共查询到18条相似文献,搜索用时 93 毫秒
1.
2.
MMAS与粗糙集在轴承复合故障诊断中的应用 总被引:4,自引:0,他引:4
在分析振动加速度信号的基础上,提出了新的粗糙集属性约简算法,并应用于轴承复合故障诊断.将最大一最小蚂蚁系统(max-min ant system,简称MMAS)引入条件属性约简中,以最坏Fisher准则函数作为启发式信息以提高搜索效率,综合考虑分类正确率和条件属性个数两方面因素,利用粗糙集理论约简故障诊断决策表,有效地提高了轴承故障诊断的效率. 相似文献
3.
4.
提出一种改进决策树智能故障诊断方法.首先构建故障诊断原始决策表,然后对特征数据进行离散化处理;接着利用可辨识矩阵约简算法对决策表进行属性约简;最后利用 G45 算法构造出最优诊断决策树;并对实例进行故障诊断.结果表明:该方法能有效地删除冗余信息,形成精简的决策规则库,提高故障识别速度,具有很强的工程实用性. 相似文献
5.
6.
基于支持向量机集成的模拟电路故障诊断 总被引:8,自引:4,他引:4
为了解决模拟电路故障诊断复杂多样难于辨识的问题,有效提高分类的准确度,提出了一种支持向量机集成的故障诊断方法.首先,该方法对采集信号进行Haar小波变换,提取1~5层小波变换的每层第1个低频系数构成特征集.然后将特征集输入集成支持向量机,实现对不同故障类型进行识别.将该方法应用于Sallen-Key带通和4运放双二次高通滤波电路进行故障诊断实验,结果表明,该方法比单一支持向量机、径向基神经网络、BP神经网络和集成K-NN分类器有更好的分类和泛化性能,故障诊断准确率更高. 相似文献
7.
提出了一种基于粗糙集属性约简技术的测点优化配置方法。首先根据齿轮箱的故障机理确定了基本测点,采用粗糙集理论建立了测点优化决策表;然后提出了采用基于属性频率的差别矩阵法求取最小属性约简集,避免了复杂的布尔运算;最后通过对约简集进行分析找到了有效的信号监测点,并且应用BP神经网络进行了仿真验证。实验结果表明该方法不需要对监测对象建模,也不需要进行动力学分析,而是根据时频域指标与故障种类之间的关联程度选择有效监测点,通过监控有效监测点,采集有效故障信息,有利于提高故障诊断的效率和准确率。 相似文献
8.
9.
为了提高汽轮机转子故障诊断的准确率和识别效率,提出了一种基于混沌的生物地理学优化算法(biogeography-based optimization with chaos,简称CS-BBO)和支持向量机(support vector machine,简称SVM)相结合的故障诊断方法。首先,将混沌理论引入到生物地理学优化算法(biogeography-based optimization,简称BBO)中,得到CS-BBO算法;其次,通过CS-BBO算法优化SVM得到诊断模型的最优参数,增强SVM的学习能力和泛化能力;最后,通过ZT-3转子试验台模拟汽轮机转子故障,利用得到的4种状态下的试验数据验证优化模型的有效性。结果表明:CS-BBO算法优化SVM的模型可以准确、高效地对汽轮机转子进行故障诊断;与BBO算法优化SVM模型相比,该方法的故障诊断准确率和识别效率更高。 相似文献
10.
在二级齿轮箱的变负载过程中,为了有效地处理非平稳信号,采用小波包提取特征参量(条件属性值);为了有效地处理带噪声的数据,将变精度粗糙集理论引入到齿轮的故障诊断中,提出了一种条件属性约简方法.首先对连续属性进行离散化;然后定义集合M,根据实际情况,选取不同的正确分类率β,利用变精度粗糙集的近似分类质量进行条件属性约简,并与加入噪声数据后所得的约简结果进行了对比;最后通过齿轮故障实例验证了此方法的有效性和实用性. 相似文献
11.
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. 相似文献
12.
13.
To analyze data from multi-level view, reduce computational burden, and improve fault diagnosis accuracy, a novel fault diagnosis method of rolling bearings based on mean multigranulation decision-theoretic rough set (MMG-DTRS) and non-naive Bayesian classifier (NNBC) is proposed in this paper. First, fault diagnosis features of rolling bearings in training samples are extracted to construct MMG-DTRS. Then, the significance degree of condition attribute in MMG-DTRS is defined to quantitatively measure the influence of condition attributes with respect to the decision ability of an information system. An attribute reduction algorithm based on MMG-DTRS is applied to acquire a lower dimensional condition attribute set, which reduces computational complexity and avoids the interference of irrelevant or redundant condition attributes. Finally, NNBC is constructed to classify rolling bearing conditions in test samples. The classification procedures by using NNBC are given. The performance of the proposed method is validated and the advantages are investigated by using a fault diagnosis experiment of rolling bearings. Experimental investigations demonstrate the proposed method is effective and reliable in identifying fault categories and fault severities of rolling bearings. 相似文献
14.
15.
Imbalanced fault diagnosis of rotating machinery using autoencoder-based SuperGraph feature learning
Existing fault diagnosis methods usually assume that there are balanced training data for every machine health state. However, the collection of fault signals is very difficult and expensive, resulting in the problem of imbalanced training dataset. It will degrade the performance of fault diagnosis methods significantly. To address this problem, an imbalanced fault diagnosis of rotating machinery using autoencoder-based SuperGraph feature learning is proposed in this paper. Unsupervised autoencoder is firstly used to compress every monitoring signal into a low-dimensional vector as the node attribute in the SuperGraph. And the edge connections in the graph depend on the relationship between signals. On the basis, graph convolution is performed on the constructed SuperGraph to achieve imbalanced training dataset fault diagnosis for rotating machinery. Comprehensive experiments are conducted on a benchmarking publicized dataset and a practical experimental platform, and the results show that the proposed method can effectively achieve rotating machinery fault diagnosis towards imbalanced training dataset through graph feature learning. 相似文献
16.
Jun Yu Mingyou Bai Guannan Wang Xianjiang Shi 《Journal of Mechanical Science and Technology》2018,32(1):37-47
In planetary gearbox operation, there are many uncertain factors that may result in incomplete diagnostic information, such as measurement instrument faults, limitation of transmission capacity, and data processing. Therefore, it has been one of the greatest obstacles to fault diagnosis of planetary gearbox. To address this issue, a novel fault diagnosis method of planetary gearbox with incomplete information using assignment reduction and Flexible naive Bayesian classifier (FNBC) is proposed. Characteristic relation was utilized to preprocess incomplete diagnostic information. Then, assignment reduction algorithm based on characteristic relation was used to remove irrelevant or redundant condition attribute values. Finally, FNBC was constructed to reason diagnosis results. To validate the performance of the proposed method, a fault diagnosis experiment was conducted. The experimental studies demonstrate the proposed method can be utilized to diagnose planetary gearbox faults with incomplete diagnostic information, reduce computational complexity, and enhance reasoning accuracy. 相似文献
17.