The Damage Identification of Power Transmission Tower Using BP-AdaBoost Model

Dongmei Tan, Suzhen Luo, Shanming Mao, Kaili Wang

Abstract


The damage identification method of transmission tower based on lift wavelet packet transform and BP-AdaBoost model is developed according to damage feature of bolt looseness of flange connection. Firstly, the vibration signal of structure is decomposed based on lift wavelet packet (WP) transform, then the corresponding damage characteristic vector is established by the lift WP component energy, which will be acted as the sample of BP-AdaBoost model. Finally, the BP-AdaBoost (Back Propagation neural network, the Adaptive Boosting) model is used to identify damage. For comparison, the damage identification methods based on fuzzy clustering and BP network are also studied. In order to verify the proposed method, the experimental research on a simple three-story transmission tower model shows that the proposed method can be effectively used to identify structural damage.


DOI
10.12783/dtetr/icaenm2017/7785

Full Text:

PDF

Refbacks

  • There are currently no refbacks.