structural damage detection under short time load using cascade-forward network

Damage identification in structures is one of the most important problems in structural engineering because early damage detection prevents a catastrophic event in structures. in this paper, a new damage identification method proposed based on a short time load excitement and dynamic time history response of structures as a damage index. to solve the equation of motion of structure, the state space method was used. to identify damage in different structures, cascade-forward network has been used. in the training process of machine, the time history of dynamic responses used as input and damage states as output. the novelty of present method is the application of time history responses of structure under short time loading excitation to train cascade-forward network. to show the efficiency of presented method, three examples consist of a frame, bending plate and beam structures has been investigated. the obtained results reveal that proposed method is viable in detecting damage in different structures.