A new monitoring and diagnostics method using support vector data description (SVDD) is proposed which only needs samples under healthy condition. The method is an ideal candidate for coping with the problem of a shortage of the unhealthy condition samples. We firstly select several nodes of the monitored structure, and decompose the signals from these nodes with wavelet packet transform (WPT). To monitoring structural health efficiently, we assemble a combine feature by using wavelet packet energy distributions of these nodes. The feature is then applied as the input of a developed SVDD classifier. Experiment shows that the SVDD classifier was able to distinguish the normal and abnormal condition ideally, and can be used as an automation approach for structural health monitoring.