Subjects: Mechanical Engineering >> Mechanical Design submitted time 2024-04-01
Abstract： Overstaffing production in underground coal mining is not convenient for daily management, and incomplete information of coal miners hinders the rescue process of firefighters during mine accidents. To address this safety sustainability issue, a novel face recognition method based on an improved multiscale neural network is proposed in this paper. A new depthwise seperable (DS)-inception block is designed and a joint supervised loss function based on center loss theory is developed to constructe a new multiscale model. The miniers can be recognized in the harsh underground environment during the life rescue. Experimental results show that the accuracy, recall and F1-score indexes of the proposed method for the miner face recognition in the underground mining environment are 97.26%, 94.17% and 95.42%, respectively. Transfer model with joint supervised loss can effectively improve the recognition accuracy by about 0.5~1.5%. In addition, the average recognition accuracy of the proposed face recognition method achieves to 91.34% and the miss detection rate is less than 5% in the dugout tunnel of coal mine.
Subjects: Mechanical Engineering >> Mechanical Design submitted time 2024-03-31
Abstract： The bottom pivot is a vital support device in the miter gate but often subject to poor lubrication and wear failures. Calculating the hydrodynamic lubrication characteristics of the bottom pivot is a complex three-dimensional (3D) problem, and most of existing models adopt simplified assumptions to reduce the calculation difficulty. To solve this issue, this work develops a 3D model to calculate the hydrodynamic lubrication characteristics of the miter gate bottom pivot. The finite difference method is used to solve the oil film thickness and pressure distribution based on the spherical coordinates Reynolds equation. The component forces in three directions are calculated from the pressure distribution and compared with the theoretical values to generate the calculation difference. Then, the genetic algorithm (GA) is used to minimize the difference to determine the optimal initial parameters for the 3D model. The analysis results show that the calculation accuracy can be significantly improved by using the optimal initial model parameters. When our initial pressure is 5.64MPa, the results meet the engineering accuracy requirements.
Subjects: Mechanical Engineering >> Mechanical Design submitted time 2021-11-17
Abstract： The biomimetic design provides an adequate solution to achieve an excellent design. However, the prototype space for biomimetic design is relatively large, and it becomes more and more challenging to find the required biological prototypes quickly and efficiently. In order to improve the design efficiency and enrich the means of biomimetic innovation, this paper proposes a biological knowledge-enabled bidirectional encoder representation from transformers (BERT) model to assist biomimetic design, namely BioDesign. We extract the biological strategies, functions and extract dimensional information from the Asknature as the data source. The linguistic expression model-BERT was used to recommend biomimetic strategies or functions combined with the biological strategies data. Finally, we take the biomimetic erosion wear resistant design of the valve core as an example and use the proposed BioDesign model to recommend biomimetic inspired functions. According to the recommended content of the BioDesign model, we obtained the erosion wear resistance strategies and designed the biomimetic structure. The erosion wear experiment proved the feasibility and effectiveness of the proposed method.
Peer Review Status:
Awaiting Review
Subjects: Mechanical Engineering >> Mechanical Design submitted time 2018-03-14
Abstract：Precision reducer is one of the key parts of an industrial robot, which generally incorporates cycloidal planetary drive. Engagement of the cycloidal wheel and the pins causes rolling friction between the wheel and the pins as well as sliding friction between the pins and the pin housing in the traditional cycloidal transmission of the reducer. In this paper, we present a new kind of design to make the pins and the pin housing a whole structure, thereby the cost of manufacturing and assembly can be significantly reduced. And in this new structure, we only need to consider sliding friction between the cycloidal wheel and the unibody of the pins and pin housing. The difference between the new structure and the conventional structure in the meshing properties was given. In addition, we used finite element method to analyze the friction and contact stress between the cycloidal wheel and the pins in the actual working condition, and compared it with the traditional structure. The simulation results proved the feasibility of the new structure and provided a theoretical basis for further design and manufacturing of this new kind of cycloidal planetary drive structure.
Peer Review Status:Awaiting Review
Subjects: Mechanical Engineering >> Mechanical Design submitted time 2018-03-14
Abstract： The cycloid drive usually has a cycloidal wheel meshing with pins to achieve transmission. The profile of the cycloidal wheel is generally a curve derived from an epitrochoid. This paper presents two design types of cycloid drive, the cycloidal wheel profile of one is internal offset of epicycloid and the other is external offset of hypocycloid. Parametric 3-D models of the two design types are constructed in AutoCAD. Dynamics simulation is carried out using machinery system dynamics simulation technology, and the correctness of the dynamics model is verified by the motion curve. The dynamic meshing force between the cycloidal wheel and the pins of the two design types is solved, and transmission characteristics are compared. The results show that the hypocycloidal drive design produces more stable output speed, and can improve meshing force.
Peer Review Status:Awaiting Review
Hits
YES
Hits
Downloads
Comment