In recent years, artificial intelligence (AI) has achieved significant progress and remarkable advancements across various disciplines, including biology, computer science, and industry. However, the increasing complexity of AI network structures and the vast number of associated parameters impose substantial computational and storage demands, severely limiting the practical deployment of these models on resource-constrained edge devices. Although edge intelligence methods have been proposed to alleviate the computational and storage burdens, they still face multiple persistent challenges, such as large-scale model deployment, poor interpretability, privacy and security vulnerabilities, and energy efficiency constraints. This article systematically reviews the current advancements in edge intelligence technologies, highlights key enabling techniques including model sparsity, quantization, knowledge distillation, neural architecture search, and federated learning, and explores their applications in industrial, automotive, healthcare, and consumer domains. Furthermore, this paper presents a comparative analysis of these techniques, summarizes major trade-offs, and proposes decision frameworks to guide deployment strategies under different scenarios. Finally, it discusses future research directions to address the remaining technical bottlenecks and promote the practical and sustainable development of edge intelligence. Standing at the threshold of an exciting new era, we believe edge intelligence will play an increasingly critical role in transforming industries and enabling ubiquitous intelligent services.

In modern manufacturing, making accurate and timely decisions requires the ability to effectively handle multiple types of data. This paper presents a multimodal system designed specifically for smart manufacturing applications. The system combines various data sources including images, sensor data, and production records, using advanced multimodal large language models. This approach addresses common limitations of traditional single-modal methods, such as isolated data analysis and poor integration between different data types. Key contributions include a unified method for representing different data types, dynamic semantic tokenization for better data processing, strong alignment strategies across modalities, and a practical two-stage training method involving initial large-scale pretraining and later fine-tuning for specific tasks. Additionally, a novel Transformer-based model is introduced for generating both images and text, significantly improving real-time decision-making capabilities. Experiments on relevant industrial datasets show that this method consistently performs better than current state-of-the-art approaches in tasks like image–text retrieval and visual question answering. The results demonstrate the effectiveness and versatility of the proposed methods, offering important insights and practical solutions to enhance intelligent manufacturing, predictive maintenance, and anomaly detection, thus supporting the development of more efficient and reliable industrial systems.

Industrial network systems are facing various new challenges, such as increasing functional failure factors, the accelerating penetration of information threats, and complex and diverse attack methods. Industrial networks are often vulnerable to natural or intentional disasters; therefore, it is highly invaluable to research to identify the influential nodes. Most of the state-of-the-art evaluates the importance of the nodes according to one or more network metrics. Moreover, there are no metrics reflecting all the properties of the network. In this paper, a novel method (Structure-based Identification Method, SIM) to identify the influential nodes in industrial networks is proposed based on the network structure, which goes beyond the use of network metrics. The SIM method extracts the weakly connected components, which are more likely to survive after the important nodes are attacked in the network. Evaluation results show that the SIM method obtains better results than the state-of-the-art methods to identify influential nodes in real-world industrial networks and has a good prospect to be applied in industrial application.

This paper proposes a feature-driven topology reconfiguration framework to enhance the resilience of Industrial Internet of Things (IIoT) systems against heterogeneous attacks. By dynamically partitioning IIoT into subnetworks based on localized attack features and reconstructing each subnetwork with tailored topologies, our framework significantly improves connectivity and communication efficiency. Evaluations on a real-world dataset (Tech-Routers-RF) characterizing IIoT topologies with 2113 nodes show that under diverse attack scenarios, connectivity and communication efficiency improve by more than 70% and 50%, respectively. Leveraging information entropy to quantify the trade-off between structural diversity and connection predictability, our work bridges adaptive network design with real-world attack dynamics, offering a scalable solution for securing large-scale IIoT deployments.

The device anomaly detection in an industrial control system (ICS) is essential for identifying devices with abnormal operating states or unauthorized access, aiming to protect the ICS from unauthorized access, malware, operational errors, and hardware failures. This paper addresses the issues of numerous manufacturers, complex models, and incomplete information by proposing a fingerprint extraction method based on ICS protocol communication models, applied to an anomaly detection model fine-tuned using the Llama3 model. By considering both hardware and software characteristics of ICS devices, the paper designs a fingerprint vector that can be extracted in both active and passive network communication environments. Experimental data include real ICS network traffic from an oilfield station and extensive ICS device traffic data obtained through network scanning tools. The results demonstrate that the proposed method outperforms existing methods in terms of accuracy and applicability, especially in differentiating devices from various manufacturers and models, significantly enhancing anomaly detection performance. The innovation lies in using large language models for feature extraction and the anomaly detection of device fingerprints, eliminating dependency on specific ICS scenarios and protocols while substantially improving detection accuracy and applicability.