Abstract: The growing waste crisis in the world at large requires automated sorting to improve on recycling efficiency and advance the application of the circular economy. In the paper, the developed intelligent waste-sorting robot combines the deep learning-based on YOLOv8 with robot manipulation systems to classify waste and sort it automatically. The given system is implemented with the usage of an RGB-D camera to obtain images, noise reduction and normalization preprocessing algorithms, and a YOLOv8 neural network to detect multiple classes of objects in 9 categories of waste. A 6-DOF collaborative robotic arm with adaptive gripper performs physical sorting tasks computed on the basis of the 3D coordinates and motion planning algorithms. Using an experimental dataset of 8,500 annotated images, the 94.3% mAP at 0.5 detect rate, 92.5% precision, 91.1% recall, and 8.7 ms inference time are achieved, which makes it possible to process images at 115 frames per second in real-time. Robotic manipulation module has 92.3 percent grasping success and the system throughput is 445 objects/hour that is impressive when compared to manual sorting techniques. The findings confirm the feasibility of the system in practice in two areas: municipal recycling centers and industrial waste management and also in niche applications such as e-waste processing. Read More

Abstract: To meet the requirements for rapid construction and commissioning verification of multi-process machining production lines for valve components, this study investigates the digital modeling and virtual commissioning of a ball valve body machining production line. Considering the complex structure of the ball valve body, the strong correlation among the three internal-hole machining processes, and the difficulty of verifying coordinated equipment operation at the production-line level, an integrated modeling procedure combining process analysis, computer numerical control (CNC) machining simulation, and production-line virtual commissioning is established. First, according to the structural characteristics and technical requirements of the ball valve body, the machining features of the large-end hole, octagonal-end hole, and side hole are analyzed, and the corresponding machining process and CNC programs are developed. Second, a virtual machining environment consisting of a CNC lathe, blank, cutting tools, and machining programs is constructed in Vericut to simulate and verify the three internal-hole machining processes, thereby evaluating the feasibility of the machining programs and the safety of the machining process. Finally, three-dimensional models of machine tools, industrial robots, conveying devices, and auxiliary mechanisms are developed in SolidWorks and imported into the Visual Engineering and Education (VE2) platform to complete the layout modeling, equipment logic configuration, and robotic operation process simulation of the machining production line. The results show that the proposed modeling and virtual commissioning procedure can realize visual verification of both the ball valve body machining process and production-line operation process, providing a reference for process scheme optimization, equipment coordination configuration, and on-site commissioning risk control of valve machining production lines. Read More

Abstract: Fretting fatigue is a special fatigue failure mode induced by the coupling of micro-amplitude relative slip and multi-axial cyclic loads on contact pairs of mechanical structures. Its crack initiation is characterized by concealment, randomness and severe damage, serving as a core trigger for the failure of key structures in aerospace, rail transit, energy equipment and other fields. Traditional uniaxial fretting fatigue life prediction models fail to account for the coupling effect of multi-axial stress and strain as well as the synergistic damage mechanism of fretting wear and contact slip, suffering from low prediction accuracy and limited applicable scenarios. Based on the critical plane fatigue theory and combined with the damage characteristics of fretting contact, this paper introduces three correction parameters, namely relative slip amplitude, contact stress gradient and surface wear damage, to establish a multi-axial fretting fatigue crack initiation life prediction model. The model is verified via finite element simulation and classical fretting fatigue test data. The results show that the modified model can effectively characterize the evolution law of composite damage in fretting contact zones under multi-axial loads. Compared with the traditional FS critical plane model and Ruiz damage model, the life prediction error is controlled within 15%, which greatly improves the prediction accuracy of fretting fatigue crack initiation life under complex working conditions. The proposed model can provide theoretical support for fatigue life evaluation and structural optimization design of precision mechanical contact structures. Read More