IEEE/CAA Journal of Automatica Sinica

In Memory of Wolter J. Fabrycky: A Pioneer of Systems Engineering and US-Sino Academic Exchange

Fei-Yue Wang

2025, 12(5): 839-840. doi: 10.1109/JAS.2025.125468

Abstract(63) HTML (15) PDF(18)

Abstract:

DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models

Luolin Xiong, Haofen Wang, Xi Chen, Lu Sheng, Yun Xiong, Jingping Liu, Yanghua Xiao, Huajun Chen, Qing-Long Han, Yang Tang

2025, 12(5): 841-858. doi: 10.1109/JAS.2025.125495

Abstract(102) HTML (53) PDF(51)

Abstract:
DeepSeek, a Chinese artificial intelligence (AI) startup, has released their V3 and R1 series models, which attracted global attention due to their low cost, high performance, and open-source advantages. This paper begins by reviewing the evolution of large AI models focusing on paradigm shifts, the mainstream large language model (LLM) paradigm, and the DeepSeek paradigm. Subsequently, the paper highlights novel algorithms introduced by DeepSeek, including multi-head latent attention (MLA), mixture-of-experts (MoE), multi-token prediction (MTP), and group relative policy optimization (GRPO). The paper then explores DeepSeek’s engineering breakthroughs in LLM scaling, training, inference, and system-level optimization architecture. Moreover, the impact of DeepSeek models on the competitive AI landscape is analyzed, comparing them to mainstream LLMs across various fields. Finally, the paper reflects on the insights gained from DeepSeek’s innovations and discusses future trends in the technical and engineering development of large AI models, particularly in data, training, and reasoning.

A Survey of Distributed Algorithms for Aggregative Games

Huaqing Li, Jun Li, Liang Ran, Lifeng Zheng, Tingwen Huang

2025, 12(5): 859-871. doi: 10.1109/JAS.2024.124998

Abstract(210) HTML (15) PDF(34)

Abstract:
Game theory-based models and design tools have gained substantial prominence for controlling and optimizing behavior within distributed engineering systems due to the inherent distribution of decisions among individuals. In non-cooperative settings, aggregative games serve as a mathematical framework model for the interdependent optimal decision-making problem among a group of non-cooperative players. In such scenarios, each player’s decision is influenced by an aggregation of all players’ decisions. Nash equilibrium (NE) seeking in aggregative games has emerged as a vibrant topic driven by applications that harness the aggregation property. This paper presents a comprehensive overview of the current research on aggregative games with a focus on communication topology. A systematic classification is conducted on distributed algorithm research based on communication topologies such as undirected networks, directed networks, and time-varying networks. Furthermore, it sorts out the challenges and compares the algorithms’ convergence performance. It also delves into real-world applications of distributed optimization techniques grounded in aggregative games. Finally, it proposes several challenges that can guide future research directions.

Exploring DeepSeek: A Survey on Advances, Applications, Challenges and Future Directions

Zehang Deng, Wanlun Ma, Qing-Long Han, Wei Zhou, Xiaogang Zhu, Sheng Wen, Yang Xiang

2025, 12(5): 872-893. doi: 10.1109/JAS.2025.125498

Abstract(150) HTML (32) PDF(42)

Abstract:
The rapid advancement of large models has led to the development of increasingly sophisticated models capable of generating diverse, personalized, and high-quality content. Among these, DeepSeek has emerged as a pivotal open-source initiative, demonstrating high performance at significantly lower computation costs compared to closed-source counterparts. This survey provides a comprehensive overview of the DeepSeek family of models, including DeepSeek-V3 and DeepSeek-R1, covering their core innovations in architecture, system pipeline, algorithm, and infrastructure. We explore their practical applications across various domains, such as healthcare, finance, and education, highlighting their impact on both industry and society. Furthermore, we examine potential security, privacy, and ethical concerns arising from the widespread deployment of these models, emphasizing the need for responsible AI development. Finally, we outline future research directions to enhance the performance, safety, and scalability of DeepSeek models, aiming to foster further advancements in the open-source large model community.

Release Power of Mechanism and Data Fusion: A Hierarchical Strategy for Enhanced MIQ-Related Modeling and Fault Detection in BFIP

Siwei Lou, Chunjie Yang, Zhe Liu, Shaoqi Wang, Hanwen Zhang, Ping Wu

2025, 12(5): 894-912. doi: 10.1109/JAS.2024.124821

Abstract(205) HTML (15) PDF(60)

Abstract:
Data-driven techniques are reshaping blast furnace iron-making process (BFIP) modeling, but their “black-box” nature often obscures interpretability and accuracy. To overcome these limitations, our mechanism and data co-driven strategy (MDCDS) enhances model transparency and molten iron quality (MIQ) prediction. By zoning the furnace and applying mechanism-based features for material and thermal trends, coupled with a novel stationary broad feature learning system (StaBFLS), interference caused by nonstationary process characteristics are mitigated and the intrinsic information embedded in BFIP is mined. Subsequently, by integrating stationary feature representation with mechanism features, our temporal matching broad learning system (TMBLS) aligns process and quality variables using MIQ as the target. This integration allows us to establish process monitoring statistics using both mechanism and data-driven features, as well as detect modeling deviations. Validated against real-world BFIP data, our MDCDS model demonstrates consistent process alignment, robust feature extraction, and improved MIQ modeling—Yielding better fault detection. Additionally, we offer detailed insights into the validation process, including parameter baselining and optimization. Details of the code are available online.¹

Feature-Driven Variational Mesh Denoising

Jianbin Yang, Cong Wang, Hui Hou, Mingyuan Wang, Xuelong Li

2025, 12(5): 913-924. doi: 10.1109/JAS.2024.124923

Abstract(91) HTML (16) PDF(24)

Abstract:
This work elaborates an innovative mesh denoising approach that combines feature recovery and denoising in an alternating manner. It proposes a feature-driven variational model and introduces an iterative scheme that alternates between feature recovery and the denoising process. The main idea is to estimate feature candidates, filter noisy face normals in the smooth (non-feature) domain, and utilize erosion and dilation operators on the feature candidates. By imposing connectivity constraints on normal vectors with large amplitude variations, the proposed scheme effectively removes noise and progressively recovers both sharp and small-scale features during the iterative process. To validate its effectiveness, this work conducts extensive numerical experiments on both simulated and real-scanned data. The results demonstrate significant improvements in noise reduction and feature preservation compared to existing methods.

Federated Services: A Smart Service Ecology With Federated Security for Aligned Data Supply and Scenario-Oriented Demands

Xiaofeng Jia, Juanjuan Li, Shouwen Wang, Hongwei Qi, Fei-Yue Wang, Rui Qin, Min Zhang, Xiaolong Liang

2025, 12(5): 925-936. doi: 10.1109/JAS.2024.124860

Abstract(85) HTML (10) PDF(20)

Abstract:
This paper introduces federated services as a smart service ecology with federated security to align distributed data supply with diversified service demands spanning digital and societal contexts. It presents the comprehensive researches on the theoretical foundation and technical system of federated services, aiming at advancing our understanding and implementation of this novel service paradigm. First, a thorough examination of the characteristics of federated security within federated services is conducted. Then, a five-layer technical framework is formulated under a decentralized intelligent architecture, ensuring secure, agile, and adaptable service provision. On this basis, the operational mechanisms underlying data federation and service confederation is analyzed, with emphasis on the smart supply-demand matching model. Furthermore, a scenario-oriented taxonomy of federated services accompanied by illustrative examples is proposed. Our work offers actionable insights and roadmap for realizing and advancing federated services, contributing to the refinement and wider adoption of this transformative service paradigm in the digital era.

Prescribed Performance Bipartite Consensus Control for MASs Under Data-Driven Strategy

Qi Zhou, Caiyun Yin, Hui Ma, Hongru Ren, Hongyi Li

2025, 12(5): 937-946. doi: 10.1109/JAS.2024.124956

Abstract(98) HTML (15) PDF(47)

Abstract:
This paper investigates the bipartite consensus control problem for discrete time nonlinear multiagent systems (MASs) based on data-driven adaptive method. To begin with, a dynamic linearization strategy is utilized to establish the relationship between bipartite tracking error and control input for MASs. Secondly, the unknown parameter linearly associated with control input is acquired by the adaptive control approach, and a discrete time extended state observer is designed to estimate nonlinear uncertainties. Thirdly, in order to achieve the prescribed performance, the constrained bipartite consensus error is transformed through a strictly increasing function. Based on the converted equivalent unconstrained error function, a sliding mode controller using only the input and output data of the MASs is designed. Finally, the efficacy of the controller is confirmed by simulations.

CSDD: A Benchmark Dataset for Casting Surface Defect Detection and Segmentation

Kai Mao, Ping Wei, Yangyang Wang, Meiqin Liu, Shuaijie Wang, Nanning Zheng

2025, 12(5): 947-960. doi: 10.1109/JAS.2025.125228

Abstract(190) HTML (15) PDF(51)

Abstract:
Automatic surface defect detection is a critical technique for ensuring product quality in industrial casting production. While general object detection techniques have made remarkable progress over the past decade, casting surface defect detection still has considerable room for improvement. Lack of sufficient and high-quality data has become one of the most challenging problems for casting surface defect detection. In this paper, we construct a new casting surface defect dataset (CSDD) containing 2100 high-resolution images of casting surface defects and 56 356 defects in total. The class and defect region for each defect are manually labeled. We conduct a series of experiments on this dataset using multiple state-of-the-art object detection methods, establishing a comprehensive set of baselines. We also propose a defect detection method based on YOLOv5 with the global attention mechanism and partial convolution. Our proposed method achieves superior performance compared to other object detection methods. Additionally, we also conduct a series of experiments with multiple state-of-the-art semantic segmentation methods, providing extensive baselines for defect segmentation. To the best of our knowledge, the CSDD has the largest number of defects for casting surface defect detection and segmentation. It would benefit both the industrial vision research and manufacturing applications. Dataset and code are available at https://github.com/Kerio99/CSDD.

Evolutionary Algorithm Based on Surrogate and Inverse Surrogate Models for Expensive Multiobjective Optimization

Qi Deng, Qi Kang, MengChu Zhou, Xiaoling Wang, Shibing Zhao, Siqi Wu, Mohammadhossein Ghahramani

2025, 12(5): 961-973. doi: 10.1109/JAS.2025.125111

Abstract(196) HTML (11) PDF(59)

Abstract:
When dealing with expensive multiobjective optimization problems, majority of existing surrogate-assisted evolutionary algorithms (SAEAs) generate solutions in decision space and screen candidate solutions mostly by using designed surrogate models. The generated solutions exhibit excessive randomness, which tends to reduce the likelihood of generating good-quality solutions and cause a long evolution to the optima. To improve SAEAs greatly, this work proposes an evolutionary algorithm based on surrogate and inverse surrogate models by 1) Employing a surrogate model in lieu of expensive (true) function evaluations; and 2) Proposing and using an inverse surrogate model to generate new solutions. By using the same training data but with its inputs and outputs being reversed, the latter is simple to train. It is then used to generate new vectors in objective space, which are mapped into decision space to obtain their corresponding solutions. Using a particular example, this work shows its advantages over existing SAEAs. The results of comparing it with state-of-the-art algorithms on expensive optimization problems show that it is highly competitive in both solution performance and efficiency.

Precision Synchronous Control of Multiple Motion Systems: A Tube-Based MPC Approach

Shuaiqi Chen, Fazhi Song, Yue Dong, Ning Cui, Yang Liu, Xinkai Chen

2025, 12(5): 974-988. doi: 10.1109/JAS.2025.125222

Abstract(113) HTML (9) PDF(29)

Abstract:
Lithography machines operate in scanning mode for the fabrication of large-scale integrated circuits (ICs), requiring high-precision synchronous motion between the reticle and wafer stages. Disturbances generated by each stage during high-acceleration movements are transmitted through the base frame, resulting in degradation of synchronization performance. To address this challenge, this paper proposes a tube-based model predictive control (tube-MPC) approach for synchronization in lithography machines. First, the proposed modeling method accurately characterizes the coupling disturbances and synchronization dynamics. Subsequently, a tube-MPC approach is developed to ensure that the states of the nominal system are constrained within the terminal constraint set. To reduce the complexity of online computations, an approach is employed to transform online optimization problems into offline problems by creating an online lookup table. This enables the determination of optimal control inputs via a simplified online optimization algorithm. The robustness and trajectory tracking performance of the proposed approach are verified through simulation experiments, demonstrating its effectiveness in enhancing the synchronization performance of multiple motion systems.

Data-Driven Two-Stage Robust Optimization Allocation and Loading for Salt Lake Chemical Enterprise Products Under Demand Uncertainty

Yiyin Tang, Yalin Wang, Chenliang Liu, Qingkai Sui, Yishun Liu, Keke Huang, Weihua Gui

2025, 12(5): 989-1003. doi: 10.1109/JAS.2025.125204

Abstract(92) HTML (10) PDF(24)

Abstract:
Most enterprises rely on railway transportation to deliver their products to customers, particularly in the salt lake chemical industry. Notably, allocating products to freight spaces and their assembly on transport vehicles are critical pre-transportation processes. However, due to demand fluctuations from changing product orders and unforeseen railway scheduling delays, manually adjusted allocation and loading may lead to excessive loading and unloading distances and times, ultimately increasing transportation costs for enterprises. To address these issues, this paper proposes a data-driven two-stage robust optimization (TSRO) framework embedding with the gated stacked temporal autoencoder clustering based on the attention mechanism (GSTAC-AM), which aims to overcome demand uncertainty and enhance the efficiency of freight allocation and loading. Specifically, GSTAC-AM is developed to help predict the deviation level of demand uncertainty and mitigate the impact of potential outliers. Then, a robust counterpart model is formulated to ensure computational tractability. In addition, a multi-stage hybrid heuristic algorithm is designed to handle the large scale and complexity inherent in the freight space allocation and loading processes. Finally, the effectiveness and applicability of the proposed framework are validated through a real case study conducted in a large salt lake chemical enterprise.

MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification With Zoom-Free Remote Sensing Imagery

Yansheng Li, Yuning Wu, Gong Cheng, Chao Tao, Bo Dang, Yu Wang, Jiahao Zhang, Chuge Zhang, Yiting Liu, Xu Tang, Jiayi Ma, Yongjun Zhang

2025, 12(5): 1004-1023. doi: 10.1109/JAS.2025.125324

Abstract(340) HTML (12) PDF(100)

Abstract:
Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications. However, existing approaches often rely on manually zooming remote sensing images at different scales to create typical scene samples. This approach fails to adequately support the fixed-resolution image interpretation requirements in real-world scenarios. To address this limitation, we introduce the million-scale fine-grained geospatial scene classification dataset (MEET), which contains over 1.03 million zoom-free remote sensing scene samples, manually annotated into 80 fine-grained categories. In MEET, each scene sample follows a scene-in-scene layout, where the central scene serves as the reference, and auxiliary scenes provide crucial spatial context for fine-grained classification. Moreover, to tackle the emerging challenge of scene-in-scene classification, we present the context-aware transformer (CAT), a model specifically designed for this task, which adaptively fuses spatial context to accurately classify the scene samples. CAT adaptively fuses spatial context to accurately classify the scene samples by learning attentional features that capture the relationships between the center and auxiliary scenes. Based on MEET, we establish a comprehensive benchmark for fine-grained geospatial scene classification, evaluating CAT against 11 competitive baselines. The results demonstrate that CAT significantly outperforms these baselines, achieving a 1.88% higher balanced accuracy (BA) with the Swin-Large backbone, and a notable 7.87% improvement with the Swin-Huge backbone. Further experiments validate the effectiveness of each module in CAT and show the practical applicability of CAT in the urban functional zone mapping. The source code and dataset will be publicly available at https://jerrywyn.github.io/project/MEET.html.

A Game-Theoretic Approach to Solving the Roman Domination Problem

Xiuyang Chen, Changbing Tang, Zhao Zhang, Guanrong Chen

2025, 12(5): 1024-1040. doi: 10.1109/JAS.2023.123840

Abstract(128) HTML (12) PDF(24)

Abstract:
The Roman domination problem is an important combinatorial optimization problem that is derived from an old story of defending the Roman Empire and now regains new significance in cyber space security, considering backups in the face of a dynamic network security requirement. In this paper, firstly, we propose a Roman domination game (RDG) and prove that every Nash equilibrium (NE) of the game corresponds to a strong minimal Roman dominating function (S-RDF), as well as a Pareto-optimal solution. Secondly, we show that RDG is an exact potential game, which guarantees the existence of an NE. Thirdly, we design a game-based synchronous algorithm (GSA), which can be implemented distributively and converge to an NE in $ O(n)$ rounds, where n is the number of vertices. In GSA, all players make decisions depending on local information. Furthermore, we enhance GSA to be enhanced GSA (EGSA), which converges to a better NE in $ O(n^2)$ rounds. Finally, we present numerical simulations to demonstrate that EGSA can obtain a better approximate solution in promising computation time compared with state-of-the-art algorithms.