基于广义粗糙集与神经网络集成的旋转机械故障诊断研究

故障诊断规则中判断条件的冗余、不完全和不确定性不利于实际应用。采用广义粗糙集理论对旋转机械振动故障诊断的非完备决策系统进行了约简 ,得到了更为简明的最优诊断规则 ;根据约简结果 ,建立了基于神经网络的故障诊断系统 ;网络的训练对比结果表明 ,基于粗糙集理论的约简处理简化了神经网络结构 ,提高了网络的训练效率 ;以诊断实例验证了广义粗糙集理论与神经网络集成进行故障诊断的可行性     

粗糙集规则获取在旋转注水机组故障诊断中的应用

粗糙集理论能够有效地处理不精确、不完整的数据和知识,并从中发现隐含知识,提示潜在规律。提出一种基于粗糙集理论的大型旋转机械故障诊断和知识获取模型。该模型从包含冗余和不一致信息的原始数据出发, 构建决策表,通过属性约简和基于分明矩阵的属性值约简获取故障诊断的最小约简属性集和诊断规则,并建立诊断规则知识库。基于该模型以某旋转注水机组故障分析为例,从来自实际的经验数据获取旋转注水机组转子故障诊断的规则知识,其属性约简率可达25％,并能有效解决旋转注水机组故障诊断中规则获取的知识冗余或缺失问题,验证了其有效性。     

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。     

基于粗糙集的旋转机械振动故障诊断研究

振动故障是旋转机械最常见的故障,旋转机械故障诊断常用的是振动分析法.粗糙集理论是一种研究不完整数据、不精确知识的表达、学习和归纳的数学工具.基于粗糙集理论,对旋转机械的振动故障诊断决策表进行分类、约简和核集的形成,推导出最简明的决策表,从而提取故障诊断的重要属性,降低决策表的冗余性.研究表明,粗糙集理论应用于旋转机械振动故障诊断可得到更明晰的诊断规则,从而提高了故障诊断的实时性和快速性.     

基于粗糙集理论的状态监测与故障诊断

为了提高监测诊断的效率和自动化、智能化水平,将粗糙集理论引入到复杂装备系统状态监测与故障诊断领域.运用基于粗糙集理论的监测参数与故障特征约简算法,对发动机监测诊断过程中大量的冗余特征进行压缩或约简,实现发动机技术状态监测参数的优选;并针对故障点建立决策表,利用粗糙集约简所获得的诊断规则进行智能故障诊断.实例表明:粗糙集监测诊断方法不仅大大减少了特征信息提取的工作量,也为在故障诊断中实现自主式学习和决策提供了很大的便利.     

基于粗糙集理论的状态监测与故障诊断

为了提高监测诊断的效率和自动化、智能化水平,将粗糙集理论引入到复杂装备系统状态监测与故障诊断领域.运用基于粗糙集理论的监测参数与故障特征约简算法,对发动机监测诊断过程中大量的冗余特征进行压缩或约简,实现发动机技术状态监测参数的优选;并针对故障点建立决策表,利用粗糙集约简所获得的诊断规则进行智能故障诊断.实例表明粗糙集监测诊断方法不仅大大减少了特征信息提取的工作量,也为在故障诊断中实现自主式学习和决策提供了很大的便利.     

粗糙集在滚动轴承故障诊断中的应用

对滚动轴承几种常见点蚀故障的振动信号特征值进行分析,使用粗糙集基于熵的离散化算法进行属性离散化,并采用基于属性重要度的启发式约简算法进行属性约简,然后选用径向基核函数的支持向量机将经过属性约简的特征向量输入支持向量机训练,建立支持向量机模型并进行故障识别与诊断。实验分析结果表明,应用粗糙集和支持向量机相结合的混合智能诊断方法,将粗糙集作为支持向量机的前置系统对数据进行预处理,利用粗糙集可以减少信息表达的属性数量和故障诊断决策系统的规则数,使支持向量机输入端数据量大大减少,提高系统的处理速度,对于滚动轴承振动信号的故障模式识别可以获得良好的效果。从而验证了粗糙集理论对滚动轴承故障诊断的有效性以及其应用价值。     

基于粗糙集与神经网络的齿轮箱故障诊断

对粗糙集的属性离散化和约简算法进行了研究,提出了一种基于粗糙集与神经网络相融合的故障诊断方法。首先提出一种优化NS断点集的方法用于离散化决策表,然后采用差别矩阵和差别函数直接求取最小属性约简集,最后采用神经网络对JZQ-250齿轮箱进行故障诊断,并比较了约简前后特征集的诊断结果,实验表明粗糙神经网络能够简化网络结构,有较强的容错和抗干扰能力,且迭代次数少,收敛速度快,诊断精度高,是一种有效的齿轮箱故障诊断方法。     

基于粗糙集与支持向量机的电动机转子断条故障诊断

提出了一种基于粗糙集与支持向量机的电动机转子断条故障诊断方法。首先将电动机在不同故障状态下的振动信号离散化,再应用粗糙集软件rosetta对数据进行进一步的约简,得到约简后的数据应用于支持向量机的训练从而得到基于支持向量机的多分类器。实验证明:该方法检测电动机的转子断条故障是可行的。     

基于决策能力的启发式属性约简及其在诊断中的应用

基于粗糙集理论中决策表条件属性区分能力的概念,提出了计算属性决策能力的量化方法,并以此作为启发式信息来指导决策表中冗余属性的约简,提高了约简效率。这种方法直接应用于机械故障诊断中的知识约简,可以得到更清晰、简明的诊断规则,应用结果表明本约简算法合理、可靠。     

Rough set based rule learning and fuzzy classification of wavelet features for fault diagnosis of monoblock centrifugal pump

The fault diagnosis problem is conceived as a classification problem. In the present study, vibration signals are used for fault diagnosis of centrifugal pumps using wavelet analysis. Rough set theory is applied to generate the rules from the vibration signals. Based on the strength of the rules the faults are identified. The different faults considered for this study are: pump at good condition, cavitation, pump with faulty impeller, pump with faulty bearing and pump with both faulty bearing and impeller. However, the classification accuracy is based on the strength and number of rules generated using rough set theory. Wavelet features are computed using Discrete Wavelet Transform (DWT) from the vibration signals and rules are generated using rough sets and classified using fuzzy logic. The results are presented in the form of confusion matrix which shows the classification capability of wavelet features with rough set and fuzzy logic for fault diagnosis of monoblock centrifugal pump.     

Fault diagnosis based on Walsh transform and rough sets

An accurate and fast method for fault diagnosis is an important issue most techniques have sought to. For this reason, a fast fault diagnosis method based on Walsh transform and rough sets is proposed in this paper. Firstly, fault signals are fast transformed by Walsh matrix, and the Walsh spectrums are obtained, whose statistical characteristics constitute feature vectors. Secondly, the feature vectors are discretized and reduced by the rough sets theory, as a result, key features are retained and diagnosis rules are provided. Finally, utilized these diagnosis rules, fault diagnosis is carried out experimentally in the spectrum domain and its performance is compared with that of other methods, the higher accuracy is achieved and much time is saved, which fully validates the effectiveness of our approach.     

A hybrid approach of rough set theory and genetic algorithm for fault diagnosis

This paper proposes an integrated intelligent system that builds a fault diagnosis inference model based on the advantage of rough set theory and genetic algorithms (GAs). Rough set theory is a novel data mining approach that deals with vagueness and can be used to find hidden patterns in data sets. Based on this approach, minimal condition variable subsets and induction rules are established and illustrated using an application for motherboard electromagnetic interference (EMI) test fault diagnosis. This integrated system successfully integrated the rough set theory for handling uncertainty with a robust search engine, GA. The result shows that the proposed method can reduce the number of conditional attributes used in motherboard EMI fault diagnosis and maintain acceptable classification accuracy. The average diagnostic accuracy of 80% shows that this hybrid model is a promising approach to EMI diagnostic support systems .     

基于粗糙集理论的航空发动机滑油光谱诊断专家系统知识获取方法研究

针对航空发动机滑油光谱诊断专家系统的知识获取问题,本文建立了基于粗糙集理论的航空发动机滑油光谱诊断专家系统知识获取模型。首先建立反映光谱元素浓度及元浓度梯度与发动机磨损故障之间关系的典型故障样本集;然后运用粗糙集理论的离散、约简及规则提取等算法,从大量的故障样本中自动获取知识规则,并将知识规则存储于专家系统知识库中;最后,建立推理机,运用一定的推理策略实现发动机磨损故障诊断。本文利用航空发动机实测的油样光谱数据对所建立的粗糙集知识获取方法,进行了实例验证。     

基于粗集理论的往复泵泵阀故障诊断方法

提出了一种基于粗集理论的往复泵泵阀故障诊断方法。该方法可以直接从经过小波包处理的泵阀振动信号中提取故障诊断观测，并由此建立基于规则的泵阀故障诊断系统，该系统不仅可以对发生故障的单个泵阀进行诊断，而且还能对同时发生故障的多个泵阀进行诊断，试验结果表明了这种方法的有效性。这种方法的可行性也为其它复杂机械的故障诊断提供了新思路。     

Fault diagnosis of multistage manufacturing systems based on rough set approach

Multistage manufacturing systems (MMS) have been investigated extensively. However, quality and dimensional problems are still one of the most important research topics, especially rapid diagnosis of dimensional failures is of critical concern. Due to the knowledge and experience intension nature of fault diagnosis, the diagnostic results depend on the preference of the decision makers on the hidden relations between possible faults and presented symptoms. In this paper, a rough set-based fault diagnosis method is proposed, and a rapid fault diagnosis system with rough set is developed. The novel approach uses rough sets theory as a knowledge extraction tool to deal with the data that are obtained from both sensors and statistical process control charts and then extracts a set of minimal diagnostic rules encoding the preference pattern of decision making by experts in the field. By means of knowledge acquisition, the machining process failures in MMS can then be identified. A practical system is presented to illustrate the efficiency and effectivity of our method.     

瞬态声与粗糙集在轴承故障诊断中的应用

针对设备实车测试中无法得到稳态信号的制约,以及常规的振动测试方法无法实现非接触、不解体、无损在线检测的弊端,提出了利用瞬态声信号对轴承进行故障诊断.并利用粗糙集理论对故障诊断决策表进行约简,形成清晰、简明的故障诊断规则,有效地提高了轴承故障诊断的精度和效率.     

基于粗集理论的高精度伺服仿真转台故障诊断研究

介绍了粗集理论基本原理，详述了某型高精度伺服仿真转台机电控制系统的实现方案。将粗集理论应用于该仿真转台的故障诊断，提出的策略以决策表为主要工具，直接从故障样本集中导出诊断规则，并揭示了仿真转台故障信息内在冗余性。实际应用表明了用粗集理论对高精度伺服仿真转台进行故障诊断的有效性和可靠性。在该高精度伺服仿真转台上已完成多项含实物实时仿真综合试验任务。