磨损对滑油系统的影响及故障磨损监控方法,探索了机械磨损故障诊断技术及诊断技术发展趋势。     

航空发动机磨损故障的智能融合诊断

提出了航空发动机磨损故障的智能融合诊断方法。对油样分析中多种数据源信息的特点进行分析，根据不同的诊断目的对多种分析方法进行了相应的组合；利用基于规则的专家系统诊断技术，分别实现发动机磨损故障的定位、定性及定因的单项诊断；在此基础上，利用D—S证据理论，实现了发动机磨损故障的融合诊断；最后用算例验证了方法的正确性和有效性。     

航空发动机滑油磨粒在线监测

航空发动机轴承部件磨损是导致发动机失效,引起飞机重大事故的主要因素之一。分析了航空发动机突发性剧烈磨损的疲劳磨损失效机理,陈述了磨粒尺寸和数量表征磨损程度的关系,系统介绍了各种航空发动机滑油磨粒在线监测技术,讨论了各技术方法的原理、技术特点、典型参数、典型应用、最新研究成果及技术适应性。滑油磨粒在线监测技术,能有效发现航空发动机突发性剧烈磨损,及时预警失效,避免出现重大事故,具有重大工程应用价值。     

基于油液分析的汽车发动机摩擦系统故障诊断专家系统知识库的建立

采集汽车发动机润滑系统中摩擦副经历磨擦学行为的信息是诊断发动机摩擦系统故障的有效手段。油液分析从摩擦学系统的润滑剂和磨损物两方面获得磨擦副的润滑和磨损状态的信息。但常规的油液分析信息处理方法上的不足影响了油液分析技术在汽车行业的实际应用,开发基于油液分析的故障诊断系统,无疑会改善油液分析的诊断准确性和诊断成本。本文着重针对该诊断专家系统知识库的建立,     

基于加权模糊优选理论的发动机磨损模式识别

发动机磨损模式识别是发动机状态监测与故障诊断的重要环节，如何快速、准确地识别发动机磨损模式是磨损状态监测与诊断的关键。结合大量铁谱分析数据与专家经验。给出了发动机磨损模式识别标准样本库。引进一种模糊相对权重的概念，并结合模糊优选理论建立了发动机磨损模式识别的加权模糊优选分析模型。实践证明，加权模糊优选分析模型能够快速、准确、有效地识别发动机磨损模式。     

发动机铁谱磨粒分析与磨粒识别研究

从发动机摩擦副及其摩擦磨损特点着手，提出了用于发动机磨损状态监测与诊断的主要10类磨粒，依据其识别特征提出了用于磨粒识别的14个磨粒形状、表面纹理与颜色特征；最后应用BP网络分层识别策略进行了磨粒识别。     

采用冷试扭矩零点监控曲轴和瓦片之间的异常磨损

发动机抱死至今仍然是一个无法完全解决的问题,导致抱死的直接原因是发动机曲轴和轴瓦之间出现异常磨损。为了在冷试阶段,发现存在抱死风险的发动机,本文提出了采用冷试扭矩零点监控发动机曲轴和瓦片磨损状态的测试方法,并对发动机进行诊断,诊断结果和实际故障结论一致。     

磨损颗粒的模糊神经网络识别研究

在传统的模式识别技术中，模式分类的基本方法是利用判别函数来划分不同的类别，然而如何选择有效的判别函数以及在识别过程中如何对判别函数的参数进行修正，对于以往的模式识别技术是比较困难的。针对油液铁谱分析中磨损颗粒的识别问题，讨论了一般机械设备的磨损颗粒的特征，分析了神经网络技术和模糊数学相结合的模式，提出了基于模糊神经网络的铁谱图象分类和识别方法，分析结果表明，提出的方法对铁谱分析的智能化和快速化提供一种有效的途径。     

基于粗糙集和神经网络的润滑油中磨损磨粒的识别

为了更有效地对润滑油中的磨损磨粒进行识别,探讨了基于粗糙集和神经网络的磨粒识别。它首先利用粗糙集理论对磨粒特征参数进行约简,这样能够大大减少了神经网络的输入维数。然后介绍了一种径向基神经网络,并利用它对磨粒进行分类。对20个磨粒进行识别,磨粒分类分对14个,分错6个,识别率达到70.0%。     

Surface roughness evolutions in sliding wear process

Wear debris analysis is a technique for machine condition monitoring and fault diagnosis. One key issue that affects the application of wear debris analysis for machine condition monitoring is whether the morphology of the wear particles accurately depicts their original states and the surface morphology of the components from which the particles separate. This study aimed to investigate the evolution of the surface morphology of wear debris in relation to change in the surface morphology of wear components in sliding wear process. Sliding wear tests were conducted using a ball-on-disc tester under proper lubrication and improper lubrication conditions. The study of the particle size distribution and the surfaces of both the wear debris and the tested samples in relation to the wear condition and the wear rates of the wear components were carried out in this study. The evolutions of the surface topographies of both the wear debris and the wear components as wear progressed were investigated. This study has provided insight to the progress of material degradation through the study of wear debris. The results of this research have clearly demonstrated that: (a) there is a good correlation of the surface morphology of wear debris and that of the wear components, and (b) the surface morphology of wear debris contains valuable information for machine condition monitoring.     

Study of grey relational grade identification for ferrography based on characteristic analysis of wear debris

Attention has been focused on how to achieve intelligent automation in ferrographic diagnosis in order to overcome the subjectivity of the diagnosis process. The present paper reports on a technique of characteristic measurement developed on the basis of the VC++ 6.0 programming platform, with characteristic parameters such as area, roundness, and aspect ratio being extracted from images of wear debris based on digital image analysis. However, the extraction of characteristic parameters from a ferrographic image is not the ultimate purpose of ferrographic diagnosis. The wear particles should be classified into several pre‐decision categories and their statistical distribution should also be calculated. The grey relational grade theory is introduced in this paper as a way to recognise wear debris and a new software system has been developed to deal with the problems occurring in the automation of ferrographic diagnosis. It is shown that the identification rules can be used to treat some real wear debris images with generally satisfactory results.     

An integrated intelligence system for wear debris analysis

Wear debris generated from two moving surfaces inside a machine is a direct wear product of operating machinery. The study of the debris can reveal wear mechanisms, wear modes and wear phases undergoing in the machine. Hence, wear debris analysis can be a very useful means to assess the condition of the machine. However, the current techniques for individual particle analysis are usually time-consuming and costly due to the requirement of analyst’s expertise to perform particle inspection, morphology characterisation and data interpretation. The limitation has obstructed the wide application of this method. Therefore, it is necessary to develop effective, reliable and cost-efficient techniques to perform wear debris analysis for industrial application. This paper presents a fully computerised package for wear debris analysis. The package includes three major systems corresponding to a three-dimensional particle analysis system, an automatic particle identification system and an expert system, communicating with each other through user-friendly interfaces. The successful development of such a system has demonstrated the possibility to achieve a fully computerised analysis system for routine and in-depth wear debris study for machine condition monitoring and fault diagnosis.     

基于粗糙集神经网络的刀具磨损监测的研究

针对多传感器刀具磨损监测系统输入维数较多、神经网络结构复杂、收敛速度慢等缺点,提出了粗糙集和遗传算法优化神经网络的模型.该模型首先利用粗糙集理论的属性约简对输入数据进行处理,从而达到减少神经网络输入维数、简化神经网络结构的目的.然后通过遗传算法优化神经网络的初始权值和阈值,以提高神经网络的收敛速度,避免神经网络陷入局部极值点.将该模型应用到刀具磨损监测,通过对声发射信号和电流信号进行处理,提取特征向量值,将特征值先通过自组织神经网络进行连续属性离散化,再通过粗糙集理论进行属性约简,最后通过遗传算法优化的BP神经网络进行识别,取得了很好的效果,证明了此模型的有效性和可行性.     

基于粗糙集-BP神经网络的垃圾破碎机故障诊断

针对目前垃圾破碎机故障诊断效率低的问题,设计了一种基于粗糙集理论与BP神经网络的故障诊断系统。结合粗糙集理论和BP神经网络的优点,首先利用粗糙集对原始故障诊断样本进行处理,然后对条件属性进行约简,删除冗余的信息,减少神经网络输入端的数据,从而简化神经网络的结构。并将基于粗糙集-BP神经网络的故障诊断系统对垃圾破碎机进行故障诊断。利用粗糙集对故障知识进行约简,简化BP神经网络结构,提高故障诊断的速度及准确度。将此方法应用于某型号垃圾破碎机的故障诊断中,诊断结果表明所提诊断方法可简化神经网络结构,提高诊断效率。     

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。