|
|||||
|
|
| 小波包和神经网络在输电铁塔损伤检测中的应用 | |
| 引用本文： | 刘春城,苏玉成,毛绪坤,倪阳. 小波包和神经网络在输电铁塔损伤检测中的应用[J]. 水电能源科学, 2012, 30(11): 170-173,90 |
| 作者姓名： | 刘春城 苏玉成 毛绪坤 倪阳 |
| 作者单位： | 东北电力大学 建筑工程学院， 吉林 吉林 132012； 大连理工大学 海岸与近海工程国家重点实验室， 辽宁 大连 116024;东北电力大学 建筑工程学院， 吉林 吉林 132012;东北电力大学 建筑工程学院， 吉林 吉林 132012;东北电力大学 建筑工程学院， 吉林 吉林 132012 |
| 基金项目： | 国家自然科学基金资助项目（50978049，50278091） |
| 摘 要： | 鉴于输电铁塔在整个电网中的重要性,基于小波包和RBF神经网络的基本理论，以晋东南—南阳—荆门输电线路工程中的500 kV角钢转角塔为例，模拟了输电铁塔主材单个单元和两个单元的损伤，以小波包能量曲率差作为损伤指标，利用RBF神经网络的自学习、自适应能力对输电铁塔的损伤程度进行了识别。结果表明，以小波包能量曲率差作为损伤指标可行，RBF神经网络能较好地识别损伤程度，且精度较高。 |
| 关 键 词： | 小波包； RBF神经网络； 输电铁塔； 损伤识别 |
Application of Wavelet Packet and Neural Network in Damage Identification of Power Transmission Tower |
|
| LIU Chuncheng,SU Yucheng,MAO Xukun and NI Yang. Application of Wavelet Packet and Neural Network in Damage Identification of Power Transmission Tower[J]. International Journal Hydroelectric Energy, 2012, 30(11): 170-173,90 | |
| Authors: | LIU Chuncheng SU Yucheng MAO Xukun NI Yang |
| Affiliation: | School of Civil Engineering, Northeast Dianli University, Jilin 132012, China; State Key Laboratory of Coastal and Offshore Engineering, Dalian University of Technology, Dalian 116024, China;School of Civil Engineering, Northeast Dianli University, Jilin 132012, China;School of Civil Engineering, Northeast Dianli University, Jilin 132012, China;School of Civil Engineering, Northeast Dianli University, Jilin 132012, China |
| Abstract: | Transmission tower plays an important role in whole power grid. Based on the wavelet packet and RBF neural network method, the 500 kV angle steel tower of Southeastern of Shanxi-Nanyang-Jingmen transmission lines is taken for an example for the damage simulation of one and two elements about its main steel structures. The degree of damage identification of main steel structures is studied by selecting wavelet packet energy curvature difference as damage index and utilizing self-learning and self-adaptive ability of RBF neural network. The results show that selecting wavelet packet energy curvature difference as damage index is feasible, and RBF network can identify the degree of damage with high precision. |
| Keywords: | wavelet packet RBF neural network power transmission tower damage identification |