摘要
轮胎成型过程中受设备及生产工艺等因素影响,因搭接量不同会造成0号带束层接头缺陷。根据轮胎X射线图像的纹理分布特点,以及缺陷区域的灰度分布特征,提出了轮胎X射线0号带束层接头检测定位量化算法。MATLAB的仿真分析表明,该算法能够准确对0号带束层接头缺陷进行定位,并量化接头大小,其误判率为3.4%,漏判率为2%。该算法克服了人工评定的不足,使评判过程更加科学化、客观化、规范化,缺陷检测结果满足工业要求,为后续的产品分级提供了技术及数据支持。
Because of the impact of equipments and production technology and other factors in the tire molding process,there will be joint defects in 0# belt because of the different of amount of overlap. According to the characteristics of the texture distribution of X-ray images and the gradation distribution of the defective areas,one inspection algorithm was proposed to the splice of 0# belt. MATLAB simulation analysis shows that this inspection algorithm can accurately locate the joint defects in 0 # belt and quantify the size of the joint with 3. 4% false positive rate and 2% missing rate. The inspection algorithm overcomes the shortcomings of manual assessment and makes the evaluating process more scientific,objective and standardized. The defect detection results meet the technical requirements and it provides technical data and supports for follow-up products classification.
出处
《科学技术与工程》
北大核心
2016年第25期121-125,136,共6页
Science Technology and Engineering
基金
山东省自然科学基金项目(ZR2015FQ013)
国家自然科学基金(615001278)资助