IEEE/CAA Journal of Automatica Sinica

Chat with ChatGPT on Industry 5.0: Learning and Decision-Making for Intelligent Industries

Fei-Yue Wang, Jing Yang, Xingxia Wang, Juanjuan Li, Qing-Long Han

2023, 10(4): 831-834. doi: 10.1109/JAS.2023.123552

Abstract(2331) HTML (251) PDF(1155)

Abstract:

Can ChatGPT Boost Artistic Creation: The Need of Imaginative Intelligence for Parallel Art

Chao Guo, Yue Lu, Yong Dou, Fei-Yue Wang

2023, 10(4): 835-838. doi: 10.1109/JAS.2023.123555

Abstract(1241) HTML (123) PDF(512)

Abstract:

Online Optimization in Power Systems With High Penetration of Renewable Generation: Advances and Prospects

Zhaojian Wang, Wei Wei, John Zhen Fu Pang, Feng Liu, Bo Yang, Xinping Guan, Shengwei Mei

2023, 10(4): 839-858. doi: 10.1109/JAS.2023.123126

Abstract(598) HTML (246) PDF(102)

Abstract:
Traditionally, offline optimization of power systems is acceptable due to the largely predictable loads and reliable generation. The increasing penetration of fluctuating renewable generation and internet-of-things devices allowing for fine-grained controllability of loads have led to the diminishing applicability of offline optimization in the power systems domain, and have redirected attention to online optimization methods. However, online optimization is a broad topic that can be applied in and motivated by different settings, operated on different time scales, and built on different theoretical foundations. This paper reviews the various types of online optimization techniques used in the power systems domain and aims to make clear the distinction between the most common techniques used. In particular, we introduce and compare four distinct techniques used covering the breadth of online optimization techniques used in the power systems domain, i.e., optimization-guided dynamic control, feedback optimization for single-period problems, Lyapunov-based optimization, and online convex optimization techniques for multi-period problems. Lastly, we recommend some potential future directions for online optimization in the power systems domain.

Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine

Ahmad Chaddad, Qizong Lu, Jiali Li, Yousef Katib, Reem Kateb, Camel Tanougast, Ahmed Bouridane, Ahmed Abdulkadir

2023, 10(4): 859-876. doi: 10.1109/JAS.2023.123123

Abstract(920) HTML (209) PDF(100)

Abstract:
Artificial intelligence (AI) continues to transform data analysis in many domains. Progress in each domain is driven by a growing body of annotated data, increased computational resources, and technological innovations. In medicine, the sensitivity of the data, the complexity of the tasks, the potentially high stakes, and a requirement of accountability give rise to a particular set of challenges. In this review, we focus on three key methodological approaches that address some of the particular challenges in AI-driven medical decision making. 1) Explainable AI aims to produce a human-interpretable justification for each output. Such models increase confidence if the results appear plausible and match the clinicians expectations. However, the absence of a plausible explanation does not imply an inaccurate model. Especially in highly non-linear, complex models that are tuned to maximize accuracy, such interpretable representations only reflect a small portion of the justification. 2) Domain adaptation and transfer learning enable AI models to be trained and applied across multiple domains. For example, a classification task based on images acquired on different acquisition hardware. 3) Federated learning enables learning large-scale models without exposing sensitive personal health information. Unlike centralized AI learning, where the centralized learning machine has access to the entire training data, the federated learning process iteratively updates models across multiple sites by exchanging only parameter updates, not personal health data. This narrative review covers the basic concepts, highlights relevant corner-stone and state-of-the-art research in the field, and discusses perspectives.

DAO to HANOI via DeSci: AI Paradigm Shifts from AlphaGo to ChatGPT

Qinghai Miao, Wenbo Zheng, Yisheng Lv, Min Huang, Wenwen Ding, Fei-Yue Wang

2023, 10(4): 877-897. doi: 10.1109/JAS.2023.123561

Abstract(1332) HTML (166) PDF(532)

Abstract:
From AlphaGo to ChatGPT, the field of AI has launched a series of remarkable achievements in recent years. Analyzing, comparing, and summarizing these achievements at the paradigm level is important for future AI innovation, but has not received sufficient attention. In this paper, we give an overview and perspective on machine learning paradigms. First, we propose a paradigm taxonomy with three levels and seven dimensions from a knowledge perspective. Accordingly, we give an overview on three basic and twelve extended learning paradigms, such as Ensemble Learning, Transfer Learning, etc., with figures in unified style. We further analyze three advanced paradigms, i.e., AlphaGo, AlphaFold and ChatGPT. Second, to enable more efficient and effective scientific discovery, we propose to build a new ecosystem that drives AI paradigm shifts through the decentralized science (DeSci) movement based on decentralized autonomous organization (DAO). To this end, we design the Hanoi framework, which integrates human factors, parallel intelligence based on a combination of artificial systems and the natural world, and the DAO to inspire AI innovations.

Passive Attack Detection for a Class of Stealthy Intermittent Integrity Attacks

Kangkang Zhang, Christodoulos Keliris, Thomas Parisini, Bin Jiang, Marios M. Polycarpou

2023, 10(4): 898-915. doi: 10.1109/JAS.2023.123177

Abstract(570) HTML (172) PDF(106)

Abstract:
This paper proposes a passive methodology for detecting a class of stealthy intermittent integrity attacks in cyber-physical systems subject to process disturbances and measurement noise. A stealthy intermittent integrity attack strategy is first proposed by modifying a zero-dynamics attack model. The stealthiness of the generated attacks is rigorously investigated under the condition that the adversary does not know precisely the system state values. In order to help detect such attacks, a backward-in-time detection residual is proposed based on an equivalent quantity of the system state change, due to the attack, at a time prior to the attack occurrence time. A key characteristic of this residual is that its magnitude increases every time a new attack occurs. To estimate this unknown residual, an optimal fixed-point smoother is proposed by minimizing a piece-wise linear quadratic cost function with a set of specifically designed weighting matrices. The smoother design guarantees robustness with respect to process disturbances and measurement noise, and is also able to maintain sensitivity as time progresses to intermittent integrity attack by resetting the covariance matrix based on the weighting matrices. The adaptive threshold is designed based on the estimated backward-in-time residual, and the attack detectability analysis is rigorously investigated to characterize quantitatively the class of attacks that can be detected by the proposed methodology. Finally, a simulation example is used to demonstrate the effectiveness of the developed methodology.

Machine Learning Accelerated Real-Time Model Predictive Control for Power Systems

Ramij Raja Hossain, Ratnesh Kumar

2023, 10(4): 916-930. doi: 10.1109/JAS.2023.123135

Abstract(795) HTML (257) PDF(139)

Abstract:
This paper presents a machine-learning-based speed-up strategy for real-time implementation of model-predictive-control (MPC) in emergency voltage stabilization of power systems. Despite success in various applications, real-time implementation of MPC in power systems has not been successful due to the online control computation time required for large-sized complex systems, and in power systems, the computation time exceeds the available decision time used in practice by a large extent. This long-standing problem is addressed here by developing a novel MPC-based framework that i) computes an optimal strategy for nominal loads in an offline setting and adapts it for real-time scenarios by successive online control corrections at each control instant utilizing the latest measurements, and ii) employs a machine-learning based approach for the prediction of voltage trajectory and its sensitivity to control inputs, thereby accelerating the overall control computation by multiple times. Additionally, a realistic control coordination scheme among static var compensators (SVC), load-shedding (LS), and load tap-changers (LTC) is presented that incorporates the practical delayed actions of the LTCs. The performance of the proposed scheme is validated for IEEE 9-bus and 39-bus systems, with ±20% variations in nominal loading conditions together with contingencies. We show that our proposed methodology speeds up the online computation by 20-fold, bringing it down to a practically feasible value (fraction of a second), making the MPC real-time and feasible for power system control for the first time.

Noncooperative Model Predictive Game With Markov Jump Graph

Yang Xu, Yuan Yuan, Zhen Wang, Xuelong Li

2023, 10(4): 931-944. doi: 10.1109/JAS.2023.123129

Abstract(506) HTML (195) PDF(88)

Abstract:
In this paper, the distributed stochastic model predictive control (MPC) is proposed for the noncooperative game problem of the discrete-time multi-player systems (MPSs) with the undirected Markov jump graph. To reflect the reality, the state and input constraints have been considered along with the external disturbances. An iterative algorithm is designed such that model predictive noncooperative game could converge to the so-called ε-Nash equilibrium in a distributed manner. Sufficient conditions are established to guarantee the convergence of the proposed algorithm. In addition, a set of easy-to-check conditions are provided to ensure the mean-square uniform bounded stability of the underlying MPSs. Finally, a numerical example on a group of spacecrafts is studied to verify the effectiveness of the proposed method.

Deterministic and Stochastic Fixed-Time Stability of Discrete-time Autonomous Systems

Farzaneh Tatari, Hamidreza Modares

2023, 10(4): 945-956. doi: 10.1109/JAS.2023.123405

Abstract(509) HTML (206) PDF(90)

Abstract:
This paper studies deterministic and stochastic fixed-time stability of autonomous nonlinear discrete-time (DT) systems. Lyapunov conditions are first presented under which the fixed-time stability of deterministic DT systems is certified. Extensions to systems under deterministic perturbations as well as stochastic noise are then considered. For the former, sensitivity to perturbations for fixed-time stable DT systems is analyzed, and it is shown that fixed-time attractiveness results from the presented Lyapunov conditions. For the latter, sufficient Lyapunov conditions for fixed-time stability in probability of nonlinear stochastic DT systems are presented. The fixed upper bound of the settling-time function is derived for both fixed-time stable and fixed-time attractive systems, and a stochastic settling-time function fixed upper bound is derived for stochastic DT systems. Illustrative examples are given along with simulation results to verify the introduced results.

Generalized-Extended-State-Observer and Equivalent-Input-Disturbance Methods for Active Disturbance Rejection: Deep Observation and Comparison

Jinhua She, Kou Miyamoto, Qing-Long Han, Min Wu, Hiroshi Hashimoto, Qing-Guo Wang

2023, 10(4): 957-968. doi: 10.1109/JAS.2022.105929

Abstract(660) HTML (187) PDF(158)

Abstract:
Active disturbance-rejection methods are effective in estimating and rejecting disturbances in both transient and steady-state responses. This paper presents a deep observation on and a comparison between two of those methods: the generalized extended-state observer (GESO) and the equivalent input disturbance (EID) from assumptions, system configurations, stability conditions, system design, disturbance-rejection performance, and extensibility. A time-domain index is introduced to assess the disturbance-rejection performance. A detailed observation of disturbance-suppression mechanisms reveals the superiority of the EID approach over the GESO method. A comparison between these two methods shows that assumptions on disturbances are more practical and the adjustment of disturbance-rejection performance is easier for the EID approach than for the GESO method.

Resilient Time-Varying Formation-Tracking of Multi-UAV Systems Against Composite Attacks: A Two-Layered Framework

Xin Gong, Michael V. Basin, Zhiguang Feng, Tingwen Huang, Yukang Cui

2023, 10(4): 969-984. doi: 10.1109/JAS.2023.123339

Abstract(795) HTML (350) PDF(146)

Abstract:
This paper studies the countermeasure design problems of distributed resilient time-varying formation-tracking control for multi-UAV systems with single-way communications against composite attacks, including denial-of-services (DoS) attacks, false-data injection attacks, camouflage attacks, and actuation attacks (AAs). Inspired by the concept of digital twin, a new two-layered protocol equipped with a safe and private twin layer (TL) is proposed, which decouples the above problems into the defense scheme against DoS attacks on the TL and the defense scheme against AAs on the cyber-physical layer. First, a topology-repairing strategy against frequency-constrained DoS attacks is implemented via a Zeno-free event-triggered estimation scheme, which saves communication resources considerably. The upper bound of the reaction time needed to launch the repaired topology after the occurrence of DoS attacks is calculated. Second, a decentralized adaptive and chattering-relief controller against potentially unbounded AAs is designed. Moreover, this novel adaptive controller can achieve uniformly ultimately bounded convergence, whose error bound can be given explicitly. The practicability and validity of this new two-layered protocol are shown via a simulation example and a UAV swarm experiment equipped with both Ultra-WideBand and WiFi communication channels.

Encrypted Finite-Horizon Energy-to-Peak State Estimation for Time-Varying Systems Under Eavesdropping Attacks: Tackling Secrecy Capacity

Lei Zou, Zidong Wang, Bo Shen, Hongli Dong, Guoping Lu

2023, 10(4): 985-996. doi: 10.1109/JAS.2023.123393

Abstract(599) HTML (274) PDF(93)

Abstract:
This paper is concerned with the problem of finite-horizon energy-to-peak state estimation for a class of networked linear time-varying systems. Due to the inherent vulnerability of network-based communication, the measurement signals transmitted over a communication network might be intercepted by potential eavesdroppers. To avoid information leakage, by resorting to an artificial-noise-assisted method, we develop a novel encryption-decryption scheme to ensure that the transmitted signal is composed of the raw measurement and an artificial-noise term. A special evaluation index named secrecy capacity is employed to assess the information security of signal transmissions under the developed encryption-decryption scheme. The purpose of the addressed problem is to design an encryption-decryption scheme and a state estimator such that: 1) the desired secrecy capacity is ensured; and 2) the required finite-horizon ${\boldsymbol{l}_{{\boldsymbol{2}}}}$–${\boldsymbol{l}_{{\boldsymbol{\infty}}}}$ performance is achieved. Sufficient conditions are established on the existence of the encryption-decryption mechanism and the finite-horizon state estimator. Finally, simulation results are proposed to show the effectiveness of our proposed encryption-decryption-based state estimation scheme.

Distributed Adaptive Output Consensus of Unknown Heterogeneous Non-Minimum Phase Multi-Agent Systems

Wenji Cao, Lu Liu, Gang Feng

2023, 10(4): 997-1008. doi: 10.1109/JAS.2023.123204

Abstract(762) HTML (170) PDF(169)

Abstract:
This article addresses the leader-following output consensus problem of heterogeneous linear multi-agent systems with unknown agent parameters under directed graphs. The dynamics of followers are allowed to be non-minimum phase with unknown arbitrary individual relative degrees. This is contrary to many existing works on distributed adaptive control schemes where agent dynamics are required to be minimum phase and often of the same relative degree. A distributed adaptive pole placement control scheme is developed, which consists of a distributed observer and an adaptive pole placement control law. It is shown that under the proposed distributed adaptive control scheme, all signals in the closed-loop system are bounded and the outputs of all the followers track the output of the leader asymptotically. The effectiveness of the proposed scheme is demonstrated by one practical example and one numerical example.

Kinematic Control of Serial Manipulators Under False Data Injection Attack

Yinyan Zhang, Shuai Li

2023, 10(4): 1009-1019. doi: 10.1109/JAS.2023.123132

Abstract(570) HTML (143) PDF(84)

Abstract:
With advanced communication technologies, cyber-physical systems such as networked industrial control systems can be monitored and controlled by a remote control center via communication networks. While lots of benefits can be achieved with such a configuration, it also brings the concern of cyber attacks to the industrial control systems, such as networked manipulators that are widely adopted in industrial automation. For such systems, a false data injection attack on a control-center-to-manipulator (CC-M) communication channel is undesirable, and has negative effects on the manufacture quality. In this paper, we propose a resilient remote kinematic control method for serial manipulators undergoing a false data injection attack by leveraging the kinematic model. Theoretical analysis shows that the proposed method can guarantee asymptotic convergence of the regulation error to zero in the presence of a type of false data injection attack. The efficacy of the proposed method is validated via simulations.

Adaptive Leader-Follower Consensus Control of Multiple Flexible Manipulators With Actuator Failures and Parameter Uncertainties

Yu Liu, Lin Li

2023, 10(4): 1020-1031. doi: 10.1109/JAS.2023.123093

Abstract(515) HTML (203) PDF(130)

Abstract:
In this paper, the leader-follower consensus problem for a multiple flexible manipulator network with actuator failures, parameter uncertainties, and unknown time-varying boundary disturbances is addressed. The purpose of this study is to develop distributed controllers utilizing local interactive protocols that not only suppress the vibration of each flexible manipulator but also achieve consensus on joint angle position between actual followers and the virtual leader. Following the accomplishment of the reconstruction of the fault terms and parameter uncertainties, the adaptive neural network method and parameter estimation technique are employed to compensate for unknown items and bounded disturbances. Furthermore, the Lyapunov stability theory is used to demonstrate that followers’ angle consensus errors and vibration deflections in closed-loop systems are uniformly ultimately bounded. Finally, the numerical simulation results confirm the efficacy of the proposed controllers.

Game and Dynamic Communication Path-Based Pricing Strategies for Microgrids Under Communication Interruption

Bo Zhang, Chunxia Dou, Dong Yue, Ju H. Park, Yudi Zhang, Zhanqiang Zhang

2023, 10(4): 1032-1047. doi: 10.1109/JAS.2023.123138

Abstract(496) HTML (194) PDF(59)

Abstract:
Nowadays, the microgrid cluster is an important application scenario for energy trading. In trading, one of the most important research directions is the issue of pricing. To determine reasonable pricing for the microgrid cluster, data communication is used to create the cyber-physical system (CPS), which can improve the observability of microgrids. Then, the following works are carried out in the CPS. In the physical layer: 1) Regarding trading between microgrids and the load, based on the generalized game theory, an optimal pricing strategy is proposed, which takes into account the interactive relationships among microgrids and transforms the pricing problem into a Nikaido-Isoda function to obtain the optimal prices conveniently; 2) Regarding peer-to-peer trading between two microgrids, based on evolutionary game theory and the penalty mechanism, the optimal sale price of the seller is selected with boundary rationality. In the cyber layer, regarding the communication interruption issue existing in pricing (i.e., the game process), based on the principle of matching the performance of the path with the importance degree of the data, a dynamic regulating method of paths is proposed, i.e., adopting a new path to re-transmit the interrupted data to the destination. Finally, the effect of the proposed strategies is verified by case studies.

A Fast Clustering Based Evolutionary Algorithm for Super-Large-Scale Sparse Multi-Objective Optimization

Ye Tian, Yuandong Feng, Xingyi Zhang, Changyin Sun

2023, 10(4): 1048-1063. doi: 10.1109/JAS.2022.105437

Abstract(1253) HTML (250) PDF(136)

Abstract:
During the last three decades, evolutionary algorithms (EAs) have shown superiority in solving complex optimization problems, especially those with multiple objectives and non-differentiable landscapes. However, due to the stochastic search strategies, the performance of most EAs deteriorates drastically when handling a large number of decision variables. To tackle the curse of dimensionality, this work proposes an efficient EA for solving super-large-scale multi-objective optimization problems with sparse optimal solutions. The proposed algorithm estimates the sparse distribution of optimal solutions by optimizing a binary vector for each solution, and provides a fast clustering method to highly reduce the dimensionality of the search space. More importantly, all the operations related to the decision variables only contain several matrix calculations, which can be directly accelerated by GPUs. While existing EAs are capable of handling fewer than 10 000 real variables, the proposed algorithm is verified to be effective in handling 1 000 000 real variables. Furthermore, since the proposed algorithm handles the large number of variables via accelerated matrix calculations, its runtime can be reduced to less than 10% of the runtime of existing EAs.

A Novel Parameter-Optimized Recurrent Attention Network for Pipeline Leakage Detection

Tong Sun, Chuang Wang, Hongli Dong, Yina Zhou, Chuang Guan

2023, 10(4): 1064-1076. doi: 10.1109/JAS.2023.123180

Abstract(753) HTML (90) PDF(56)

Abstract:
Accurate detection of pipeline leakage is essential to maintain the safety of pipeline transportation. Recently, deep learning (DL) has emerged as a promising tool for pipeline leakage detection (PLD). However, most existing DL methods have difficulty in achieving good performance in identifying leakage types due to the complex time dynamics of pipeline data. On the other hand, the initial parameter selection in the detection model is generally random, which may lead to unstable recognition performance. For this reason, a hybrid DL framework referred to as parameter-optimized recurrent attention network (PRAN) is presented in this paper to improve the accuracy of PLD. First, a parameter-optimized long short-term memory (LSTM) network is introduced to extract effective and robust features, which exploits a particle swarm optimization (PSO) algorithm with cross-entropy fitness function to search for globally optimal parameters. With this framework, the learning representation capability of the model is improved and the convergence rate is accelerated. Moreover, an anomaly-attention mechanism (AM) is proposed to discover class discriminative information by weighting the hidden states, which contributes to amplifying the normal-abnormal distinguishable discrepancy, further improving the accuracy of PLD. After that, the proposed PRAN not only implements the adaptive optimization of network parameters, but also enlarges the contribution of normal-abnormal discrepancy, thereby overcoming the drawbacks of instability and poor generalization. Finally, the experimental results demonstrate the effectiveness and superiority of the proposed PRAN for PLD.