The cable prestressing loss and web members damage experiment of a bea m string structure was carried out. Different prestressing forces were exerted o n the cable to simulate cable prestressing loss, the prestressing forces were ca lculated by the frequencies which were solved by Fourier transform or wavelet tr ansform under impulse excitation. Test results show this method is accurate and convenient. The damage cases of web members on the beam were tested to validate the efficiency of wavelet support vector machine method. Wavelet packet decompos ition was applied to the structural response signals under ambient vibration, fe ature vectors were obtained by feature extraction method with “energydamage s t ate”. The feature vectors were used for training and classification as the inpu ts of the compact support vector machine. The structural damage position and deg ree can be identified and classified, and the test result is highly accurate esp ecially combined with principle component analysis.