Aiming at the demand of rapid detection for coaxiality of crankshaft journal, a method of visual measurement of coaxiality error based on 3D point cloud is proposed. In this research, a laser scanner is utilized to obtain a 3D point cloud model of the part to be measured, and a circular method of rotary cutting is put forward to obtain equally spaced optimal slices of the journal. The center of the slice is then obtained using the Pratt circle fitting method optimized in this paper. After that, the center of the slice is used to obtain the common reference axis using the least squares method, which finally realizes the measurement of the coaxiality error. The experimental results show that the proposed method of getting the slices is more accurate, the maximum absolute error of the circle fitting method compared with the results of the coordinate measuring machine (CMM) is no more than 4.2 mu m, and the maximum absolute error of the coaxiality detection results and the results of the CMM is 5.5 mu m, which can satisfy the practical needs of fast and efficient measurement of the coaxiality error of crankshafts.
Aiming at the optimization problem of minimizing the maximum completion time in job shop scheduling, a deep reinforcement learning optimization algorithm is proposed. First, a deep reinforcement learning scheduling environment is built based on the disjunctive graph model, and three channels of state characteristics are established. The action space consists of 20 designed combination scheduling rules. The reward function is designed based on the proportional relationship between the total work of the scheduled operation and the current maximum completion time. The deep convolutional neural network is used to construct action network and target network, and the state features are used as inputs to output the Q value of each action. Then, the action is selected by using the action validity exploration and exploitation strategy. Finally, the immediate reward is calculated and the scheduling environment is updated. Experiments are carried out using benchmark instances to verify the algorithm. The results show that it can balance solution quality and computation time effectively, and the trained agent has good generalization ability to the scheduling problem in the non-zero initial state.
为适应机械设计与制造的教育数字化转型发展要求,利用了互联网技术、反求设计、五轴数控加工、虚实结合技术以及现代机械设计方法等技术手段,设计了"三位一体"数字化实验平台,开发了数字化设计模块、数字化制造模块以及数字化检测模块,研究了复杂零件数字化制造过程的先进技术方法以及可行性和有效性,基于"三位一体"实验平台,使复杂叶轮优化设计后的等熵效率提升了 0.7％,流量提高了 3.92％,并改善了加工质量和制造效率,提高了五轴数控机床的使用精度."三位一体"数字化制造实验平台的设计和研发为企事业单位和高等院校的教育数字化转型提供了理论基础和建设方案,有助于机械设计与制造行业创新复合型人才的培养.
以"独立挤出"型连续碳纤维增强PLA复合材料(continuous carbon fiber reinforced PLA composite,CCFRC/PLA)3D打印制件为研究对象,设计了柔性的连续碳纤维增强PLA复合材料丝(continuous carbon fiber reinforced composite filament/PLA,CCFRCF/PLA)送丝机构,研究了打印喷嘴直径与CCFRCF/PLA直径、表面包裹树脂膨胀特性及打印层高的关系,探讨了喷嘴端面直径对打印表面热辐射的影响规律,推导了喷嘴直径的计算公式,求解了最佳喷嘴直径和最佳端面直径.基于设计的打印喷头,采用仿真分析与实验验证的方法,探索了打印层高与制件力学性能之间的关系,结果表明CCFRC/PLA的抗拉强度与纤维层数呈正相关,并验证了层合板预测模型的有效性,获得了打印层高0.1 mm时CCFRC/PLA抗拉强度的修正系数为0.039,打印层高0.2 mm时,修正系数为0.124,为连续碳纤维增强复合材料3D打印技术的发展提供了理论基础和参考价值.
预测性维护是通过设备运行状态的实时监测预测其未来工作状况,实现故障诊断、寿命预测、设备维护与管理的重要技术,是人工智能技术在智能制造领域的最典型应用之一.但目前预测性维护相关术语和定义的混淆、系统间通信和集成接口的缺失、监测诊断方案和预测算法的差异,严重阻碍了预测性维护技术的应用落地.因此,文章从预测性维护技术应用、标准体系和标准内容三个方面分析和探讨了预测性维护标准的需求,构建了覆盖基础共性标准、关键技术标准和行业应用标准的预测性维护标准体系,分析了现行标准以及未来标准化的工作方向.能够促进数据、测评、剩余寿命预测和维修维护管理相关标准的研制,有效推动预测性维护技术发展以及设备数字化转型.
