Guest Editorial

Abstract

In modern industrial processes, aerospace systems, vehicle systems, and elsewhere there are increased demands for fuel efficiency, conservation of resources, cost and energy savings, and other optimal performance requirements. However, there is generally no dynamical model available for the process, or the process model is too complex to be tractable for controller design. Modelling and system identification are expensive and time-consuming, and models may be time-varying, or non-linear, or contain delays. The term ‘Data-driven Control’ (DDC) originated in the 1990s in Computer Science and it shares the same context as ‘big data’, ‘data mining’, and ‘data fusion’. On the other hand, Data-Based System Modelling, Monitoring, and Control are a set of topics used in the Control Systems community. The development of all these topics was driven by the huge amounts of data measured in complex process control systems, both stored historical data from prior measurements and on-line data available in real time during process runs. In these fields, the intent is to efficiently use the information in huge amounts of process input/output data to design predictors, controllers, and monitoring systems that provide guaranteed performance of the process. This Special Issue presents the latest developments on data-driven modelling and control, iterative learning control and reinforcement learning, and their applications in process industries. It contains eighteen papers, the contents of which are summarised below. A novel hybrid intelligent dynamic modelling approach is proposed by Tie et al. in their paper entitled ‘Hybrid intelligent modelling and simulation for cold tandem rolling process’. The approach combines a linearised state space model, a case-based reasoning multi models selection, a case attributes optimisation, an adaptive fractal filtering algorithm and a compensation model for the strip velocity. Shen et al. propose a model-independent approach for short-term electric load forecasting with guaranteed error convergence in their paper. The paper introduces the tracking control and Lyapunov stability theory into the load forecasting algorithm design. It can approximate the load dynamics inherent laws, without statistically learning from a certain forecasting model. Hu et al. develop a data-driven controller tuning scheme in their paper ‘Convergence performance oriented data-driven tuning method for parameterised controller design with cases investigation’. An iterative law based on the behaviour between the current parameter and the optimal parameter is proposed, which has the ability to directly seek the global optimal parameter. The paper entitled ‘MIMO system experimental validation of model-free control and virtual reference feedback tuning techniques’, by Precup et al., proposes three data-driven MIMO control system structures applied to the control of a representative non-linear MIMO system represented by the twin rotor aerodynamic system. Gao et al. address the adaptive and optimal control of a Quanser's 2-degree-of-freedom helicopter via output feedback in their paper ‘Sampled-data-based adaptive optimal output-feedback control of a 2-DOF helicopter’. The paper presents a policy iteration algorithm which yields to learn a near-optimal control gain iteratively by input/output data. The convergence is theoretically ensured and the trade-off between the optimality and the sampling period is rigorously studied as well. The authors show the performance of the proposed algorithm under bounded model uncertainties. A data-driven optimisation solution for operational index control to the selection of the set-points for a class of industrial processes is presented by Lu et al. in their paper ‘Data-driven optimal control of operational indices for a class of industrial processes’. A reinforcement learning actor-critic structure is employed to provide a data-driven optimisation. The effectiveness of the proposed method is demonstrated by experimental results carried out on a hardware-in-the-loop emulation system for a mineral grinding process. Mabrok et al. present a data-driven controller design algorithm for a class of systems where the plant satisfies the negative imaginary (NI) property in their paper ‘Controller synthesis for negative imaginary systems: a data driven approach’. In this approach, measured frequency response data of the plant is used to construct the controller frequency response at every frequency by minimising a cost function. Then, this controller response is used to identify the controller transfer function. The infinite horizon optimal control problem for a class of continuous-time systems is examined by Song et al. in their paper ‘Data-driven policy iteration algorithm for optimal control of continuous-time Itô stochastic systems with Markovian jumps’. The authors decompose the stochastic systems with Markovian jumps into N decoupled linear subsystems and a data-driven policy iteration algorithm is developed to learn the solutions and its convergence is proved. Chi et al. present a novel initial value dynamic compensation-based data-driven optimal terminal iterative learning control approach for non-linear systems under random initial conditions in their paper ‘Data-driven optimal terminal iterative learning control with initial value dynamic compensation’. The authors use a dynamical linearisation of the controlled non-linear system along the iteration direction to deduce the unknown influence on the terminal output caused by the initial states. It is estimated iteratively and incorporated into the learning control law. The paper by Wang et al. proposes an iterative tuning strategy for traffic network in their paper ‘Iterative tuning strategy for setting phase splits with anticipation of traffic demand in urban traffic network’. A decentralised data-driven method is used to fine-tune urban traffic signals iteratively by utilising historical and repetitive traffic demand. A novel hybrid Q-learning algorithm is introduced for the design of a linear adaptive optimal regulator for a large-scale interconnected system with event-sampled inputs and state vector by Narayanan et al. in their paper ‘Distributed adaptive optimal regulation of uncertain large-scale interconnected systems using hybrid Q-learning approach’. The time-driven Q-learning along with iterative parameter learning update is utilised within the event-sampled instants to obtain a more generalised online Q-learning framework. Xia et al. investigate the online reinforcement learning control in their paper entitled ‘Online reinforcement learning control by Bayesian inference’. It models the action value function as the latent variable of Gaussian process. Then an online approach is proposed to update the action value function by Bayesian inference and an efficient exploration strategy is presented. The optimal tracking of non-linear systems without knowing system dynamics is investigated by Zhu et al. in the paper ‘Using reinforcement learning techniques to solve continuous-time non-linear optimal tracking problem without system dynamics’. A model-free adaptive optimal tracking algorithm is proposed and it learns the optimal solution online in real time without any information of the system dynamics. Application of an improved data-driven model free adaptive constrained control for a solid oxide fuel cell is investigated by Xu et al. in their paper ‘An improved data-driven model free adaptive constrained control for a solid oxide fuel cell’. The authors give an overview of dynamic linearisation data-driven modelling and present a dynamic anti-windup compensator to deal with the move control input saturation. Application of the reagent dosages control on a flotation process is examined by Cao et al. in the paper ‘Reagent dosages control based on bubble size characteristics for flotation process’. The authors combine the distribution features of the bubble size, the estimation of the probability density function of the bubble size to propose a control method of reagent dosages based on bubble size characteristics. Adaptive CPS attack detection and reconstruction with application to power systems is addressed by Ao et al. This study investigates the problem of unexpected cyber-attack and its automatic recovery. As an illustration of attack detection and reconstruction, the results are applied to an IEEE 39 bus power system. Application of fractional order iterative learning controller for a type of batch bioreactor is investigated by Rezaei et al. The paper uses a parallel fractional order iterative learning controller (FOILC) along with a robust fractional order PID structure to achieve precise tracking and robustness against iterative, non-iterative and noises. Application of local learning-based model-free adaptive predictive control for adjustment of oxygen concentration in syngas manufacturing industry is reported by Liu et al. The online and offline I/O data in the database is utilised. It has been applied to the oxygen control problem in the syngas manufacturing industry. While the selected topics and papers are not a comprehensive representation of the area covered by this Special Issue, they do provide some recent advances in the field of Data-driven Control, and Data-Based System Modelling, Monitoring, and Control which could benefit current research in some way. We would like to thank all the authors who submitted their papers to this Special Issue and to reviewers for their timely and insightful review that have greatly helped improve the quality of the papers presented here. We also thank the Editor-in-Chief and the Editorial Office of IET Control Theory and Applications for their great support with this project, without which the completion of this work would not be possible. Jinliang Ding received the Ph.D. degree in Control Theory and Control Engineering from Northeastern University, Shenyang, China. He is currently a Professor with the State Key Laboratory of Synthetical Automation for Process Industry, Northeastern University. He is a senior member of IEEE. He is a technical committee member of IFAC Mining, Mineral and Metal Processing and IFAC Large Scale Complex Systems. He visited the Control Systems Centre, University of Manchester from April 2010 to March 2012. His research interests include data-based modelling, control and optimisation for the complex industrial systems, intelligent optimisation and applications. He has published more than 80 journal and international conference papers. One co-authored paper published on Control Engineering Practice was selected for the CEP Best Paper Award of 2011–2013. He received the National Technological Invention Award in 2013 and has twice received the first-prize in the Science and Technology Awards run by the Ministry of Education. He is also the inventor and co-inventor of 17 patents. Yong-duan Song received his Ph.D. degree in Electrical and Computer Engineering from Tennessee Technological University, Cookeville, USA, in 1992. He held a tenured Full Professor position with North Carolina A&T State University, Greensboro, from 1993 to 2008 and a Langley Distinguished Professor position with the National Institute of Aerospace, Hampton, VA, from 2005 to 2008. He is now the Dean of School of Automation, Chongqing University, China and the Founding Director of the Institute of Smart Systems and Renewable Energy, Chongqing University. He was one of the six Langley Distinguished Professors with the National Institute of Aerospace (NIA), and Founding Director of Cooperative Systems at NIA. He has served as an Associate Editor/Guest Editor for several prestigious scientific journals. Prof. Song has received several competitive research awards from the National Science Foundation, the National Aeronautics and Space Administration, the U.S. Air Force Office, the U.S. Army Research Office, and the U.S. Naval Research Office. His research interests include intelligent systems, guidance navigation and control, bio-inspired adaptive and cooperative systems, rail traffic control and safety, and smart grid. Tianyou Chai received the Ph.D. degree in Control Theory and Engineering in 1985 from Northeastern University, Shenyang, China, where he became a Professor in 1988. He is the founder and Director of the Center of Automation, which became a National Engineering and Technology Research Center and a State Key Laboratory. He is a member of the Chinese Academy of Engineering, an IFAC Fellow and IEEE Fellow, and Director of the Department of Information Science at the National Natural Science Foundation of China. His current research interests include modelling, control, optimisation and integrated automation of complex industrial processes. He has published 150 peer reviewed international journal papers. His paper titled ‘Hybrid intelligent control for optimal operation of shaft furnace roasting process’ was selected as one of three best papers for the Control Engineering Practice Paper Prize for 2011–2013. He has developed control technologies with applications to various industrial processes. For his contributions, he has won four prestigious awards of National Science and Technology Progress and National Technological Innovation, the 2007 Industry Award for Excellence in Transitional Control Research at the IEEE Multiple-conference on Systems and Control. S. Jagannathan, Fellow IEEE, Fellow IET, U.K. and Fellow U.K. Institute of Measurement and Control, is based at the Missouri University of Science and Technology (former University of Missouri-Rolla) where he is a Rutledge-Emerson Endowed Chair Professor of Electrical and Computer Engineering and Site Director for the NSF Industry/University Cooperative Research Center on Intelligent Maintenance Systems. He has co-authored 138 peer reviewed journal articles, most of them in IEEE Transactions, and 247 refereed IEEE conference articles, several book chapters, and six books. He holds 20 U.S. patents. He has supervised to graduation 23 doctoral and 29 Masters level students and his funding is in excess of $16 million from various US federal and industrial members. His research interests include neural network control, adaptive event-triggered control, secure networked control systems, prognostics, and autonomous systems/robotics. He was the co-editor for the IET book series on control from 2010 through 2013 and is now serving as the Editor-in-Chief for Discrete Dynamics and Society, and is on many editorial boards. He has received many awards and has been on organising committees of several IEEE Conferences. He served as the IEEE CSS Tech Committee Chair on Intelligent Control. F.L. Lewis is a Member of the National Academy of Inventors, a Fellow of IEEE, IFAC, and the U.K. Institute of Measurement and Control, a Professional Engineer (PE Texas), a U.K. Chartered Engineer, and Moncrief-O'Donnell Chair at the University of Texas at Arlington Research Institute. He is Qian Ren Thousand Talents Consulting Professor at Northeastern University, Shenyang, China. He obtained the Ph.D. at the Georgia Institute of Technology. He works in feedback control, intelligent systems, cooperative control systems, and non-linear systems. He is author of six U.S. patents, numerous journal special issues, 320 journal papers, and 20 books, including Optimal Control, Aircraft Control, Optimal Estimation, and Robot Manipulator Control which are used as university textbooks worldwide. He received the Fulbright Research Award, the NSF Research Initiation Grant, the ASEE Terman Award, the International Neural Network Society Gabor Award, the U.K. Institute of Measurement and Control Honeywell Field Engineering Medal, and the IEEE Computational Intelligence Society Neural Networks Pioneer Award. He received the Outstanding Service Award from Dallas IEEE Section, was selected as Engineer of the year by Ft. Worth IEEE Section, and received the Texas Regents Outstanding Teaching Award 2013. He is Distinguished Visiting Professor at Nanjing University of Science and Technology and Project 111 Professor at Northeastern University in Shenyang, China. He is a Founding Member of the Board of Governors of the Mediterranean Control Association.