应用小波包神经网络的塔机起重臂损伤识别

Study on Damage Identification of Tower Crane Boom by Using Wavelet Packet and Neural Network

经长期服役后的塔式起重机,其安全状况会整体下降,若出现的损伤不能被及时监测处理,可能造成严重的事故,因此,塔机起重臂的局部损伤识别研究对于其及时检修有重要意义。文章利用塔机起重臂损伤前后的加速度响应信号,得到用于表征起重臂损伤信息的小波包能量变化率特征集,为神经网络损伤识别输入参数的选择提供依据。结果显示,采用神经网络与小波包构造的能量变化率指标相结合的损伤识别方法,可以对塔机起重臂损伤杆件发生的具体位置以及损伤的程度进行准确的识别,同时,数值仿真证明方法的有效性。

After a long-term service,the safety of tower cranes will be reduced.If these damages can not be monitored in time,it may cause serious accidents.Therefore,it is of great significance to recognize the local damage of tower cranes for its timely maintenance.the characteristic sets of wavelet packet energy rate of change,used to characterize the damage information of the tower crane boom are obtained by using the vibration response signals before and after the tower crane boom damage,which provides the basis for the selection of the input parameters of the damage identification of the neural network.The results show that the combination of neural network and wavelet packet feature identification can identify the specific location and extent of the damaged rod.At the same time,the numerical simulation proves the effectiveness of the proposed method.