共查询到20条相似文献,搜索用时 93 毫秒
1.
2.
3.
在变工况齿轮故障诊断过程中,存在齿轮运行工况多变、故障样本数据少、数据分布性差异大和故障数据非均衡性等问题,导致传统的深度学习模型通用性差、诊断准确率不高。针对这些问题,提出了一种基于元学习技术的变工况齿轮故障诊断(VWFD)方法(模型)。首先,采用重叠采样技术,对齿轮的原始振动信号进行了重采样,增加了故障样本的数量;其次,对重采样的故障数据进行了短时傅里叶变换(STFT),将其转化为时频特征图,使其数据形式更加符合模型的输入,以便于后续提取更完善的故障特征;然后,将Inception模块引入到基于元学习技术的原型网络中,以提高其特征表达能力,获取更加全面的齿轮故障特征信息;最后,基于优化的原型网络,建立了各类故障的度量类原型,采用度量分类器进行了故障分类,对变工况下的齿轮故障进行了诊断;为了验证VWFD模型结构与Inception模块引入位置和数量的合理性,设计了一系列对比实验,并对实验结果进行了分析。研究结果表明:与采用其他故障诊断方法得到的结果相比,采用VWFD方法所得到的诊断精度更高,如在相同负载、不同转速变工况类型下的5-way 5-shot实验组中,VWFD的平均诊断精度高... 相似文献
4.
简述了齿轮故障诊断的原理,并通过冷轧厂开卷机齿轮故障的诊断实例,阐述了齿轮故障诊断的方法,并进一步说明了齿轮故障诊断技术在现场中的应用。 相似文献
5.
6.
7.
8.
9.
10.
11.
Zhanqiang Xing Jianfeng Qu Yi Chai Qiu Tang Yuming Zhou 《Journal of Mechanical Science and Technology》2017,31(2):545-553
The gear vibration signal is nonlinear and non-stationary, gear fault diagnosis under variable conditions has always been unsatisfactory. To solve this problem, an intelligent fault diagnosis method based on Intrinsic time-scale decomposition (ITD)-Singular value decomposition (SVD) and Support vector machine (SVM) is proposed in this paper. The ITD method is adopted to decompose the vibration signal of gearbox into several Proper rotation components (PRCs). Subsequently, the singular value decomposition is proposed to obtain the singular value vectors of the proper rotation components and improve the robustness of feature extraction under variable conditions. Finally, the Support vector machine is applied to classify the fault type of gear. According to the experimental results, the performance of ITD-SVD exceeds those of the time-frequency analysis methods with EMD and WPT combined with SVD for feature extraction, and the classifier of SVM outperforms those for K-nearest neighbors (K-NN) and Back propagation (BP). Moreover, the proposed approach can accurately diagnose and identify different fault types of gear under variable conditions. 相似文献
12.
As a dominant machine learning method, the support vector machine is known to have good generalization capability in its application of the multiclass machine–fault classification utility. In this paper, an application of the SVM in multiclass gear–fault diagnosis has been studied when the gear vibration data in frequency domain averaged over a large number of samples is used. It is established that the SVM classifier has excellent multiclass classification accuracy when the training data and testing data are at identical angular speeds. However, this method relies on the availability of both the training and testing data at that particular angular speed of the gear operation. But the training data may not always be available at all angular speeds of the gear. Hence, two novel techniques, namely the interpolation and the extrapolation methods, have been proposed; these techniques that help the SVM classifier perform multiclass gear fault diagnosis with noticeable accuracy, even in the absence of the training data at the testing angular speed. This method is based on interpolating and extrapolating the training data at angular speeds near the speeds of the test data. In this study effects of choice over different kernels and parameters of SVM on its overall classification accuracy has been studied and optimum values for these are suggested. Finally, the effect on length of training data and data density on the SVM accuracy is also presented. 相似文献
13.
14.
在Microsoft的SQ Server2000平台上,对从实验室采集的4对不同齿轮副的故障信号建立数据库,由此建立一个齿轮故障情况数据仓库,采用OLAP技术构造一个判断齿轮故障类别的决策模型,并利用该模型去分析未知故障的齿轮信号,支持齿轮箱的诊断决策。诊断结果有较高的可信度,说明OLAP技术在机械设备故障的诊断决策中有实用价值。 相似文献
15.
16.
提出了一种基于局部特征尺度分解(LCD)和核最近邻凸包(KNNCH)分类算法的齿轮故障诊断方法。该方法采用LCD对齿轮原始振动信号进行分解得到若干内禀尺度分量(ISC),然后提取包含主要信息的ISC分量的能量作为特征向量输入到KNNCH分类器,根据其输出结果来判断齿轮的工作状态。实验分析结果表明,所提出的方法能有效地提取齿轮故障特征信息,而且在小样本的情况下仍能准确地对齿轮的工作状态进行识别。同时,与支持向量机(SVM)算法的对比分析结果表明,KNNCH算法能取得与SVM算法相当或更高的正确识别率。 相似文献
17.
针对齿轮故障诊断问题,利用数理统计特征提取方法、深度学习神经网络、粒子群算法和支持向量机等技术,提出了一种基于深度学习特征提取和粒子群支持向量机状态识别相结合的智能诊断模型。该模型利用深度学习自适应提取的频谱特征与数理统计方法提取的时域特征相结合组成联合特征向量,然后利用粒子群支持向量机对联合特征向量进行故障诊断。该模型在对多级齿轮传动系统试验台的故障诊断中实现了中速轴大齿轮不同故障类型的可靠识别,获得了满意的诊断结果。应用结果也验证了基于深度学习自适应提取频谱特征的有效性。 相似文献
18.
19.
针对齿轮故障的非线性、非稳定性特点和单个分类器在故障诊断中准确率低的问题,提出了一种基于变分模态分解(VMD)和随机森林(RF)的齿轮故障识别方法。首先,采用变分模态分解将振动信号分解成有限个本征模态函数(IMFs),并与总体平均经验模态分解对比其分解效果;其次,计算各模态函数的能量熵,将能量熵作为评判齿轮状态的标准,构建特征向量;最后,将特征向量输入随机森林进行故障分类。结果表明,与支持向量机(SVM)识别方法对比,该方法具有较强的学习能力以及较高的诊断精度。 相似文献
20.
为了准确识别转子不平衡、不对中、碰摩和油膜涡动等故障,利用小波分析对转子故障信号进行4层分解,将频率由高到低的5个分支信号作为奇异值分解(Singular Value Decomposition,SVD)矩阵的行向量,经奇异值分解后得到信号的故障特征值。通过支持向量机(Support Vector Machine,SVM)在选择不同的核函数和结构参数下比较其对转子故障诊断结果的影响。结果表明在选择最优SVM模型和参数的基础上,对SVD获得的故障特征值进行诊断,得出了准确的诊断结果。 相似文献