将预处理后数据作为SVM(支持向量机)算法的输入,通过SVM算法来检测轴承故障。
Subsequently those preprocessing data are the input of SVM (support vector machine) algorithm, which is used for ball bearing fault detection.
因此,通过有限元软件ANSYS对具有各种损伤程度的结构进行模态分析,得到固有频率和模态分量的数据,经过归一化处理后作为神经网络的输入向量。
Therefore, through structural modal analysis with different damage degree using ANSYS, get natural frequencies and mode shape data as neural network input vector after unitary.
该系统的主要输入数据是心电向量图数据,但也可心接受心电图或其它临床参数和知识。
The major input data are VCG data, however, other ones, such as ECG or symptom parameters, can be also received.
自组织特征映射(SOFM)网络利用神经元权值向量表示输入数据的结构、具有较好的分类能力。
The self-organizing feature map (SOFM) uses weight of network to present structure of the input data and has preferable ability of classification.
本文分别针对数据的预处理、训练数据集大小以及输入向量的大小分别进行了研究,以确定使用BP神经网络预测的一个最佳参数组合。
Raw data preprocessing, the size of training data, as well as the size of input vectors have been studied separately, to find out the best parameter set of BP neural network prediction.
本文分别针对数据的预处理、训练数据集大小以及输入向量的大小分别进行了研究,以确定使用BP神经网络预测的一个最佳参数组合。
Raw data preprocessing, the size of training data, as well as the size of input vectors have been studied separately, to find out the best parameter set of BP neural network prediction.
应用推荐