基于样本重采样的电路非平衡数据预处理方法

针对机载设备电子电路故障状态测试数据少、整体测试数据不均衡的问题,提出了一种基于样本重采样的数据预处理方法。首先,采用超限学习机对原始数据集进行训练以挑选出分类准确的样本。然后,对其中的少数类和多数类分别采用合成少数类过采样技术(synthetic minority oversampling technique, SMOTE)进行过采样和局部密度欠采样处理;并将错误分类的多数类样本作为干扰因素进行删除。通过以上两种手段可以均衡数据集,并控制数据规模防止过拟合,提高对故障样本的检测率。实测数据处理结果表明,相比于其他重采样算法,所提算法整体效果优良且稳定,对电子电路故障诊断具有一定的应用价值。

Preprocessing method based on sample resampling for imbalanced data of electronic circuits

In order to solve the deficiency of fault state data and imbalance of whole test data in airborne electronic circuit, a data preprocessing method based on sample resampling is proposed. Firstly, extreme learning machine is used to training the original data set to select the correct classified samples. Secondly, the synthetic minority oversampling technique (SMOTE) is used to oversampling and local density under-sampling respectively for the minority and majority of the correct classified samples. And the misclassified majority samples are deleted as interference factors. In this way, the data set can be equalized, and the data size can be controlled to prevent over-fitting, and the detection rate of fault samples can be improved. Compared with other data resampling methods, the test data processing results show that the proposed method has a good and stable overall effect, which has a certain application value for the fault diagnosis of electronic circuit.