Convolutional neural networks (CNNs) have received widespread attention due to their powerful modeling capabilities and have been successfully applied in natural language processing, image recognition, and other fields. On the other hand, traditional CNN can only deal with Euclidean spatial data. In contrast, many real‐life scenarios, such as transportation networks, social networks, reference networks, and so on, exist in graph data. The creation of graph convolution operators and graph pooling is at the heart of migrating CNN to graph data analysis and processing. With the advancement of the Internet and technology, graph convolution network (GCN), as an innovative technology in artificial intelligence (AI), has received more and more attention. GCN has been widely used in different fields such as image processing, intelligent recommender system, knowledge‐based graph, and other areas due to their excellent characteristics in processing non‐European spatial data. At the same time, communication networks have also embraced AI technology in recent years, and AI serves as the brain of the future network and realizes the comprehensive intelligence of the future grid. Many complex communication network problems can be abstracted as graph‐based optimization problems and solved by GCN, thus overcoming the limitations of traditional methods. This survey briefly describes the definition of graph‐based machine learning, introduces different types of graph networks, summarizes the application of GCN in various research fields, analyzes the research status, and gives the future research direction.

The separate design of vision algorithms and motion control algorithms in existing vision servo systems limits their application in high-speed and high-precision industrial scenarios. To address this problem, a vision-motion codesign method is proposed for integrating visual servo systems with motion controllers via real-time Ethernet connections. During the engineering design phase of our proposal, we developed a control kernel architecture to clarify the system design logic. Then, we proposed a runtime module for real-time trajectory generation to facilitate the unified deployment of different planning methods in the kernel. On this basis, we implemented a self-adaptive trajectory generation synthesis method capable of dynamically adjusting the motion resources for real-time interpolation. The experimental results demonstrate that in visual servo static tracking experiments with the SCARA robot, our proposed method has a faster response time and smaller impact than other mainstream trajectory generation methods in 1 ms real-time interpolation cycles.

The development of Industry 4.0 has provided the possibility to meet frequent changes in product type and batches, a sharp decline in the delivery cycle, constraints of quality cost, and other relevant parameters of customized production mode. Intelligent manufacturing, as a core of Industry 4.0, represents a deep integration of new IT technologies, such as the industrial Internet of Things and service-oriented architecture, and manufacturing process. To realize intelligent manufacturing, this article introduces a cloud-assisted and edge-decision-making manufacturing architecture that contains a cloud and production edges. An intelligent production edge is designed to provide the traditional devices the abilities of data access and self-decision making. Besides, the proposed architecture is modeled as a multiagent system with the edge intelligence support, describing the agent-based reconfiguration mechanism from the three aspects, namely, agent interaction, agent behavior, and negotiation mechanism. The experimental results show that the reconfigurable method based on the proposed architecture can be used in the mixed-flow production scenario based on random orders, to improve the adaptability and robustness.

The fourth industrial revolution involves the advanced topics such as industrial Internet of Things (IIoT), Cyber-physical system (CPS) and smart manufacturing that address increasing demands for mass customized manufacturing. The agent-based manufacturing is a highly distributed control paradigm that can cope with these challenges well. This paper gives an overview of agent-based architectures for manufacturing systems. Besides, a cloud-assisted self-organized architecture (CASOA) is presented by comprising smart agents and cloud to communicate and negotiate through networks. Ontological representations of knowledge base are constructed to provide the information basis for decision-making of agents, which enables dynamic reconfiguration among agents in a collaborative way to achieve agility and flexibility. Furthermore, the agents’ interaction behavior is modeled to structure the agents hierarchically to reduce the complexity, because the interactions among agents in distributed system are difficult to understand and predict. The experimental results show that the presented architecture can be easily deployed to build smart manufacturing system and can improve the adaptiveness and robustness of the manufacturing system when dealing with mixed multi-product tasks.