论文部分内容阅读
鉴于支持向量机的优越性及提升机的故障特点,提出将支持向量机应用到提升机的故障智能诊断中。该方法专门针对小样本集合设计,能够在小样本情况下获得较大的推广能力,而且模型简单。首先对采集的故障信号采取信息融合方式进行特征提取,以获得特征向量。在此基础上通过多类分类支持向量机对提升机故障进行分类,建立故障诊断模型。试验结果表明,该方法具有较高的诊断精度,取得了比较令人满意的结果。
In view of the superiority of support vector machines and the characteristics of the failure of hoisting machines, the application of support vector machines to the intelligent fault diagnosis of hoisting machines is proposed. The method is designed for small sample set design, which can get more popularization ability in the case of small sample, and the model is simple. First of all, the fault signals collected by information fusion method for feature extraction, to obtain the eigenvector. On this basis, the classification of the hoisting machine faults is classified by the multi-class classification SVM, and the fault diagnosis model is established. The experimental results show that the method has high diagnostic accuracy and has achieved satisfactory results.