
基本信息:
- 专利标题: 一种基于神经网络的桥梁螺栓脱落自动识别方法
- 专利标题(英):Automatic bridge bolt come-off identification method based on neural network
- 申请号:CN201610229918.2 申请日:2016-04-14
- 公开(公告)号:CN105930774A 公开(公告)日:2016-09-07
- 发明人: 刘有桥 , 赵大成 , 戴新军 , 简珍珍 , 陈斌 , 王翔 , 金昌根 , 吴来义 , 岳青
- 申请人: 中铁大桥勘测设计院集团有限公司 , 中铁大桥(南京)桥隧诊治有限公司
- 申请人地址: 湖北省武汉市武汉经济技术开发区(沌口)博学路8号
- 专利权人: 中铁大桥勘测设计院集团有限公司,中铁大桥(南京)桥隧诊治有限公司
- 当前专利权人: 中铁大桥勘测设计院集团有限公司,中铁大桥(南京)桥隧诊治有限公司
- 当前专利权人地址: 湖北省武汉市武汉经济技术开发区(沌口)博学路8号
- 代理机构: 北京捷诚信通专利事务所
- 代理人: 王卫东
- 主分类号: G06K9/00
- IPC分类号: G06K9/00 ; G06N3/08 ; H04N7/18
The invention discloses an automatic bridge bolt come-off identification method based on the neural network, and relates to the bridge monitoring field. The method comprises the steps that S1) a bridge is provided with cameras, and the cameras are connected with a server of a monitoring center; S2) the bridge is divided into multiple monitoring areas; S3) the cameras collect images, in which bolts are complete and come off, in the monitoring areas, and transmit the images to the server; S4) a neural network model is established, and the images collected in the S3) are used to train the neural network; S5) the cameras collect images each area and transmit the images to the server; and S6) the neural network identifies images of the step S5) to determine whether a bolt comes off. The method of the invention can be used to monitor bridge bolts accurately and conveniently.
IPC结构图谱:
G | 物理 |
--G06 | 计算;推算;计数 |
----G06K | 数据识别;数据表示;记录载体;记录载体的处理 |
------G06K9/00 | 用于阅读或识别印刷或书写字符或者用于识别图形,例如,指纹的方法或装置 |