轮胎X光0号带束层接头检测定位量化算法的研究

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。本论文根据轮胎X光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光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。

One Inspection Algorithm to the Splice of 0# Belt

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, this paper proposed one inspection algorithm 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.