In order to solve the problem of scarcity of negative samples in the study of visual anomaly detection algorithms for high-speed trains, this paper proposes a controllable abnormal image sample generation framework based on the fusion of diffusion model and Lora weight fine-tuning, and systematically verifies its effectiveness. First, the controllable image generation and image conversion model based on the diffusion model is introduced, and the principle of its image generation and the steps of generating abnormal image samples of functional components of high-speed trains are described. Then, the core principle of Lora's weight fine-tuning method and the implementation steps of LoRA fine-tuning are introduced. Finally, the experimental results of generating abnormal image samples of high-speed train components by combining the diffusion model local redrawing with the LoRA weight finetuning method are introduced, which proves the effectiveness of this method.

Rapid detection and precise segmentation of the weld seam region of interest (ROI) remain a core challenge in robotic intelligent grinding. To address this issue, this paper proposes a method for weld seam ROI detection and segmentation based on the fusion of active and passive vision. The proposed approach primarily consists of two stages: weld seam image instance segmentation and weld seam ROI point cloud segmentation. In the image segmentation stage, an enhanced segmentation network is constructed by integrating a convolutional attention module into YOLOv8n-seg, which effectively improves the localization accuracy and mask extraction quality of the weld seam region. In the point cloud segmentation stage, the 3D point cloud is first mapped onto a 2D pixel plane to achieve spatial alignment. Subsequently, a coarse screening of the projected point cloud is performed based on the bounding boxes output from the instance segmentation, eliminating a large amount of redundant data. Furthermore, a grayscale matrix is constructed based on the segmentation masks, enabling precise extraction of the weld seam ROI point cloud through point-wise discrimination. Experimental results demonstrate that the proposed method achieves high-quality segmentation of the weld seam region, providing a reliable foundation for robotic automated grinding.

介绍了一种通用的利用三维CAD模型进行三坐标检测程序离线编制的系统开发方法,该系统基于三维CAD建模平台,集成了测头与坐标系管理模块、测量规划模块以及编程与仿真模块等功能,实现了工件在虚拟端的采样规划、路径规划、测量程序生成以及测量过程的虚拟验证,有效提升了测量程序编制的效率和质量,有助于实现批量零件的自动化测量.

转向架是高速动车组最为重要的部件之一,而构架是转向架的骨架,是衡量高速动车组研制水平和制造能力的关键指标.转向架构架焊接成型制造包括组装、焊接、打磨、检测等工艺,并分布在不同的作业区域.运用仿真推演与重构、哑终端智能改造、M2M交互集成、"推-拉"智能物流、健康监测、云边协同等智能制造技术和模式,实现了构架组"焊-磨-检"工艺一体化柔性成线,并得到了应用验证,可以在工程机械、船舶等行业应用推广.

目前自动化仓储系统正朝着高可靠性、安全性、保密性、友好的人机界面、网络化和远程控制方向发展.为了提升自动化仓储系统信息化、网络化、智能化水平,本文对自动化仓储的智能调度管理系统进行了研究与设计,制定了软件系统架构和通信网络.通过对入库/出库/移库业务流程的规划、库存的管理、WMS、WCS等软件系统的设计,实现了自动化仓储系统信息化、网络化、智能化管控,为企业仓储系统规划和设计提供了理论支持.

U-shaped assembly lines are widely used to implement just-in-time manufacturing. U-shaped assembly line balancing problem is important to improve productivity. Most of the studies ignore uncertainty such as operation times. This study applies robust optimisation method to deal with type-II U-shaped assembly line balancing problem (UALBP-2) under uncertainty. A mathematical programming model is proposed with interval task operation times, and a genetic algorithm is developed to deal with it. A robust solution is defined as the most frequent solution falling within a pre-specified percentage of the optimal solution for different sets of scenarios. The experimental results are compared with the expected solution to verify the feasibility and effectiveness of the robust method.

薄壁铝合金型材对接焊缝结构复杂,并受检测空间限制,尚无可行的焊缝焊接质量检测方法.为此提出一种超声爬波检测工艺进行检测试验.通过设计型材结构试块、模拟焊缝余高试块和人工模拟缺陷试块等,研究型材结构与焊缝余高等对爬波检测的影响,并测试该爬波检测工艺对各种缺陷的检测能力.并与超声相控阵技术进行对比试验,分析两种技术对该种焊缝检测的适应性.试验结果表明:对于余高磨平的焊缝,爬波与相控阵的检测能力基本相当,能够检测裂纹、未焊透和未熔合等焊接缺陷,具有快速检测的优势;对于余高未磨平的薄壁焊缝,爬波检测发现缺陷的能力优于相控阵技术.试验结果可为实际工程检测提供参考和指导.

The problems of flexitable job-shops were analyzed.A novel model for task distribution with buffer constraint was proposed.On the principle of user equilibrium proposed by Wardrop, the model was solved by incremental assignment method to obtain the task distributions of all manufacture cells and process routes and to settle the minimum makespan of tasks.A practical example with nonlinear process rate and multi-process-routes was afforded, and the validity of the model and the algorithm also has been proved.Using the model and the algorithm provided, the process time-windows of all cells can be acquired, and there is a better instructional significance for flexible job-shops scheduling.

Process planning is a task that determines the detailed manufacturing steps for transforming a raw material into a completed part, by utilizing the available machining resources. It involves multiple decision-making activities, such as operation-type selection, operation-method (machine, tool, and tool approach direction) selection, and operations sequencing. This study aims to developing an approach for process planning based on polychromatic sets and fuzzy sets. A complete flow and model is established for processing method seeking, processing route generation, and optimal route selection. The verification, grounding on a true model, is performed for the proposed model to prove the well practicability of this method.