基于图像处理的改进电缆角度识别算法
段传辉，田大庆*，宋洪睿，程冬
（四川大学 机械工程学院，四川 成都 610065）
摘要：成缆机是一种专门制造电缆的专用设备，并线工艺是保证成缆品质的关键工序。但现有并线工序均为人工目视纠偏线缆，纠偏精度难以精确保证，存在严重安全隐患与产品质量问题，生产效率低。为提高成缆机并线工艺中线芯偏转角度识别与纠正的智能化，提出了改进的电缆角度识别算法。其中，根据线芯截面形状特性，在线芯0到90°的偏转范围内，分三个阶段推导了线芯轮廓俯视宽度和当前偏转角度的计算公式；结合图像处理技术，经过图像灰度化、对比度处理、形态学操作等图像预处理过程，提取出线芯俯视图中外轮廓线特征。依据线芯在并线工艺中沿轴线运动的运动特点，使用两条线芯轴线方向的直线拟合其两边的轮廓，从而获取线芯轮廓宽度数据，可以代入公式进行偏转角的解算；同时，为了解决线芯偏转方向识别的问题，提出了两种方案，其一是利用线芯表面反光特性结合图像处理技术识别偏转方向，其二则在线芯支架两端追加了两个力传感器用以采集受力数据进行比对得出偏转方向，经实验比较，力传感器判断的方案具有更高的可靠性。
关键词：成缆机并线工艺；偏转角度；图像处理；力传感器
中图分类号：TH16 文献标志码：A doi：10.3969/j.issn.1006-0316.2022.11.005
文章编号：1006-0316 (2022) 11-0036-07
Improved Recognition Algorithm for the Cable Angle Based on Image Processing
DUAN Chuanhui，TIAN Daqing，SONG Hongrui，CHENG Dong
( School of Mechanical Engineering, Sichuan University, Chengdu 610065, China )
Abstract：Cable forming machine is a special equipment for manufacturing cable, The parallel process is the key process to ensure the quality of cable forming. However, the existing parallel processes are rectification with manual visual inspection. Therefore it is difficult to guarantee the rectification accuracy, which causes serious security risks, product quality problems, and low production efficiency. An improved recognition algorithm for cable angle is proposed to improve the intelligence of cable core deflection angle recognition and correction in the parallel process. According to the section shape characteristics of the cable core, the calculation formulas of the cable core width from top view and the current deflection Angle are derived in three stages in the deflection range from 0° to 90°. Combined with image processing technology, after image graying, contrast processing, morphological operation and other image pretreatment process, contour features from top view of cable core are extracted. According to the motion characteristics of the cable core moving along the axis in the parallel process, two lines along the axis of the cable core are used to fit the contour, so as to obtain contour width data of cable core which can be substituted into the formula to solve the deflection angle, At the same time, in order to recognize cable core deflection direction, two solutions are proposed. One is to identify the deflection direction by using the reflective characteristics of the cable core surface with image processing technology. The other is to collect force data for comparison to obtain deflection direction by adding two force sensors at both ends of the on-line core bracket. Experimental comparison shows that the scheme judged by force sensor has higher reliability.
Key words：cable；parallel process of cable forming machine；deflection angle；picture processing；force sensor
———————————————
收稿日期：2022-01-04
基金项目：四川省科技厅重点研发项目：智能监控技术在大型成缆机并线关键工艺中的应用开发（2020YFG0118）；泸州市科技厅（川大－泸州）合作项目（2019）：大型成缆机并线关键工艺智能监控技术研究（2019CDLZ-08）
作者简介：段传辉（1998－），男，湖南张家界人，硕士研究生，主要研究方向为数字化设计与制造，E-mail：993218231@qq.com。*通讯作者：田大庆（1971－），男，四川南充人，工学博士，副教授，主要研究方向为数控技术、设备故障诊断、缺陷安全评价，E-mail：dqtian@163.com。
- 上一篇：智能仓储设计与信息化应用
- 下一篇：面向高自由度的发动机虚拟维修考核方法设计
设为首页 | 加入收藏 | 免责条款
《机械》杂志版权所有 Copyright©2008-2012 Jixiezazhi.com All Rights Reserved
电话：028-85925070 传真：028-85925073 E-mail：jixie@vip.163.com
地址：四川省成都锦江工业开发区墨香路48号 邮编：610063
Powered by PageAdmin CMS