The hard turning process has been widely used in the field of hard material precision machining because of its high efficiency, low processing residual stress, and low environmental pollution. Due to its undesirably processing quality, it is still not a substitute for traditional grinding, so many studies have reported that the process has been optimized. However, there has been little research on the geometry optimization of hard cutting tools, which have a great influence on the traditional machining process. In this paper, two tools with different rake face shapes are designed. The finite element analysis method is used to compare their performance with a conventional plane tool while turning hardened steel. The results show that the cutting performance of the designed tool T1 and T2 (chip morphology, cutting force, and cutting temperature) and the quality of the machined surface are improved compared with the tool. The cutting force decreased by 12.72% and 14.74%, the cutting temperature decreased by 7.56% and 9.01%, respectively, and the surface residual stress decreased by 26.56% and 28.66%.
Addressing the challenge of acquiring depth information in aero-engine assembly scenes using monocular vision, which complicates mixed reality (MR) virtual and real occlusion processing, we propose an ORB-SLAM3-based monocular vision assembly scene virtual and real occlusion processing method. The method proposes optimizing ORB-SLAM3 for matching and depth point reconstruction using the MNSTF algorithm. MNSTF can solve the problems of feature point extraction and matching in weakly textured and texture-less scenes by expressing the structure and texture information of the local images. It is then proposed to densify the sparse depth map using the double-three interpolation method, and the complete depth map of the real scene is created by combining the 3D model depth information in the process model. Finally, by comparing the depth values of each pixel point in the real and virtual scene depth maps, the virtual occlusion relationship of the assembly scene is correctly displayed. Experimental validation was performed with an aero-engine piping connector assembly scenario and by comparing it with Holynski’s and Kinect’s methods. The results showed that in terms of virtual and real occlusion accuracy, the average improvement was 2.2 and 3.4 pixel points, respectively. In terms of real-time performance, the real-time frame rate of this paper’s method can reach 42.4 FPS, an improvement of 77.4% and 87.6%, respectively. This shows that the method in this paper has good performance in terms of the accuracy and timeliness of virtual and real occlusion. This study further demonstrates that the proposed method can effectively address the challenges of virtual and real occlusion processing in monocular vision within the context of mixed reality-assisted assembly processes.
8 May 2024 in The International Journal of Advanced Manufacturing Technology
In the assembly process of the anti-loosening steel wire of the aero-engine variable stator vane (VSV) adjusting rod, it is still necessary to manually detect the correctness of the assembly, which is inefficient and error-prone. To replace manual detection, an intelligent detection method based on a multi-model cascade is proposed. The method contains two parts: a detection module and a classification module. Firstly, on the detection module, we propose to improve YOLOv5s by mixing depth-separable convolution with different-size convolutional kernels and lightweight decoupling head, and the improved YOLOv5s achieves an average accuracy of 97.9% on the test set, which improves by 3.4% and 1.5% compared to YOLOv5s and YOLOv8s, respectively. Secondly, the ConvNeXt classification head is improved by using 7*7 deep convolution instead of global average pooling on the classification module, and the performance is improved to reach 97.5% and 95.4% accuracy on the two datasets, respectively. Finally, the detection method is utilized to validate the image dataset collected by the on-site assembly workshop, and the results show that the average accuracy of this paper's method reaches 92.7%, which further validates the reliability of this paper's intelligent assembly detection method.
Ship painting personnel usually employ physical, hands-on training to enhance their proficiency and improve the quality of their painting. However, this method poses environmental pollution problems and has high costs. Therefore, this paper develops a ship artificial spraying simulation training system based on a Virtual Reality (VR) environment. Firstly, a artificial spraying model for a ship for personnel training is established by the relationship between the gun parameters, gun position, spraying direction, and coating thickness. A method for calculating the coating thickness and coating loss by using a frame cycle in a VR environment is proposed. And the artificial spraying model is verified from these two perspectives by a spraying test. Finally, based on the artificial spraying model, a ship spraying simulation training system is developed by combining C# and Unity3D, and a corresponding scoring mechanism is established to evaluate the spraying results. By recruiting personnel with different spraying experiences to wear VR helmets for spraying training trials, the results show that the method of using VR for spraying training can effectively improve the spraying level of operators with different spraying experiences.