摘要
针对织物人工视觉检测效率低下的问题,研究了基于单片机的光学检测系统,实现了织物实时高效的自动瑕疵检测。采用光透射的单点扫描方法来实现稀疏经纬线的织物的检测具有高信噪比的优点,因为在这种情况下透射光远远大于发射光。由光电传感器的输出信号可以提取织物的瑕疵信息,此信号经过放大滤波并采样至单片机,最后经单片机定量分析和评估并发出瑕疵报警。研究结果表明,基于单片机的光电检测系统有较好的实时性、鲁棒性,并具有较高的检测精度,该系统可以推广至纺织企业,具有较好的应用前景。
Aiming at solving the low efficiency problems of manual visual fabric defect inspection,a real-time fabric defect photoelectric detection system was investigated. Instead of detection of light reflection from fabric,a light transmission technique with higher signal-to- noise rate was employed in the system for evaluating the fabric defect. A photodiode was used to record the defect signal of fabric. The weak signal was amplified, filtered, and then converted to a digital signal by an analog-to-digital converter. Consequently, the digital signal was sent to a microcomputer. The signal was quantitatively evaluated and finally a defect alarm was triggered. From the experimental results,the timeliness,robustness and detection precision of the system are demonstrated,therefore,it can be recommended for the applications in fabric industries.
出处
《机电工程》
CAS
2011年第11期1324-1326,共3页
Journal of Mechanical & Electrical Engineering
基金
国家自然科学基金资助项目(51005077)
福建省杰出青年基金资助项目(2011J06020)
教育部回国留学人员启动基金资助项目(教外司留[2008]890号)
福州大学人才基金资助项目(XRC-1024)
关键词
织物瑕疵检测
光电检测
单片机
fabric defect detection
photoelectric detection
microcomputer