欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对自动机故障诊断中仅单方面从时域、频域和时频域提取特征向量，导致特征指标具有很大片面性的问题，本文提出了一种基于时频特性和PCA—RBF的自动机故障诊断方法。首先利用统计分析和总体经验模态分解（EEMD）方法，构造高维混合域初始特征向量；然后通过主成分分析法（PCA）对高维初始特征向量进行降维和简化；最后将经过PCA处理过的主特征向量输入到径向基函数（Radial Basis Function，RBF）神经网络中实现故障类型的识别。实验结果表明，混合域初始特征向量能够准确全面地描述故障特征，经过PCA处理的主特征向量大大简化了分类器结构，RBF神经网络结构简单、收敛速度快、具有很高的分类准确率。
英文摘要：
Aiming at the problem that automatic machine fault diagnosis only extracts feature vector unilaterally from the time domain, frequency domain and time-frequency domain, resulting in characteristic index has great one-sidedness, this paper proposes a method based on frequency characteristics and PCA-RBF. Firstly, statistical analysis and ensemble empirical mode decomposition （EEMD） method are used to construct high-dimensional mixed-domain initial feature vector; and then through the principal component analysis （PCA） , dimensionality reduction and feature extraction ,the high dimensional variables changes into less dimensional independent eigenvector; Finally, the principal component vectors using PCA to Radial Basis function （RBF） neural network, realizes the fault recognition. Experimental results show that the mixed domain initial feature vector can accurately describe the fault characteristics, and the main feature vector extracted by PCA can discard the redundant information and simplify the classifier, and the RBF neural network diagnosis can improve the classification accuracy.
同期刊论文项目
同项目期刊论文
期刊信息
位置：