Bevel Gear Detection System with Multi-Camera Vision

doi:10.7652/xjtuxb201404001

您当前的位置：

首页 >

文章列表页 >

Bevel Gear Detection System with Multi-Camera Vision

更新时间：2025-04-29

- Bevel Gear Detection System with Multi-Camera Vision
- Vol. 48, Issue 4, Pages: 1-7(2014)
- 作者机构：
  
  西安交通大学电子与信息工程学院,西安,710049
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201404001
  CLC： TP391
- Online First：10 April 2014，
  
  Published：2014
- 稿件说明：
移动端阅览
Bevel Gear Detection System with Multi-Camera Vision[J]. 2014, 48(4): 1-7.
DOI：

Bevel Gear Detection System with Multi-Camera Vision[J]. 2014, 48(4): 1-7. DOI： 10.7652/xjtuxb201404001.

摘要

针对人工检测汽车伞齿轮表面缺陷与尺寸参数存在成本高、工作量大、检测速度慢且产品一致性差等问题

利用机器视觉技术进行研究

开发了一种集缺陷检测和尺寸测量于一体的伞齿轮多目视觉检测装置。通过构建的邻域均差缺陷提取、圆逼近和快速旋转定位3种高效图像处理算法

解决了伞齿轮齿面多、外形结构复杂、缺陷种类多样等复杂条件下的齿轮缺陷与尺寸检测难题。可检测缺陷包括磕碰伤、裂纹、充填不满、划痕、凹陷与凸起、麻点、花键重复拉削等

可检测最小缺陷尺寸为0.4 mm×0.4 mm

测量精度为40～50 μm

单次检测耗时小于1.3 s

检测精度与速度均满足伞齿轮高速自动化生产线的实时在线检测需求。

Abstract

It is expensive

inefficient

slow and imprecise to detect surface defects and dimension parameters of automotive bevel gear by manual observing. A synthetic bevel gear detection system and device with multi-vision technology are developed. The system is able to detect surface defects and measure gear dimension simultaneously. Three efficient image processing algorithms named Neighborhood Mean Value Difference Defect Extraction

Circle Approximation Method and Fast Rotation and Position are proposed

and knocked holes

cracks

scratches

dints

gibbosities and repeated cuttings of spline can be rapidly detected. The detection process takes no more than 1.3 seconds. The dimensions of the detectable defects are 0.4 mm×0.4 mm and the dimension measurement precision reaches 40-50 μm.

关键词

Keywords

references

SHAO Yimin, LIANG Jie, GU Fengshou, et al. Fault prognosis and diagnosis of an automotive rear axle gear using a RBF-BP neural network[J]. Journal of Physics: Conference Series, 2011, 305(1): 12063-12073.

PAREY A, TANDON N. Impact velocity modelling and signal processing of spur gear vibration for the estimation of defect size[J]. Mechanical Systems and Signal Processing, 2007, 21(1): 234-243.

SARAVANAN N, RAMACHANDRAN K I. Fault diagnosis of spur bevel gear box using discrete wavelet features and decision tree classification[J]. Expert Systems with Applications, 2009, 36(5): 9564-9573.

张勇. 汽车设计齿轮分类方案比较分析[J]. 现代商贸工业, 2009, 21(19): 292-293.

ZHANG Yong. Comparative analysis of automobile gear classification scheme[J]. Modern Business Trade Industry, 2009, 21(19): 292-293.

HAYES M. Better bevel gear production[EB/OL].(2010-01-01)[2013-09-28]. http:∥www.gear-solutions.com/article/detail/6076/better-bevel-gear-production.

CUBERO S, ALEIXOS N, MOLTO E, et al. Advances in machine vision applications for automatic inspection and quality evaluation of fruits and vegetables[J]. Food and Bioprocess Technology, 2011, 4(4): 487-504.

GOLNABI H, ASADPOUR A. Design and application of industrial machine vision systems[J]. Robotics and Computer-Integrated Manufacturing, 2007, 23(6): 630-637.

吕涛,刘志刚,邓忠文,等.一种光纤组量程扩增的激光频率扫描干涉绝对测距系统.2013,47(9):77-82.[doi:10.7652/xjtuxb201309013]

穆为磊,高建民,王昭,等.考虑人眼视觉特性的射线检测数字图像质量评价方法.2013,47(7):91-95.[doi:10.7652/xjtuxb201307017]

黄进,金炜东,秦娜,等.消除阴影和高亮噪声的双梯柱体码本前景检测模型.2013,47(4):28-34.[doi:10.7652/xjtuxb 201304006]

郝元宏,韩静,齐春.一种新的浮选泡沫图像识别方法.2011,45(4):104-108.[doi:10.7652/xjtuxb201104019]

刘京鑫,孙剑,孟德宇.基于视觉原理的分类算法.2010,44(10):116-119.[doi:10.7652/xjtuxb201010022]

张斌,梅魁志,郭青.仿生物视觉的非均匀采样方法及其硬件设计.2010,44(6):99-103.[doi:10.7652/xjtuxb201006019]

马加庆,韩崇昭.一种多线索融合的均值偏移跟踪算法.2009,43(10):42-46.[doi:10.7652/xjtuxb200910009]

张国亮,谢宗武,蒋再男,等.模糊化多视觉信息融合的视觉跟踪策略.2009,43(8):33-37.[doi:10.7652/xjtuxb200908 007]

欧阳诚苏,袁军,田军委,等.人眼视觉特性与粗糙集结合的X射线图像增强算法.2009,43(6):48-51.[doi:10.7652/xjtuxb200906011]

张国亮,王捷,刘宏.大范围视觉伺服方法在空间机器人上的应用.2009,43(1):85-89.[doi:10.7652/xjtuxb200901019]

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Optimized Design of Lightweight Detection Algorithm for Train Wheelset Tread Defects

Energy Efficiency Optimization of the Cryogenic Air Separation Process for Electronic-Grade Ultra Pure Nitrogen

A Structure-Semantics-Residual Collaborative Image Compression Framework：Towards Privacy Protection and High-Fidelity Reconstruction

Knowledge Graph Representation Learning Driven by Semantic Discrimination and Subgraph Integration

Effects of Steam Addition on the Swirl Combustion and Emission Characteristics of Cracked Ammonia

Related Author

HOU Tao

REN Yikun

NIU Hongxia

Related Institution

School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China

⁰