IEEE/CAA Journal of Automatica Sinica

Knowledge As Not Only Justified True Beliefs in Vision

Wenbo Zheng, Fei-Yue Wang

2025, 12(2): 297-299. doi: 10.1109/JAS.2024.124584

Abstract(39) HTML (10) PDF(35)

Abstract:

From Static and Dynamic Perspectives: A Survey on Historical Data Benchmarks of Control Performance Monitoring

Pengyu Song, Jie Wang, Chunhui Zhao, Biao Huang

2025, 12(2): 300-316. doi: 10.1109/JAS.2024.124902

Abstract(66) HTML (9) PDF(20)

Abstract:
In recent decades, control performance monitoring (CPM) has experienced remarkable progress in research and industrial applications. While CPM research has been investigated using various benchmarks, the historical data benchmark (HIS) has garnered the most attention due to its practicality and effectiveness. However, existing CPM reviews usually focus on the theoretical benchmark, and there is a lack of an in-depth review that thoroughly explores HIS-based methods. In this article, a comprehensive overview of HIS-based CPM is provided. First, we provide a novel static-dynamic perspective on data-level manifestations of control performance underlying typical controller capacities including regulation and servo: static and dynamic properties. The static property portrays time-independent variability in system output, and the dynamic property describes temporal behavior driven by closed-loop feedback. Accordingly, existing HIS-based CPM approaches and their intrinsic motivations are classified and analyzed from these two perspectives. Specifically, two mainstream solutions for CPM methods are summarized, including static analysis and dynamic analysis, which match data-driven techniques with actual controlling behavior. Furthermore, this paper also points out various opportunities and challenges faced in CPM for modern industry and provides promising directions in the context of artificial intelligence for inspiring future research.

When Software Security Meets Large Language Models: A Survey

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

2025, 12(2): 317-334. doi: 10.1109/JAS.2024.124971

Abstract(22) HTML (18) PDF(10)

Abstract:
Software security poses substantial risks to our society because software has become part of our life. Numerous techniques have been proposed to resolve or mitigate the impact of software security issues. Among them, software testing and analysis are two of the critical methods, which significantly benefit from the advancements in deep learning technologies. Due to the successful use of deep learning in software security, recently, researchers have explored the potential of using large language models (LLMs) in this area. In this paper, we systematically review the results focusing on LLMs in software security. We analyze the topics of fuzzing, unit test, program repair, bug reproduction, data-driven bug detection, and bug triage. We deconstruct these techniques into several stages and analyze how LLMs can be used in the stages. We also discuss the future directions of using LLMs in software security, including the future directions for the existing use of LLMs and extensions from conventional deep learning research.

Privacy Distributed Constrained Optimization Over Time-Varying Unbalanced Networks and Its Application in Federated Learning

Mengli Wei, Wenwu Yu, Duxin Chen, Mingyu Kang, Guang Cheng

2025, 12(2): 335-346. doi: 10.1109/JAS.2024.124869

Abstract(155) HTML (9) PDF(53)

Abstract:
This paper investigates a class of constrained distributed zeroth-order optimization (ZOO) problems over time-varying unbalanced graphs while ensuring privacy preservation among individual agents. Not taking into account recent progress and addressing these concerns separately, there remains a lack of solutions offering theoretical guarantees for both privacy protection and constrained ZOO over time-varying unbalanced graphs. We hereby propose a novel algorithm, termed the differential privacy (DP) distributed push-sum based zeroth-order constrained optimization algorithm (DP-ZOCOA). Operating over time-varying unbalanced graphs, DP-ZOCOA obviates the need for supplemental suboptimization problem computations, thereby reducing overhead in comparison to distributed primary-dual methods. DP-ZOCOA is specifically tailored to tackle constrained ZOO problems over time-varying unbalanced graphs, offering a guarantee of convergence to the optimal solution while robustly preserving privacy. Moreover, we provide rigorous proofs of convergence and privacy for DP-ZOCOA, underscoring its efficacy in attaining optimal convergence without constraints. To enhance its applicability, we incorporate DP-ZOCOA into the federated learning framework and formulate a decentralized zeroth-order constrained federated learning algorithm (ZOCOA-FL) to address challenges stemming from the time-varying imbalance of communication topology. Finally, the performance and effectiveness of the proposed algorithms are thoroughly evaluated through simulations on distributed least squares (DLS) and decentralized federated learning (DFL) tasks.

Unifying Fixed Time and Prescribed Time Control for Strict-Feedback Nonlinear Systems

Xiang Chen, Yujuan Wang, Yongduan Song

2025, 12(2): 347-355. doi: 10.1109/JAS.2024.124401

Abstract(68) HTML (10) PDF(35)

Abstract:
This paper investigates the prescribed-time tracking control problem for a class of multi-input multi-output (MIMO) nonlinear strict-feedback systems subject to non-vanishing uncertainties. The inherent unmatched and non-vanishing uncertainties make the prescribed-time control problem become much more nontrivial. The solution to address the challenges mentioned above involves incorporating a prescribed-time filter, as opposed to a finite-time filter, and formulating a prescribed-time Lyapunov stability lemma (Lemma 5). The prescribed-time Lyapunov stability lemma is based on time axis shifting time-varying yet bounded gain, which establishes a novel link between the fixed-time and prescribed-time control method. This allows the restriction condition that the time-varying gain function must satisfy as imposed in most exist prescribed-time control works to be removed. Under the proposed control method, the desire trajectory is ensured to closely track the output of the system in prescribed time. The effectiveness of the theoretical results are verified through numerical simulation.

Cubature Kalman Fusion Filtering Under Amplify-and-Forward Relays With Randomly Varying Channel Parameters

Jiaxing Li, Zidong Wang, Jun Hu, Hongli Dong, Hongjian Liu

2025, 12(2): 356-368. doi: 10.1109/JAS.2024.124590

Abstract(65) HTML (9) PDF(17)

Abstract:
In this paper, the problem of cubature Kalman fusion filtering (CKFF) is addressed for multi-sensor systems under amplify-and-forward (AaF) relays. For the purpose of facilitating data transmission, AaF relays are utilized to regulate signal communication between sensors and filters. Here, the randomly varying channel parameters are represented by a set of stochastic variables whose occurring probabilities are permitted to exhibit bounded uncertainty. Employing the spherical-radial cubature principle, a local filter under AaF relays is initially constructed. This construction ensures and minimizes an upper bound of the filtering error covariance by designing an appropriate filter gain. Subsequently, the local filters are fused through the application of the covariance intersection fusion rule. Furthermore, the uniform boundedness of the filtering error covariance’s upper bound is investigated through establishing certain sufficient conditions. The effectiveness of the proposed CKFF scheme is ultimately validated via a simulation experiment concentrating on a three-phase induction machine.

A Multi-Condition Sequential Network Ensemble for Industrial Energy Storage Prediction Considering the Condition Switching Characteristics

Tianyu Wang, Fan Zhou, Yangjie Wu, Jun Zhao, Wei Wang

2025, 12(2): 369-380. doi: 10.1109/JAS.2024.124962

Abstract(60) HTML (8) PDF(15)

Abstract:
As a crucial storage and buffering apparatus for balancing the production and consumption of byproduct gases in industrial processes, accurate prediction of gas tank levels is essential for optimizing energy system scheduling. Considering that the continuous switching of the pressure and valve status (mechanism knowledge) would bring about multiple working conditions of the equipment, a multi-condition time sequential network ensembled method is proposed. In order to especially consider the time dependence of different conditions, a central-wise condition sequential network is developed, where the network branches are specially designed based on the condition switching sequences. A branch combination transfer learning strategy is developed to tackle the sample imbalance problem of different condition data. Since the condition or status data are real-time information that cannot be recognized during the prediction process, a pre-trained and ensemble learning approach is further proposed to fuse the outputs of the multi-condition networks and realize a transient-state involved prediction. The performance of the proposed method is validated on practical energy data coming from a domestic steel plant, comparing with the state-of-the-art algorithms. The results show that the proposed method can maintain a high prediction accuracy under different condition switching cases, which would provide effective guidance for the optimal scheduling of the industrial energy systems.

Broad-Learning-System-Based Model-Free Adaptive Predictive Control for Nonlinear MASs Under DoS Attacks

Hongxing Xiong, Guangdeng Chen, Hongru Ren, Hongyi Li

2025, 12(2): 381-393. doi: 10.1109/JAS.2024.124929

Abstract(71) HTML (11) PDF(25)

Abstract:
In this paper, the containment control problem in nonlinear multi-agent systems (NMASs) under denial-of-service (DoS) attacks is addressed. Firstly, a prediction model is obtained using the broad learning technique to train historical data generated by the system offline without DoS attacks. Secondly, the dynamic linearization method is used to obtain the equivalent linearization model of NMASs. Then, a novel model-free adaptive predictive control (MFAPC) framework based on historical and online data generated by the system is proposed, which combines the trained prediction model with the model-free adaptive control method. The development of the MFAPC method motivates a much simpler robust predictive control solution that is convenient to use in the case of DoS attacks. Meanwhile, the MFAPC algorithm provides a unified predictive framework for solving consensus tracking and containment control problems. The boundedness of the containment error can be proven by using the contraction mapping principle and the mathematical induction method. Finally, the proposed MFAPC is assessed through comparative experiments.

Penalty Function-Based Distributed Primal-Dual Algorithm for Nonconvex Optimization Problem

Xiasheng Shi, Changyin Sun

2025, 12(2): 394-402. doi: 10.1109/JAS.2024.124935

Abstract(100) HTML (10) PDF(43)

Abstract:
This paper addresses the distributed nonconvex optimization problem, where both the global cost function and local inequality constraint function are nonconvex. To tackle this issue, the p-power transformation and penalty function techniques are introduced to reframe the nonconvex optimization problem. This ensures that the Hessian matrix of the augmented Lagrangian function becomes local positive definite by choosing appropriate control parameters. A multi-timescale primal-dual method is then devised based on the Karush-Kuhn-Tucker (KKT) point of the reformulated nonconvex problem to attain convergence. The Lyapunov theory guarantees the model’s stability in the presence of an undirected and connected communication network. Finally, two nonconvex optimization problems are presented to demonstrate the efficacy of the previously developed method.

Residential Energy Scheduling With Solar Energy Based on Dyna Adaptive Dynamic Programming

Kang Xiong, Qinglai Wei, Hongyang Li

2025, 12(2): 403-413. doi: 10.1109/JAS.2024.124809

Abstract(76) HTML (9) PDF(13)

Abstract:
Learning-based methods have become mainstream for solving residential energy scheduling problems. In order to improve the learning efficiency of existing methods and increase the utilization of renewable energy, we propose the Dyna action-dependent heuristic dynamic programming (Dyna-ADHDP) method, which incorporates the ideas of learning and planning from the Dyna framework in action-dependent heuristic dynamic programming. This method defines a continuous action space for precise control of an energy storage system and allows online optimization of algorithm performance during the real-time operation of the residential energy model. Meanwhile, the target network is introduced during the training process to make the training smoother and more efficient. We conducted experimental comparisons with the benchmark method using simulated and real data to verify its applicability and performance. The results confirm the method’s excellent performance and generalization capabilities, as well as its excellence in increasing renewable energy utilization and extending equipment life.

Impulsive Consensus of MASs With Input Saturation and DoS Attacks

Xuyang Wang, Dengxiu Yu, Xiaodi Li

2025, 12(2): 414-424. doi: 10.1109/JAS.2024.124944

Abstract(73) HTML (5) PDF(24)

Abstract:
This paper investigates the secure impulsive consensus of Lipschitz-type nonlinear multi-agent systems (MASs) with input saturation. According to the coupling of input saturation and denial of service (DoS) attacks, impulsive control for MASs becomes extremely challenging. Considering general DoS attacks, this paper provides the sufficient conditions for the almost sure consensus of the MASs with input saturation, where the error system can achieve almost sure local exponential stability. Through linear matrix inequalities (LMIs), the relation between the trajectory boundary and DoS attacks is characterized, and the trajectory boundary is estimated. Furthermore, an optimization method of the domain of attraction is proposed to maximize the size. And a non-conservative and practical boundary is proposed to characterize the effect of DoS attacks on MASs. Finally, considering a multi-agent system with typical Chua’s circuit dynamic model, an example is provided to illustrate the theorems’ correctness.

A Correntropy-Based Echo State Network With Application to Time Series Prediction

Xiufang Chen, Zhenming Su, Long Jin, Shuai Li

2025, 12(2): 425-435. doi: 10.1109/JAS.2024.124932

Abstract(45) HTML (7) PDF(6)

Abstract:
As a category of recurrent neural networks, echo state networks (ESNs) have been the topic of in-depth investigations and extensive applications in a diverse array of fields, with spectacular triumphs achieved. Nevertheless, the traditional ESN and the majority of its variants are devised in the light of the second-order statistical information of data (e.g., variance and covariance), while more information is neglected. In the context of information theoretic learning, correntropy demonstrates the capacity to grab more information from data. Therefore, under the guidelines of the maximum correntropy criterion, this paper proposes a correntropy-based echo state network (CESN) in which the first-order and higher-order information of data is captured, promoting robustness to noise. Furthermore, an incremental learning algorithm for the CESN is presented, which has the expertise to update the CESN when new data arrives, eliminating the need to retrain the network from scratch. Finally, experiments on benchmark problems and comparisons with existing works are provided to verify the effectiveness and superiority of the proposed CESN.

Value Iteration-Based Distributed Adaptive Dynamic Programming for Multi-Player Differential Game With Incomplete Information

Yun Zhang, Yuqi Wang, Yunze Cai

2025, 12(2): 436-447. doi: 10.1109/JAS.2024.124950

Abstract(57) HTML (8) PDF(24)

Abstract:
In this paper, a distributed adaptive dynamic programming (ADP) framework based on value iteration is proposed for multi-player differential games. In the game setting, players have no access to the information of others’ system parameters or control laws. Each player adopts an on-policy value iteration algorithm as the basic learning framework. To deal with the incomplete information structure, players collect a period of system trajectory data to compensate for the lack of information. The policy updating step is implemented by a nonlinear optimization problem aiming to search for the proximal admissible policy. Theoretical analysis shows that by adopting proximal policy searching rules, the approximated policies can converge to a neighborhood of equilibrium policies. The efficacy of our method is illustrated by three examples, which also demonstrate that the proposed method can accelerate the learning process compared with the centralized learning framework.

Decentralized Federated Learning Algorithm Under Adversary Eavesdropping

Lei Xu, Danya Xu, Xinlei Yi, Chao Deng, Tianyou Chai, Tao Yang

2025, 12(2): 448-456. doi: 10.1109/JAS.2024.125079

Abstract(43) HTML (11) PDF(15)

Abstract:
In this paper, we study the decentralized federated learning problem, which involves the collaborative training of a global model among multiple devices while ensuring data privacy. In classical federated learning, the communication channel between the devices poses a potential risk of compromising private information. To reduce the risk of adversary eavesdropping in the communication channel, we propose TRADE (transmit difference weight) concept. This concept replaces the decentralized federated learning algorithm’s transmitted weight parameters with differential weight parameters, enhancing the privacy data against eavesdropping. Subsequently, by integrating the TRADE concept with the primal-dual stochastic gradient descent (SGD) algorithm, we propose a decentralized TRADE primal-dual SGD algorithm. We demonstrate that our proposed algorithm’s convergence properties are the same as those of the primal-dual SGD algorithm while providing enhanced privacy protection. We validate the algorithm’s performance on fault diagnosis task using the Case Western Reserve University dataset, and image classification tasks using the CIFAR-10 and CIFAR-100 datasets, revealing model accuracy comparable to centralized federated learning. Additionally, the experiments confirm the algorithm’s privacy protection capability.