International Journal of Adaptive Control and Signal Processing最新文献

筛选
英文 中文
Signal Quantization and Event-Triggered Trajectory Tracking for Multi-Constraint Control of Unmanned Surface Vehicle 无人水面飞行器多约束控制的信号量化与事件触发轨迹跟踪
IF 3.8 4区 计算机科学
International Journal of Adaptive Control and Signal Processing Pub Date : 2026-11-11 Epub Date: 2026-07-08 DOI: 10.1002/acs.70124
Xiangjie Cui, Wei Li, Jun Ning, Lu Liu
{"title":"Signal Quantization and Event-Triggered Trajectory Tracking for Multi-Constraint Control of Unmanned Surface Vehicle","authors":"Xiangjie Cui,&nbsp;Wei Li,&nbsp;Jun Ning,&nbsp;Lu Liu","doi":"10.1002/acs.70124","DOIUrl":"https://doi.org/10.1002/acs.70124","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper addresses the adaptive trajectory tracking control problem for unmanned surface vehicle (USV) operating under challenging conditions, including thruster saturation, unknown dynamics, state constraints, and unavailable velocity measurements. An adaptive quantized feedback control strategy based on a neural network observer is proposed. To address the challenge of limited maritime communication resources, a signal quantization and event-triggered mechanism was introduced. The input quantization process is described by a linear analytical model. A neural network observer is designed to estimate the unavailable velocity states. Neural networks are employed to approximate the unknown system dynamics, and a low-frequency gain learning method is introduced to effectively suppress control signal chattering induced by external disturbances. A dynamic auxiliary system is designed to compensate for the effects of thruster saturation. Furthermore, a constraint-handling mechanism based on a logarithmic barrier function is incorporated to ensure that all state variables remain strictly within the prescribed safe boundaries. Rigorous stability analysis of the resulting closed-loop system is conducted based on Lyapunov stability theory. Comprehensive simulation studies validate the effectiveness of the proposed control strategy.</p>\u0000 </div>","PeriodicalId":50347,"journal":{"name":"International Journal of Adaptive Control and Signal Processing","volume":"40 11","pages":"2142-2159"},"PeriodicalIF":3.8,"publicationDate":"2026-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149384599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Proportional Integral Observer-Based Secured Resilient Control for Nonlinear Semi-Markov Jump Cyber-Physical Systems Under Multiple Cyberattacks 基于比例积分观测器的非线性半马尔可夫跳变网络物理系统安全弹性控制
IF 3.8 4区 计算机科学
International Journal of Adaptive Control and Signal Processing Pub Date : 2026-11-11 Epub Date: 2026-07-18 DOI: 10.1002/acs.70128
V. Panneerselvam, S. Sweetha, R. Sakthivel, Y. Lim
{"title":"Proportional Integral Observer-Based Secured Resilient Control for Nonlinear Semi-Markov Jump Cyber-Physical Systems Under Multiple Cyberattacks","authors":"V. Panneerselvam,&nbsp;S. Sweetha,&nbsp;R. Sakthivel,&nbsp;Y. Lim","doi":"10.1002/acs.70128","DOIUrl":"https://doi.org/10.1002/acs.70128","url":null,"abstract":"<div>\u0000 \u0000 <p>This research focuses on the state estimation based stabilization of nonlinear semi-Markov jump cyber-physical systems that are exposed to external disturbances, multiple cyberattacks, time-varying delay and gain fluctuations. A proportional integral observer is constructed to reconstruct the immeasurable system states. The stabilization issue is addressed through the design of an appropriate resilient control that can withstand multiple cyberattacks, namely denial-of-service and deception attacks. In particular, the occurrence of multiple cyberattacks is characterized by two independent Bernoulli-distributed random variables. Moreover, a mode dependent Lyapunov–Krasovskii functional is employed along with integral inequalities to derive a set of sufficient conditions in the form of linear matrix inequalities, which ensures stochastic stability and <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>(</mo>\u0000 <msub>\u0000 <mrow>\u0000 <mover>\u0000 <mrow>\u0000 <mi>Q</mi>\u0000 </mrow>\u0000 <mo>˜</mo>\u0000 </mover>\u0000 </mrow>\u0000 <mrow>\u0000 <mi>w</mi>\u0000 </mrow>\u0000 </msub>\u0000 <mo>,</mo>\u0000 <msub>\u0000 <mrow>\u0000 <mover>\u0000 <mrow>\u0000 <mi>S</mi>\u0000 </mrow>\u0000 <mo>˜</mo>\u0000 </mover>\u0000 </mrow>\u0000 <mrow>\u0000 <mi>w</mi>\u0000 </mrow>\u0000 </msub>\u0000 <mo>,</mo>\u0000 <msub>\u0000 <mrow>\u0000 <mover>\u0000 <mrow>\u0000 <mi>R</mi>\u0000 </mrow>\u0000 <mo>˜</mo>\u0000 </mover>\u0000 </mrow>\u0000 <mrow>\u0000 <mi>w</mi>\u0000 </mrow>\u0000 </msub>\u0000 <mo>)</mo>\u0000 </mrow>\u0000 <annotation>$$ left({tilde{Q}}_w,{tilde{S}}_w,{tilde{R}}_wright) $$</annotation>\u0000 </semantics></math>-<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>γ</mi>\u0000 </mrow>\u0000 <annotation>$$ gamma $$</annotation>\u0000 </semantics></math> dissipativity of the addressed system regardless of multiple cyberattacks. Subsequently, the resulting conditions are solved to compute the values of the observer and controller gain matrices. Eventually, two numerical examples are provided to validate the theoretical outcomes.</p>\u0000 </div>","PeriodicalId":50347,"journal":{"name":"International Journal of Adaptive Control and Signal Processing","volume":"40 11","pages":"2208-2221"},"PeriodicalIF":3.8,"publicationDate":"2026-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149384687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Stochastic Attitude Controller With Sensor Delay and Input Saturation: A Neural-Adaptive Nonlinear Approach on 𝕊 𝕆 ( 3 ) 具有传感器延迟和输入饱和的随机姿态控制器:一种基于<s:2>的神经自适应非线性方法(3)
IF 3.8 4区 计算机科学
International Journal of Adaptive Control and Signal Processing Pub Date : 2026-11-11 Epub Date: 2026-07-07 DOI: 10.1002/acs.70121
Yaolei Wang, Guoliang Wei, Wangyan Li
{"title":"Stochastic Attitude Controller With Sensor Delay and Input Saturation: A Neural-Adaptive Nonlinear Approach on \u0000 \u0000 𝕊\u0000 𝕆\u0000 (\u0000 3\u0000 )","authors":"Yaolei Wang,&nbsp;Guoliang Wei,&nbsp;Wangyan Li","doi":"10.1002/acs.70121","DOIUrl":"https://doi.org/10.1002/acs.70121","url":null,"abstract":"<div>\u0000 \u0000 <p>In this work, a novel neural-adaptive nonlinear delay stochastic filter is designed to address the attitude estimation problem. This filter is represented using the special orthogonal group <span></span><math>\u0000 <mrow>\u0000 <mi>𝕊</mi>\u0000 <mi>𝕆</mi>\u0000 <mo>(</mo>\u0000 <mn>3</mn>\u0000 <mo>)</mo>\u0000 </mrow></math>, and employs low-cost sensors' units. Specifically, the Brownian motion is introduced to characterize the noise that maps the system dynamics to stochastic differential equations (SDEs), ensuring that the attitude estimation problem can be analyzed in a stochastic sense. Neural networks (NNs) are employed to design an attitude filter that accounts for sensor measurement delay and noise by incorporating a Lyapunov function. Then, based on the stochastic attitude filter, a novel controller for attitude tracking with unknown input saturation is proposed. The saturation characteristic of the input signal is approximated by a function that is smooth and not directly dependent on the control input. The proposed stochastic filter-based controller ensures that the closed-loop system is almost semi-globally uniformly ultimately bounded (SGUUB) in the mean square sense. Finally, simulations are conducted to verify the efficiency of the proposed attitude filter.</p>\u0000 </div>","PeriodicalId":50347,"journal":{"name":"International Journal of Adaptive Control and Signal Processing","volume":"40 11","pages":"2114-2129"},"PeriodicalIF":3.8,"publicationDate":"2026-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149384695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An Intermediate Observer-Based Fault Estimation for Lipschitz Nonlinear Multi-Agent Systems Subject to Switching Topologies 基于中间观测器的切换拓扑Lipschitz非线性多智能体系统故障估计
IF 3.8 4区 计算机科学
International Journal of Adaptive Control and Signal Processing Pub Date : 2026-11-11 Epub Date: 2026-07-13 DOI: 10.1002/acs.70127
Dong Yan, Chunsong Han, Ling Zhu, Tengyu Ma, Jiafeng Yu
{"title":"An Intermediate Observer-Based Fault Estimation for Lipschitz Nonlinear Multi-Agent Systems Subject to Switching Topologies","authors":"Dong Yan,&nbsp;Chunsong Han,&nbsp;Ling Zhu,&nbsp;Tengyu Ma,&nbsp;Jiafeng Yu","doi":"10.1002/acs.70127","DOIUrl":"https://doi.org/10.1002/acs.70127","url":null,"abstract":"<div>\u0000 \u0000 <p>Multi-agent systems operating in complex environments face challenges such as topology switching, nonlinear dynamics, multiple faults, and external disturbances. Traditional fault estimation methods often rely on strict observer matching conditions and exhibit poor adaptability to topology changes, leading to reduced estimation accuracy. To overcome these issues, this paper proposes a fault estimation algorithm based on an intermediate observer by leveraging the average dwell-time technique and <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mrow>\u0000 <mi>H</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mi>∞</mi>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {H}_{infty } $$</annotation>\u0000 </semantics></math> theory. First, an intermediate observer is designed by constructing an augmented state vector. An intermediate auxiliary variable is introduced using relative output estimation errors to eliminate the matching condition constraint. Second, the average dwell-time technique is applied to analyze the stability conditions of the system under topology switching, and a minimum dwell-time threshold is derived. Moreover, the <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mrow>\u0000 <mi>H</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mi>∞</mi>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {H}_{infty } $$</annotation>\u0000 </semantics></math> performance criterion is incorporated into the observer gain design to suppress external disturbances and enhance the system's disturbance rejection capability. Finally, simulation results demonstrate that the proposed method achieves accurate fault estimation in the presence of switching topologies, nonlinearities, multiple faults, and external disturbances.</p>\u0000 </div>","PeriodicalId":50347,"journal":{"name":"International Journal of Adaptive Control and Signal Processing","volume":"40 11","pages":"2177-2189"},"PeriodicalIF":3.8,"publicationDate":"2026-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149384607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Observer-Based Adaptive Event-Triggered Tracking Control for Fuzzy TS Systems With Premise Mismatch 前提不匹配模糊TS系统的观测器自适应事件触发跟踪控制
IF 3.8 4区 计算机科学
International Journal of Adaptive Control and Signal Processing Pub Date : 2026-11-11 Epub Date: 2026-07-09 DOI: 10.1002/acs.70125
Oussama Djadane, Salama Makni, Mourad Kchaou, Ahmed El Hajjaji
{"title":"Observer-Based Adaptive Event-Triggered Tracking Control for Fuzzy TS Systems With Premise Mismatch","authors":"Oussama Djadane,&nbsp;Salama Makni,&nbsp;Mourad Kchaou,&nbsp;Ahmed El Hajjaji","doi":"10.1002/acs.70125","DOIUrl":"https://doi.org/10.1002/acs.70125","url":null,"abstract":"<p>This paper addresses the challenge of designing an observer-based event-triggered controller for Takagi-Sugeno (TS) fuzzy nonlinear systems subject to network-induced delay and input amplitude boundaries for reference model trajectory tracking. The proposed event-triggered scheme uses the logistic function to adapt its threshold in order to alleviate the burden on the communication network and to reduce computing and energy resource consumption. The mismatch of premise variables (PVs) is dealt with in a way that reduces the number of design conditions and decision variables. The analysis and design of the observer-based tracking control problem are formulated as a convex optimization problem under Linear Matrix Inequality (LMI) conditions. A hybrid strategy that employs LMIs tools jointly with the Secretary Bird Optimization Algorithm (SBOA) is then proposed for optimal gain design. Finally, numerical simulations illustrate the effectiveness of the proposed approach.</p>","PeriodicalId":50347,"journal":{"name":"International Journal of Adaptive Control and Signal Processing","volume":"40 11","pages":"2160-2176"},"PeriodicalIF":3.8,"publicationDate":"2026-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/acs.70125","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149384674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An Adaptive Flow Compensation Algorithm for Hydraulic Loopers Based on Servo Valve Current Control of Hydraulic Cylinders 基于伺服阀电流控制的液压活套自适应流量补偿算法
IF 3.8 4区 计算机科学
International Journal of Adaptive Control and Signal Processing Pub Date : 2026-11-11 Epub Date: 2026-07-22 DOI: 10.1002/acs.70130
Shengyue Zong, Shuying Sun, Jinyan Li
{"title":"An Adaptive Flow Compensation Algorithm for Hydraulic Loopers Based on Servo Valve Current Control of Hydraulic Cylinders","authors":"Shengyue Zong,&nbsp;Shuying Sun,&nbsp;Jinyan Li","doi":"10.1002/acs.70130","DOIUrl":"https://doi.org/10.1002/acs.70130","url":null,"abstract":"<div>\u0000 \u0000 <p>In the hot rolling process, the hydraulic looper device is the key actuator that maintains the dynamic stability of strip tension between stands. Its flow compensation strategy plays a critical role in mitigating tension fluctuations and enhancing control accuracy. To overcome the limitations of conventional hydraulic looper flow compensation methods that rely on empirical parameters and are unsuited to dynamic rolling environments, this paper proposes an adaptive flow compensation algorithm based on servo valve current control for hydraulic cylinders. Initially, a comprehensive model of the hydraulic looper system is developed, encompassing both a servo valve-hydraulic cylinder sub-model and an overall looper system model. This integrated model is then used to perform theoretical calculations of the flow compensation value. Subsequently, to address the impact of varying system parameters due to operational conditions and environmental disturbances, a state-space model is formulated, and a Kalman filtering technique is employed for real-time system state estimation and flow compensation prediction. This approach facilitates the adaptive regulation of the servo valve current. Experimental results demonstrate that the proposed method effectively suppresses strip tension fluctuations and significantly enhances the system's dynamic response and disturbance rejection capabilities.</p>\u0000 </div>","PeriodicalId":50347,"journal":{"name":"International Journal of Adaptive Control and Signal Processing","volume":"40 11","pages":"2222-2234"},"PeriodicalIF":3.8,"publicationDate":"2026-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149384703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Dynamic Event-Triggered Fixed-Time Consensus Control for High-Order Multi-Agent Systems 高阶多智能体系统的动态事件触发固定时间一致性控制
IF 3.8 4区 计算机科学
International Journal of Adaptive Control and Signal Processing Pub Date : 2026-11-11 Epub Date: 2026-07-28 DOI: 10.1002/acs.70133
Jing Sun, Shengping Luo
{"title":"Dynamic Event-Triggered Fixed-Time Consensus Control for High-Order Multi-Agent Systems","authors":"Jing Sun,&nbsp;Shengping Luo","doi":"10.1002/acs.70133","DOIUrl":"https://doi.org/10.1002/acs.70133","url":null,"abstract":"<div>\u0000 \u0000 <p>This article investigates the consensus control problem in multi-agent systems (MASs) and proposes a fixed-time dynamic event-triggered consensus control (FxTDETC) scheme. Based solely on the assumption that each agent is controllable, rather than relying on the full-row-rank condition of the input matrix <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>B</mi>\u0000 </mrow>\u0000 <annotation>$$ B $$</annotation>\u0000 </semantics></math>, a fixed-time state observer (FxTSO) is used to estimate the leader's state more rapidly. The FxTDETC scheme introduces a dynamic event-triggered (DET) mechanism, reducing the number of controller updates and thereby conserving system energy. Furthermore, the proposed protocol ensures consensus within a finite time and provides an upper bound on the convergence time that is independent of the initial conditions. Finally, the effectiveness of the proposed FxTDETC scheme is validated through numerical simulations.</p>\u0000 </div>","PeriodicalId":50347,"journal":{"name":"International Journal of Adaptive Control and Signal Processing","volume":"40 11","pages":"2245-2258"},"PeriodicalIF":3.8,"publicationDate":"2026-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149384641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Handling Uncertainty in Semi-Batch Process Via Extremum-Seeking and Extended State Observer 利用极值寻求和扩展状态观测器处理半批过程中的不确定性
IF 3.8 4区 计算机科学
International Journal of Adaptive Control and Signal Processing Pub Date : 2026-11-11 Epub Date: 2026-07-14 DOI: 10.1002/acs.70126
Jinggao Sun, Daoshuai Jiao, Chenghu Ge, Huaicheng Yan
{"title":"Handling Uncertainty in Semi-Batch Process Via Extremum-Seeking and Extended State Observer","authors":"Jinggao Sun,&nbsp;Daoshuai Jiao,&nbsp;Chenghu Ge,&nbsp;Huaicheng Yan","doi":"10.1002/acs.70126","DOIUrl":"https://doi.org/10.1002/acs.70126","url":null,"abstract":"<div>\u0000 \u0000 <p>Semi-batch polymerization is a crucial industrial chemical process. Due to the inherent uncertainties in model parameters and external disturbances affecting the system, achieving robust control performance is challenging. Enthalpy, a time-invariant yet uncertain parameter, varies from its nominal value across different batches and is not precisely known. This article addresses the estimation problem by converting it into a convex optimization problem and employing time-varying extremum-seeking control to solve it. Using the estimated enthalpy and chemical reaction rate, backstepping control is applied to track the reactor temperature to its setpoint. To mitigate external disturbances arising from fluctuations in feed and inlet coolant temperature, extended state observer based estimators are designed to compute the unknown terms associated with uncertainties. These terms are subsequently utilized in the backstepping controller to reduce the impact of external disturbances. Numerical simulations demonstrate the effectiveness of the proposed control scheme in the semi-batch polymerization process.</p>\u0000 </div>","PeriodicalId":50347,"journal":{"name":"International Journal of Adaptive Control and Signal Processing","volume":"40 11","pages":"2190-2207"},"PeriodicalIF":3.8,"publicationDate":"2026-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149384608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Bayesian-Optimized GRU Network With WMD-EFAST Self-Organizing Mechanism for Multimodal Atmospheric Pollutant Prediction 基于WMD-EFAST自组织机制的多模态大气污染物预测贝叶斯优化GRU网络
IF 3.8 4区 计算机科学
International Journal of Adaptive Control and Signal Processing Pub Date : 2026-11-11 Epub Date: 2026-07-29 DOI: 10.1002/acs.70131
Yuxin Jia, Nan Guo, |Tiewei Shang, Wenlu Li, Yueyang Sun, Junfei Qiao
{"title":"A Bayesian-Optimized GRU Network With WMD-EFAST Self-Organizing Mechanism for Multimodal Atmospheric Pollutant Prediction","authors":"Yuxin Jia,&nbsp;Nan Guo,&nbsp;|Tiewei Shang,&nbsp;Wenlu Li,&nbsp;Yueyang Sun,&nbsp;Junfei Qiao","doi":"10.1002/acs.70131","DOIUrl":"https://doi.org/10.1002/acs.70131","url":null,"abstract":"<div>\u0000 \u0000 <p>Atmospheric pollutant concentration prediction is a critical component of environmental governance. Deep learning-based methods now dominate this prediction field, yet current deep learning models still face several challenges: inefficient hyperparameter optimization leading to high training costs, static network structures struggling to adapt to the nonlinear spatiotemporal coupling between pollutant concentrations and meteorological factors, and these limitations consequently causing performance fluctuations in cross-timescale predictions. To address these challenges, this paper proposes a Bayesian-optimized self-organizing gated recurrent unit (BO-SOGRU) model, achieving dual synergy between Bayesian optimization and dynamic self-organizing mechanisms. First, a hyperparameter self-configuration mechanism is constructed within the Bayesian optimization framework, where a Gaussian process surrogate model performs global optimal search for key parameters, significantly improving hyperparameter optimization efficiency. Second, a dynamic self-organizing mechanism is designed, employing Weighted Minkowski Distance (WMD) to measure neuron similarity and integrating the Extended Fourier Amplitude Sensitivity Test (EFAST) to dynamically evaluate neuron contributions, thereby enabling adaptive network structure optimization. Convergence analysis verifies the algorithm's stability and feasibility. Experiments were conducted on two benchmark datasets and real-world pollutant concentration prediction tasks across multiple time scales, and the prediction accuracy was calculated. Compared with other models of the same type, BO-SOGRU has significant advantages in prediction accuracy and model compactness.</p>\u0000 </div>","PeriodicalId":50347,"journal":{"name":"International Journal of Adaptive Control and Signal Processing","volume":"40 11","pages":"2259-2273"},"PeriodicalIF":3.8,"publicationDate":"2026-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149384579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Event-Triggered Adaptive Neural Networks Fault-Tolerant Control for Nonlinear Multi-Agent Systems With Sensor Faults 具有传感器故障的非线性多智能体系统的事件触发自适应神经网络容错控制
IF 3.8 4区 计算机科学
International Journal of Adaptive Control and Signal Processing Pub Date : 2026-11-11 Epub Date: 2026-07-23 DOI: 10.1002/acs.70129
Guowei Dong, Wenhua You, Kewen Li, Wenshuai Lin
{"title":"Event-Triggered Adaptive Neural Networks Fault-Tolerant Control for Nonlinear Multi-Agent Systems With Sensor Faults","authors":"Guowei Dong,&nbsp;Wenhua You,&nbsp;Kewen Li,&nbsp;Wenshuai Lin","doi":"10.1002/acs.70129","DOIUrl":"https://doi.org/10.1002/acs.70129","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper designs a novel adaptive neural networks (NNs) event-triggered fault-tolerant control scheme, which can effectively address the impacts of sensor faults and unknown external disturbances on non-strict feedback multi-agent systems (MASs). First, the radial basis function (RBF) NNs are employed to reconstruct the sensor faults for mitigating its adverse effects on the system. Second, compared with the conventional disturbance scaling method, the external disturbance observer is constructed to accurately eliminate the adverse effects induced by external disturbances. Third, a novel dynamic event-triggered switching threshold strategy (DETSTS) is proposed to efficiently balance the diverse requirements of trigger conditions in different environments. The designed controller ensures that all signals in the closed-loop system are semi-globally, uniformly, ultimately bounded (SGUUB). Finally, simulation results verify the effectiveness of the proposed strategy.</p>\u0000 </div>","PeriodicalId":50347,"journal":{"name":"International Journal of Adaptive Control and Signal Processing","volume":"40 11","pages":"2235-2244"},"PeriodicalIF":3.8,"publicationDate":"2026-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149384625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书