基于3D视觉的车载雷达PCB焊点缺陷检测系统研究

本研究采用将焊点三维特征提取与人工神经网络模型两种检测方法相结合的方式进行车载雷达焊点缺陷检测,克服了基于三维特征提取检测方法准确率低、基于人工神经网络检测方法对样本质量和数量要求高的缺点,具有在样本数量较少的情况下达到较高的检测准确率以及随着样本数量的积累增加检测准确率不断提升的优点。

Research on Vehicle Radar PCB Solder Joints Defect Detection System Based on 3D Vision

In this study,the solder joints defect detection of vehicle radar is carried out by combining the three-dimensional feature extraction and artificial neural network model.It overcomes the shortcomings of low accuracy of detection method based on three-dimensional feature extraction and high requirements for sample quality and quantity based on artificial neural network.It has the advantages of achieving high detection accuracy when the number of samples is small and increasing with the accumulation of the number of samples.