基于卷积神经网络的气体绝缘组合开关盆式绝缘子螺栓松动检测方法

Looseness detection method of gas insulated switchgear basin insulator bolts based on convolutional neural network

盆式绝缘子是气体绝缘组合开关中的关键绝缘器件,通过螺栓与两侧气室法兰进行紧固连接,当螺栓预紧力分布不均时会导致盆式绝缘子应力分布不均,严重时会引起绝缘子破裂,从而影响电力设备运行的安全性和可靠性。文章搭建了盆式绝缘子螺栓松动超声波检测系统,以获取不同螺栓不同工况下的超声信号,基于卷积神经网络对超声信号进行特征提取。实验结果表明,卷积神经网络可以自动提取盆式绝缘子螺栓松动特征量,当迭代次数为320、学习率为0.001时,10种螺栓松动工况的识别准确率达到100%。该检测方法可实现对盆式绝缘子法兰螺栓松动的检测,判断螺栓松动状态,具有一定的工程实用价值。

Basin-type insulator is the key insulation device of gas insulated switchgear(GIS).It is fastened and connected with the flanges of the gas chambers on both sides by bolts.When the bolt preload is unevenly distributed,the stress distribution of the basin insulator will be uneven,and in severe cases,the insulator will be cracked,which will affect the safety and reliability of power equipment operation.The article builds an ultrasonic detection system for the looseness of flange bolts of basin insulators to obtain ultrasonic signals of different bolts under different working conditions.The features of the ultrasonic signals are extracted based on the convolutional neural network(CNN).The experimental results show that the CNN can automatically extract the bolt loosening feature of the basin insulator.When the number of iterations is 320 and the learning rate is 0.001,the recognition accuracy of ten bolt loosening conditions reaches 100%.The detection method can realize the detection of the looseness of the flange bolts of the basin-type insulator,judge the looseness of the bolts,and has certain practical engineering value.