Weed detection technology is of paramount significance in achieving automation and intelligence in weed control. Nevertheless, it grapples with several formidable challenges, including imprecise small target detection, high computational demands, inadequate real-time performance, and susceptibility to environmental background interference. In response to these practical issues, we introduce CCCS-YOLO, a lightweight weed detection algorithm, built upon enhancements to the Yolov5s framework. In this study, the Faster_Block is integrated into the C3 module of the YOLOv5s neck network, creating the C3_Faster module. This modification not only streamlines the network but also significantly amplifies its detection capabilities. Subsequently, the context aggregation module is enhanced in the head by improving the convolution blocks, strengthening the network’s ability to distinguish between background and targets. Furthermore, the lightweight Content-Aware ReAssembly of Feature (CARAFE) module is employed to replace the upsampling module in the neck network, enhancing the performance of small target detection and promoting the fusion of contextual information. Finally, Soft-NMS-EIoU is utilized to replace the NMS and CIoU modules in YOLOv5s, enhancing the accuracy of target detection under dense conditions. Through detection on a publicly available sugar beet weed dataset and sesame weed datasets, the improved algorithm exhibits significant improvement in detection performance compared to YOLOv5s and demonstrates certain advancements over classical networks such as YOLOv7 and YOLOv8.

The continuous development of information technology has increased the level of automation and informatization in the manufacturing industry, which makes it necessary for companies to effectively monitor their assembly lines. Aiming to visualize the monitoring challenges of the assembly line production process, taking the industrial detonator automatic assembly line as the research object and referring to the digital twin five-dimensional model, a visualization monitoring method that utilizes an assembly line based on a digital twin is proposed. First, the architecture of the assembly line visualization monitoring system based on digital twin is constructed, and its specific operation flow is studied. Then, three key implementation methods, including assembly line virtual entity model construction, data collection in the assembly process and complex equipment error detection, are studied. Finally, a visualization monitoring system for the industrial detonator automatic assembly line is designed and developed, which verifies that the proposed method is effective in the visualization monitoring of the assembly line.

Compared with the traditional needle driving method, hybrid maglev needle driving is a new weft knitting machine technology, which alleviates the problems of noise, heat, and needle breakage. However, in the structure of needle arrays, magnetic disturbance between permanent magnet knitting needles leads to unstable needle control. Therefore, this paper attempts to solve this problem through a performance analysis of hybrid maglev needle driving. Based on the structure, the magnetic force distribution model of permanent magnet knitting needles is established. Aiming at the magnetic interference between magnetic arrays, a magnetic shielding material, silicon steel with a high permeability, is proposed to optimize the driving structure of a magnetic levitation needle array. Through simulation and experimental analysis, the influence of different silicon steel thicknesses on magnetic field shielding is analyzed. It is concluded that the optimal value of a silicon steel sheet is 1 mm and that the optimal gauge of hybrid maglev knitting needles is 8 mm. Finally, compared with the theoretical and simulation analysis, the experimental results have indicated that the proposed optimized structure of the gauge of hybrid maglev knitting needles is correct and effective.

To address the issues of low visibility, poor real-time performance, and weak interaction capabilities in the operation of magnetic levitation circular knitting needles, an online monitoring method based on digital twin technology for magnetic levitation knitting needles is proposed. This method first conducts an in-depth analysis of the digital twin five-dimensional model of the magnetic levitation knitting needle to monitor the operational status of the equipment in real time. Additionally, an online monitoring system based on the Unity3D engine and a digital twin-based architecture for magnetic levitation knitting needles are designed. On this basis, the comprehensive monitoring, operation, and maintenance of the magnetic levitation knitting needles are achieved through the design of virtual models, visual interfaces, and real-time data acquisition and driving technology. Finally, this method takes a 5-inch 32-needle magnetic levitation circular knitting machine as the application research object. By analyzing the movement trajectory and real-time current feedback data of the three working positions of the magnetic levitation knitting needles, the rationality, effectiveness, and accuracy of the proposed method and model are demonstrated, achieving online monitoring of the magnetic levitation knitting needles and reflecting the full lifecycle process of the magnetic levitation knitting needles.

Textile equipment monitoring and scheduling are constrained by device heterogeneity, stringent real-time requirements, and complex dynamic resource scheduling. To address these challenges, this study proposes a cloud-edge-end collaborative remote monitoring and scheduling system for textile equipment. The proposed system aims to overcome the limitations of traditional solutions in compatibility, real-time performance, and resource utilization. This work is positioned as an applied systems study, in which the scheduling modules are used as monitoring-driven service extensions rather than as standalone algorithmic contributions. We develop (i) an adaptive multi-protocol parsing mechanism, (ii) a collaborative hierarchical alerting framework, and (iii) monitoring-driven computing-resource and production-scheduling services. The system is implemented across the terminal device layer, edge computing layer, and central cloud layer. Embedded acquisition terminals were designed to support multiple industrial protocols, including Modbus RTU, OPC UA, and EtherCAT. Dynamic protocol adaptation was used to identify, parse, and map heterogeneous protocol frames into a unified information model at runtime. In the workshop deployment reported in this study, field validation was conducted on 120 air-jet looms connected through RS485-based Modbus RTU. Other interfaces were evaluated as prototype-supported communication options rather than as quantitatively validated workshop interfaces. A cloud-edge-end collaborative alerting framework is designed by combining an improved OPTICS algorithm with a graph neural network (GNN) model. It improves the redundant-alarm filtering rate by 42.1%, achieves 96.8% root-cause diagnosis accuracy, and keeps the end-to-end alert latency at or below 200 ms at the 99th percentile. A cross-layer resource scheduling strategy incorporating a fuzzy PID controller is proposed, accompanied by a weighted multi-criteria resource-optimization model. This strategy increases the average CPU utilization of edge nodes to 84.3 ± 3.6% and reduces burst-task response latency to 236 ± 48 ms. In addition, an adaptive particle-swarm optimization module based on a scalarized composite scheduling objective reduces the equipment idle rate to 6.5% and shortens the average order completion time by 28.4%. Overall, the proposed framework demonstrates the feasibility of cloud-edge-end collaborative monitoring and scheduling in the validated RS485/Modbus-RTU-based weaving-workshop scenario, while its application to other textile processes, machine types, and communication configurations requires further protocol-specific adaptation and field validation.