Digital twin and data-driven technologies provide an idea for realizing complex product quality prediction. Aiming at the issues of real-time visual monitoring, operating status analysis, and quality prediction in complex die-casting intelligent manufacturing, a digital twin and data-driven quality prediction architecture is proposed. The virtual-real interaction digital twin of die-casting manufacturing cells is established. The collaborative working mode of physical cells, virtual cells, and real-time monitoring is constructed to predict product quality. The learning method of die-casting parameter data and appearance defect data is proposed to realize the real-time quality prediction in die-casting process and the appearance defect quality prediction after processing, respectively. The data preprocessing and XGBoost-based learning method is proposed for real-time quality prediction of die-casting process. A single-shot refinement neural network for aluminum casting tiny defects detection (Refine-ACTDD) based on deep learning is proposed to solve the high-precision defect detection problems of small appearance defects of complex castings and large interference of complex background. Taking the complex aluminum die-casting as an example, the applications of quality prediction are verified. The method provides a new technical approach for high-precision quality prediction of complex die-casting manufacturing.
30 November 2021 in IEEE Transactions on Instrumentation and Measurement
The complex and changeable robotic operating environment will often cause the low success rate or failure of the robot grasping. This article proposes a grasp pose detection method based on the cascaded convolutional neural network, which can be applied to grasp unknown irregular objects under unstructured environment. The grasping feature and the grasp position candidate bounding-boxes of objects are extracted by Mask-RCNN. To guarantee the generalization and improve the detection rate, grasp angle estimation network Y-Net is proposed to accurately obtain the grasp angle. To solve the problem of insufficient accuracy of grasping position, grasping feasibility evaluation network Q-Net is proposed for acquiring the grasp quality distribution. Finally, the optimal grasp posture is obtained for the robotic object grasping task in cluttered scenes. Experiments are validated in Cornell datasets, Jacquard datasets, and real environments, respectively. The experimental results show that the proposed method can quickly calculate the robot posture for irregular objects with random poses and different shapes. Compared to the previous methods, it has considerable improvement in grasp accuracy and speed. The method can be applied to object grasping scenarios in cluttered scenes and has strong stability and robustness.
23 February 2018 in The International Journal of Advanced Manufacturing Technology
Compared with traditional mechanical seals, magnetic fluid seals have unique characters of high airtightness, minimal friction torque requirements, pollution-free and long life-span, widely used in...
4 April 2019 in International Journal of Control, Automation, and Systems
The segmentation of slender structures in images faces challenges of discontinuous segmentation and insufficient recognition. These slender structures, such as arteries and veins, are particularly important in 3D medical images that are sensitive to the computational complexity of segmentation networks. Therefore, in order to balance the computational complexity of the network and adaptive perception of slender structures, this paper proposes a multi-directional attention module for slender structures, which is a lightweight attention module that can be inserted into the encoder or decoder unit. At the same time, we propose a contour loss function to address the class imbalance phenomenon that may arise in the joint segmentation task of slender and ordinary structures. This function improves the balance by converting traditional class mask labels into contour mask labels. The effectiveness of our proposed module has been validated through training on segmentation tasks on 2D and 3D images.