转子在运行过程中的振动加速度信号包含了转子运行状态大量信号,瞬态过程中故障加速度信号特征的提取及其识别对于旋转机械故障诊断是十分重要的。针对在升降速运行时的故障特征数据样本有限而制约有效智能诊断的问题,探讨和提出了基于支持向量机的加速度信号故障诊断方法。实验分析结果表明:该方法可实现转子的振动加速度信号对转子在升降速运行时的多故障的识别和诊断。
The vibration acceleration signals of rotor in operation consist of plenty of information about its running condition, and extraction and identification of the acceleration features in the process of speed change are necessary for the fault diagnosis of rotating machinery. A new method of acceleration signal fault diagnosis based on support vector machine is put forward to solve the problem in the development of rotating machinery transient fault intelligent diagnosis due to needing many fault data samples. The testing results demonstrate that the approach can correctly classify and identify faults when the rotor is at tran- sient speed.