Article
Automation & Control Systems
Louis Massucci, Fabien Lauer, Marion Gilson
Summary: This paper focuses on the identification analysis of switched linear systems using statistical learning theory, including the derivation of prediction error bounds and the proposal of a method for estimating the number of modes. The proposed method is inspired by the principle of structural risk minimization in model selection.
Article
Automation & Control Systems
Wentao Bai, Fan Guo, Lei Chen, Kuangrong Hao, Biao Huang
Summary: This article proposes a robust variational Bayesian algorithm for identifying piecewise autoregressive exogenous systems with time-varying time-delays. To mitigate the effects of outliers, a $t$-distribution is used to model the noise probability distribution. A solution strategy for accurately classifying undecidable data points is proposed, using support vector machines to determine the hyperplanes for data splitting. Maximum-likelihood estimation is employed for re-estimating unknown parameters based on the classification results. The time-delay is treated as a hidden variable and identified through the variational Bayesian algorithm. The effectiveness of the algorithm is demonstrated through two simulation examples.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Telecommunications
B. Mathivanan, P. Perumal
Summary: This paper presents a method for human gait recognition based on the ADBNN-BWO algorithm, which utilizes human walking style images to identify human emotions. The proposed method goes through four stages including pre-processing, feature extraction, feature selection, and classification. It successfully achieves human gait recognition and applies it to emotion recognition.
WIRELESS PERSONAL COMMUNICATIONS
(2022)
Article
Automation & Control Systems
Jinlong Yuan, Changzhi Wu, Chongyang Liu, Kok Lay Teo, Jun Xie
Summary: In this paper, a robust suboptimal feedback control problem is investigated for a nonlinear time-delayed switched system in a 1,3-propanediol microbial fed-batch process. The feedback control strategy based on radial basis function is designed to balance system performance and sensitivity. The problem is transformed into one subject only to box constraints using an exact penalty method and a novel time scaling transformation approach, and solved by a hybrid optimization algorithm. Numerical results demonstrate the effectiveness of the developed algorithm.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2023)
Article
Automation & Control Systems
Wenjie Ma, Bo Zhang, Dongyuan Qiu
Summary: This article proposes a single-loop control strategy for the four-level flying-capacitor converter using the switched system theory, which simplifies the control design and implementation by driving all voltages towards their desired values with a single control loop instead of using multiple individual controllers. The proposed control strategy also ensures the system's large-signal stability in a straightforward manner.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Computer Science, Artificial Intelligence
Baptiste Schubnel, Rafael E. Carrillo, Pierre-Jean Alet, Andreas Hutter
Summary: The presented method is a three-step approach based on data-driven techniques for system identification and optimal control of nonlinear systems, without the need for system excitation. It involves building simulation models, training neural networks on simulation outputs, and using reinforcement learning for optimal control. By combining these steps, stable functional controllers can be generated that outperform benchmark rule-based controllers.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Automation & Control Systems
Wenjie Ma, Bo Zhang
Summary: The introduction of the switched affine system opens new possibilities for the control design of dc-dc converters. However, existing methods suffer from nonlinear optimization problems and high computational resource requirements. This article proposes a new hybrid control scheme based on linear matrix inequality formulations, reducing the online computing burden and establishing a unified view with classical continuous-time switching schemes.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Engineering, Civil
Saharnaz Nazari, Hai Huang, Tong Qiu
Summary: This study utilizes statistical pattern recognition technique and data input from SmartRock sensors to develop a method for timely detection of ballast fouling. The method successfully distinguishes between different ballast conditions based on the data sets obtained. The study shows the potential suitability of this method for maintenance planning.
TRANSPORTATION GEOTECHNICS
(2022)
Article
Automation & Control Systems
Hongjuan Wu, Chuandong Li, Yinuo Wang, Hao Deng
Summary: In this article, a novel class of mathematical models for uncertain switched nonlinear systems with saturation constraints on control signals is proposed. The robust stability of the system is analyzed using Lyapunov stability theory, polytopic representation approach, matrix inequality, and Schur complement. Design of the hybrid control gains and optimization problems for larger estimation of the attraction domain are also investigated. Simulation results show the feasibility and effectiveness of the proposed methods.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Automation & Control Systems
Lijun Long, Fenglan Wang, Zhiyong Chen
Summary: This article focuses on the robust adaptive event-triggered control (ETC) problem for switched nonlinear systems. A novel robust adaptive controller is constructed based on a common virtual control Lyapunov function method and backstepping. The dynamic ETC (DETC) strategy is integrated into the switching controller to address the challenges caused by the interaction of switching and triggering instants. The proposed solution guarantees global asymptotic stability and exclusion of Zeno behavior for the closed-loop system, and is applicable to a larger class of switched nonlinear systems.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2023)
Article
Engineering, Electrical & Electronic
Xizheng Zhang, Zhangyu Lu, Xiaofang Yuan, Yaonan Wang, Xuejun Shen
Summary: The article introduces an innovative L2-ARC method for the voltage/current tracking control of a hybrid energy storage system in electric vehicles. By combining the IDA-PBC controller with the L2 gain disturbance attenuation technique, the method ensures stable control. It adopts an adaptive mechanism to estimate electrical parameters, achieving high performance and robust stability.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2021)
Article
Automation & Control Systems
Xiaodong Sun, Yefei Xiong, Ming Yao, Xingtao Tang
Summary: This article proposes a hybrid control strategy for switched reluctance motors (SRMs) based on the principle of dynamic coordination control. The proposed controller achieves a small torque ripple in a wide speed range by using different control methods in different modes.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Automation & Control Systems
Jinhao Liang, Yanbo Lu, Jiwei Feng, Guodong Yin, Weichao Zhuang, Jian Wu, Liwei Xu, Faan Wang
Summary: A novel driver-automation cooperative shared control system is proposed in this article to better cooperate with aggressive drivers. By introducing a driving activity parameter, the conflicts between aggressive drivers and ADAS can be mitigated. An H8 robust output-feedback control method is presented to provide robustness and stability of the polytope space.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Automation & Control Systems
Jinlong Yuan, Lei Wang, Jingang Zhai, Kok Lay Teo, Changjun Yu, Ming Huang, Jun Xie
Summary: This paper considers a nonlinear switched time-delayed (NSTD) system with an unknown time-varying function in a batch culture. The goal is to estimate unknown quantities using noisy output measurements and biological robustness. The estimation problem is formulated as a robust optimal control problem governed by the NSTD system with continuous state inequality constraints, and approximated using a sequence of nonlinear programming subproblems.
NONLINEAR ANALYSIS-HYBRID SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Yuchuan Ma, Qiao Wang, Min Ye, Gaoqi Lian
Summary: This paper proposes a robust controller to regulate the current of the hybrid energy system (HES) in order to adapt to the working conditions of pure electric construction machinery. The working principles and energy flow patterns of the HES are analyzed, and a robust control method is designed. An electric loader experiment platform is created to verify the effectiveness of the control method.
Article
Automation & Control Systems
Yue Cao, Nabil Magbool Jan, Biao Huang, Yalin Wang, Zhuofu Pan, Weihua Gui
Summary: The primary goal of multimodal process monitoring is to detect abnormalities or occurrence of faults. This paper proposes a Gaussian mixture model based variational Bayesian principal component analysis (GMM-VBPCA) method that combines global GMM and local VBPCA models to better characterize normal multimodal processes. The monitoring statistics of KL divergence and model residuals are used to detect fault occurrences.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Yu Hui, Ronghu Chi, Biao Huang, Zhongsheng Hou
Summary: This study addresses the challenges of heterogeneous dynamics, strongly non-linear and non-affine structures, and cooperation-antagonism networks in multi-agent systems output consensus. It introduces a heterogeneous linear data model and an adaptive learning consensus protocol to improve system performance effectively.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Automation & Control Systems
Chao Jiang, Yusheng Lu, Weimin Zhong, Biao Huang, Dayu Tan, Wenjiang Song, Feng Qian
Summary: Inferential modeling plays a significant role in estimating quality-related process variables in modern manufacturing. This article proposes a new nonlinear extension of probabilistic slow feature analysis (PSFA) under the deep learning framework to enhance dynamic feature extraction and improve prediction accuracy by incorporating variational inference and Monte Carlo inference. The proposed model considers the relevance of inputs with outputs to enhance prediction performance. The model is validated through an industrial hydrocracking process and achieves a significant reduction in root mean squared error compared to PSFA.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Atefeh Daemi, Bhushan Gopaluni, Biao Huang
Summary: In this article, we propose a novel transfer learning approach, called domain adversarial probabilistic principal component analysis (DAPPCA), to monitor processes with data from multiple distributions. DAPPCA automatically learns feature representations that are relevant across different operational modes and improves fault detection accuracy by transferring knowledge from previously known modes.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Jinxi Zhang, Fan Guo, Kuangrong Hao, Biao Huang, Lei Chen
Summary: In this article, a method is proposed for identifying an errors-in-variable system contaminated by heteroscedastic noise. A Markov chain is used to describe the correlation of the switching of the heteroscedastic noise model. A variational Bayesian algorithm is employed for estimating the model parameters. The effectiveness of the proposed method is demonstrated through simulated numerical examples and an experimental study on a polyester fiber process. Three performance indexes are used to evaluate the algorithm's performance and Monte Carlo cross validations are performed to demonstrate its effectiveness and superiority.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Yan Qin, Chau Yuen, Xunyuan Yin, Biao Huang
Summary: To address the data discrepancy across batteries, researchers propose a transferable multistage SOH estimation model that outperforms its competitors in various transfer tasks. By using stage information and an updating scheme to compensate for estimation errors, the model significantly improves estimation accuracy.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Xiuli Zhu, Seshu Kumar Damarla, Kuangrong Hao, Biao Huang, Hongtian Chen, Yicun Hua
Summary: The polymerization process is crucial in industry, but the lack of real-time measurement of quality variables poses challenges in monitoring and control. To address this, a novel multioutput soft sensor algorithm based on canonical correlation analysis (CCA) and deep learning techniques is proposed for estimating quality variables in the industrial polymerization process. The proposed soft sensor outperforms state-of-the-art machine learning algorithms in terms of prediction accuracy and offers advantages such as complex feature extraction, handling of overfitting, and quick estimations.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Automation & Control Systems
Wentao Bai, Fan Guo, Lei Chen, Kuangrong Hao, Biao Huang
Summary: This article proposes a robust variational Bayesian algorithm for identifying piecewise autoregressive exogenous systems with time-varying time-delays. To mitigate the effects of outliers, a $t$-distribution is used to model the noise probability distribution. A solution strategy for accurately classifying undecidable data points is proposed, using support vector machines to determine the hyperplanes for data splitting. Maximum-likelihood estimation is employed for re-estimating unknown parameters based on the classification results. The time-delay is treated as a hidden variable and identified through the variational Bayesian algorithm. The effectiveness of the algorithm is demonstrated through two simulation examples.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Automation & Control Systems
Huaying Li, Ronghu Chi, Zhongsheng Hou, Biao Huang
Summary: This article proposes a higher order indirect adaptive iterative learning control scheme for nonlinear nonaffine systems, which improves the control performance by using a P-type controller and iterative learning to update set points, and introduces an iterative dynamic linearization method to transform into a linear parametric learning controller.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Energy & Fuels
Stefan Jespersen, Zhenyu Yang, Dennis Severin Hansen, Mahsa Kashani, Biao Huang
Summary: To reduce the environmental impact of offshore oil and gas, stricter regulations on hydrocarbon discharge are being implemented. One approach to reducing oil discharge is by improving control systems through the introduction of new oil-in-water sensing technologies and advanced control methods. However, obtaining valid control-oriented models for de-oiling hydrocyclones has proven to be challenging, as existing models are often based on droplet trajectory analysis and do not account for the dynamics or require the measurement of droplet size distribution.
Article
Computer Science, Artificial Intelligence
Hongtian Chen, Hao Luo, Biao Huang, Bin Jiang, Okyay Kaynak
Summary: transfer learning has attracted attention as a new learning paradigm, and is used to develop fault diagnosis approaches for improving the safety and reliability of automation systems. This survey article provides a comprehensive review of transfer learning-motivated fault diagnosis methods and highlights open problems and potential research directions in this field. It also presents principles and a classification strategy for utilizing previous knowledge specifically for fault diagnosis tasks, aiming to contribute timely to transfer learning-motivated techniques in this area.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Pengyu Song, Chunhui Zhao, Biao Huang, Jinliang Ding
Summary: Industrial processes often exhibit both temporal and spatial dependencies due to dynamic changes and inter-variable coupling. However, existing methods struggle to effectively separate and represent these dependencies, leading to inaccurate fault detection and isolation. This study proposes a framework that utilizes a double-level separation method and an information aliasing loss function to explicitly represent and isolate temporal and spatial characteristics. By monitoring explicit statistics obtained from the separation modules, anomalies affecting different dependencies can be identified and located. Furthermore, a customized isolation strategy is introduced to accurately characterize and isolate anomalies in temporal and spatial characteristics. The proposed framework is validated through numerical examples and real-world processes.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Automation & Control Systems
Ronghu Chi, Wenzhi Cui, Na Lin, Zhongsheng Hou, Biao Huang
Summary: This work presents a new sampled-data model-free adaptive control approach for continuous-time systems. The approach utilizes the sampling period and past I/O data to enhance control performance. A sampled-data-based dynamical linearization model is established to address the nonlinearity and nonaffine structure of the continuous-time system. The proposed control approach is data-driven and overcomes the issues caused by model-dependence.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Huimin Zhang, Ronghu Chi, Biao Huang
Summary: A novel data-driven internal model learning control strategy is proposed for a nonlinear nonaffine system. The strategy reformulates the nonlinear plant into an iterative linear data model using an iterative dynamic linearization approach, and estimates the model parameters using only input-output data. The controller design is based on the inversion of the internal model using the equivalent feedback principle, achieving perfect tracking of the target output and compensating for uncertainties.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Automation & Control Systems
Wenxin Sun, Weili Xiong, Hongtian Chen, Ranjith Chiplunkar, Biao Huang
Summary: This study presents a novel regression modeling approach based on the CVAE framework to address the challenges of long-term prediction biases and reliability assessment in quality variable prediction. The method achieves multistep soft measurement prediction by simulating system state trajectories, and demonstrates lower prediction biases compared to traditional methods.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
