识别一个结构在震动状态下的变化在结构监测中是十分重要的，神经网络能用于这种目的．本文研究了使用可分析的学习样本来训练神经网络的可行性问题。神经网络从损伤状态中训练产生，然后用于诊断一个5层钢框架在一系列模拟震动测试中的损伤状态。结果表明，使用神经网络可使在线结构诊继更为可行。 Identifying changes in a structure under vibrating conditions is important in structural monitoring, and neural networks can be used for this purpose. This paper studies the feasibility of training neural networks using analyzable learning samples. The neural network is trained from the damaged state and then used to diagnose the damage status of a five-story steel frame in a series of simulated vibration tests. The results show that the use of neural networks online structure diagnosis after more feasible.