Automated inspection has proven to be the most effective approach to maintaining quality in industrial-scale manufacturing. This study employed the eye-in-hand architecture in conjunction with deep learning and convolutional neural networks to automate the detection of defects in forged aluminum rims for electric vehicles. RobotStudio software was used to simulate the environment and path trajectory for a camera installed on an ABB robot arm to capture 3D images of the rims. Four types of surface defects were examined: (1) dirt spots, (2) paint stains, (3) scratches, and (4) dents. Generative adversarial network (GAN) and deep convolutional generative adversarial networks (DCGAN) were used to generate additional images to expand the depth of the training dataset. We also developed a graphical user interface and software system to mark patterns associated with defects in the images. The defect detection algorithm based on YOLO algorithms made it possible to obtain results more quickly and with higher mean average precision (mAP) than that of existing methods. Experiment results demonstrated the accuracy and efficiency of the proposed system. Our developed system has been shown to be a helpful rim defective detection system for industrial applications.

The global positioning system (GPS) is a satellite-based navigation sensor that supplies the consumer/military users with the proper equipment access to accurate positioning and timing information anywhere in the world. Interference has a significant influence on the acquisition and tracking of satellite signals from a GPS sensor. An adaptive BEACON filter based on optimal bounding ellipsoid (OBE) criterion is proposed for GPS interference mitigation applications. The OBE algorithm that provides the low computational efficiency and highly selective update mechanism is adopted to adjust the weights and thereby track swiftly the stationary and non-stationary frequency modulation (FM) waveforms. According to the GPS signal specification, a time-varying error bound mechanism is derived and incorporated into the BEACON method. The remarkable properties of the proposed BEACON canceller are their rapider convergence rate and favorable lower complexity burden. Simulation results demonstrate that its SNR improvement factor exceeds the factors of conventional NLMS, SM-NLMS, and SM-APA filters under the single-tone CWI, multi-tone CWI, pulse CWI, and FM jamming environments, respectively.