Integration of Deep Learning Network and Robot Arm System for Rim Defect Inspection Application.

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.

Note: automatic mass-flow configuration method for evaluating turbomolecular pump performance.

An automatic mass-flow configuration method is presented for the evaluation of turbomolecular pump performance. This configuration method is used to obtain an effective mass-flow rate. In addition, the throughput, inlet pressure, and compression ratio are evaluated. The throughput increases with the mass-flow rate. Moreover, the compression ratio increases almost linearly with the outlet pressure for mass-flow rates from 2.97 × 10(-9) to 3.96 × 10(-7) kg/s. Finally, empirical correlations are proposed for the throughput and inlet pressure.

Optical effects of shadow masks on short circuit current of organic photovoltaic devices.

In this paper, we have employed different shadow masks attached on top of organic photovoltaic (OPV) devices to study the optical effects of the former on the short circuit current (J(SC)). To rule out possible lateral electrical conduction and simplify the optical effects inside the device, a small-molecular heterojunction OPV device with a clear donor/acceptor interface was employed with a hole extraction layer exhibiting high resistance intentionally. Careful calibration with a shadow mask was employed. By attaching two layers of opaque masks in combination with a suitable holder design to shield the light from the edges and backside, the value of J(SC) approached that of the dark current, even under 1-sun radiation. With different illumination areas, we found that the photons illuminating the non-active region of the device contributed to 40% of the J(SC) by optical effect within the width of about 1 mm around the active region. When illuminating the non-active area with 12 mm to the active area, a 5.6 times improvement in the J(SC) was observed when the incident angle was 75°. With the introduction of a microstructured film onto the OPV device and an increase in the reflection from the non-active region, a 15% enhancement of the J(SC) compared to the control device was achieved.