Machine Learning In Model Predictive Control Operational Safety And Cybersecurity

This book is focused on the development of rigorous, yet practical, methods for the design of advanced process control systems to improve process operational safety and cybersecurity for a wide range of nonlinear process systems. Process Operational Safety and Cybersecurity develops designs for novel model predictive control systems accounting for operational safety considerations, presents theoretical analysis on recursive feasibility and simultaneous closed-loop stability and safety, and discusses practical considerations including data-driven modeling of nonlinear processes, characterization of closed-loop stability regions and computational efficiency. The text then shifts focus to the design of integrated detection and model predictive control systems which improve process cybersecurity by efficiently detecting and mitigating the impact of intelligent cyber-attacks. The book explores several key areas relating to operational safety and cybersecurity including: machine-learning-based modeling of nonlinear dynamical systems for model predictive control; a framework for detection and resilient control of sensor cyber-attacks for nonlinear systems; insight into theoretical and practical issues associated with the design of control systems for process operational safety and cybersecurity; and a number of numerical simulations of chemical process examples and Aspen simulations of large-scale chemical process networks of industrial relevance. A basic knowledge of nonlinear system analysis, Lyapunov stability techniques, dynamic optimization, and machine-learning techniques will help readers to understand the methodologies proposed. The book is a valuable resource for academic researchers and graduate students pursuing research in this area as well as for process control engineers. Advances in Industrial Control reports and encourages the transfer of technology in control engineering. The rapid development of control technology has an impact on all areas of the control discipline. The series offers an opportunity for researchers to present an extended exposition of new work in all aspects of industrial control.

Big data is considered to play an important role in the fourth industrial revolution, which requires engineers and computers to fully utilize data to make smart decisions and improve the performance of industrial processes and of their control and safety systems. Traditionally, industrial process control systems rely on a (usually linear) data-driven model with parameters that are identified from industrial/simulation data, and in certain cases, for example, in profit-critical control loops, on first-principles models (with data-determined model parameters) that describe the underlying physico-chemical phenomena. However, modeling large-scale, complex nonlinear processes continues to be a major challenge in process systems engineering. Modeling is particularly important now and into the future, as process models are key elements of advanced model-based control systems, e.g., model predictive control (MPC) and economic MPC (EMPC). Due to the wide variety of applications, machine learning models have great potential, yet, the development of rigorous and systematic methods for incorporating machine learning techniques in nonlinear process control and operational safety is in its infancy. Traditionally, operational safety of chemical processes has been addressed through process design considerations and through a hierarchical, independent design of control and safety systems. However, the consistent accidents throughout chemical process plant history (including several high profile disasters in the last decade) have motivated researchers to design control systems that explicitly account for process operational safety considerations. In particular, a new design of control systems such as model predictive controllers (MPC) that incorporate safety considerations and can be coordinated with safety systems has the potential to significantly improve process operational safety and avoid unnecessary triggering of alarms systems, where machine learning techniques can be utilized to derive dynamic process models. However, the rigorous design of safety-based control systems poses new challenges that cannot be addressed with traditional process control methods, including, for example, proving simultaneous closed-loop stability and safety. On the other hand, cybersecurity has become increasingly important in chemical process industries in recent years as cyber-attacks that have grown in sophistication and frequency have become another leading cause of process safety incidents. While the traditional methods of handling cyber-attacks in control systems still rely partly on human analysis and mainly fall into the area of fault diagnosis, the intelligence of cyber-attacks and their accessibility to control system information has recently motivated researchers to develop cyber-attack detection and resilient operation control strategies to address directly cybersecurity concerns. Motivated by the above considerations, this dissertation presents the use of machine learning techniques in model predictive control, operational safety and cybersecurity for chemical processes described by nonlinear dynamic models. The motivation and organization of this dissertation are first presented. Then, the use of machine learning techniques to develop data-driven nonlinear dynamic process models to be used in model predictive controllers is presented, followed by the discussion of real-time implementation with online learning of machine leaning models and of physics-based machine learning modeling methods. Subsequently, the MPC and economic MPC schemes that use control Lyapunov-barrier functions (CLBF) are presented in detail with rigorous analysis provided on their closed-loop stability, operational safety and recursive feasibility properties. Next, the development of machine-learning-based CLBF-MPC schemes is presented with process stability and safety analysis. Finally, the development of an integrated detection and control system for process cybersecurity is developed, in which several types of intelligent cyber-attacks, machine learning detection methods and resilient control strategies are presented. Throughout the dissertation, the control methods are applied to numerical simulations of nonlinear chemical process examples to demonstrate their effectiveness and performance.

Nearly all our safety data collection and reporting systems are backwardlooking: incident reports; dashboards; compliance monitoring systems; and so on. This book shows how we can use safety data in a forward-looking, predictive sense. Predictive Safety Analytics: Reducing Risk through Modeling and Machine Learning contains real use cases where organizations have reduced incidents by employing predictive analytics to foresee and mitigate future risks. It discusses how Predictive Safety Analytics is an opportunity to break through the plateau problem where safety rate improvements have stagnated in many organizations. The book presents how the use of data, coupled with advanced analytical techniques, including machine learning, has become a proven and successful innovation. Emphasis is placed on how the book can “meet you where you are” by illuminating a path to get there, starting with simple data the organization likely already has. Highlights of the book are the real examples and case studies that will assist in generating thoughts and ideas for what might work for individual readers and how they can adapt the information to their particular situations. This book is written for professionals and researchers in system reliability, risk and safety assessment, quality control, operational managers in selected industries, data scientists, and ML engineers. Students taking courses in these areas will also find this book of interest to them.

Recent successes in the field of machine learning, as well as the availability of increased sensing and computational capabilities in modern control systems, have led to a growing interest in learning and data-driven control techniques. Model predictive control (MPC), as the prime methodology for constrained control, offers a significant opportunity to exploit the abundance of data in a reliable manner, particularly while taking safety constraints into account. This review aims at summarizing and categorizing previous research on learning-based MPC, i.e., the integration or combination of MPC with learning methods, for which we consider three main categories. Most of the research addresses learning for automatic improvement of the prediction model from recorded data. There is, however, also an increasing interest in techniques to infer the parameterization of the MPC controller, i.e., the cost and constraints, that lead to the best closed-loop performance. Finally, we discuss concepts that leverage MPC to augment learning-based controllers with constraint satisfaction properties.

This book presents the latest results on predictive control of networked systems, where communication constraints (e.g., network-induced delays and packet dropouts) and cyber attacks (e.g., deception attacks and denial-of-service attacks) are considered. For the former, it proposes several networked predictive control (NPC) methods based on input-output models and state-space models respectively. For the latter, it designs secure NPC schemes from the perspectives of information security and real-time control. Furthermore, it uses practical experiments to demonstrate the effectiveness and applicability of all the methods, bridging the gap between control theory and practical applications. The book is of interest to academic researchers, R&D engineers, and graduate students in control engineering, networked control systems and cyber-physical systems.

Machine learning boosts the capabilities of security solutions in the modern cyber environment. However, there are also security concerns associated with machine learning models and approaches: the vulnerability of machine learning models to adversarial attacks is a fatal flaw in the artificial intelligence technologies, and the privacy of the data used in the training and testing periods is also causing increasing concern among users. This book reviews the latest research in the area, including effective applications of machine learning methods in cybersecurity solutions and the urgent security risks related to the machine learning models. The book is divided into three parts: Cyber Security Based on Machine Learning; Security in Machine Learning Methods and Systems; and Security and Privacy in Outsourced Machine Learning. Addressing hot topics in cybersecurity and written by leading researchers in the field, the book features self-contained chapters to allow readers to select topics that are relevant to their needs. It is a valuable resource for all those interested in cybersecurity and robust machine learning, including graduate students and academic and industrial researchers, wanting to gain insights into cutting-edge research topics, as well as related tools and inspiring innovations.

Machine learning algorithms allow computers to learn without being explicitly programmed. Their application is now spreading to highly sophisticated tasks across multiple domains, such as medical diagnostics or fully autonomous vehicles. While this development holds great potential, it also raises new safety concerns, as machine learning has many specificities that make its behaviour prediction and assessment very different from that for explicitly programmed software systems. This book addresses the main safety concerns with regard to machine learning, including its susceptibility to environmental noise and adversarial attacks. Such vulnerabilities have become a major roadblock to the deployment of machine learning in safety-critical applications. The book presents up-to-date techniques for adversarial attacks, which are used to assess the vulnerabilities of machine learning models; formal verification, which is used to determine if a trained machine learning model is free of vulnerabilities; and adversarial training, which is used to enhance the training process and reduce vulnerabilities. The book aims to improve readers’ awareness of the potential safety issues regarding machine learning models. In addition, it includes up-to-date techniques for dealing with these issues, equipping readers with not only technical knowledge but also hands-on practical skills.

The performance of model predictive control (MPC) largely depends on the accuracy of the prediction model and of the constraints the system is subject to. However, obtaining an accurate knowledge of these elements might be expensive in terms of money and resources, if at all possible. In this thesis, we develop novel learning-based MPC frameworks that actively incentivize learning of the underlying system dynamics and of the constraints, while ensuring recursive feasibility, constraint satisfaction, and performance bounds for the closed-loop. In the first part, we focus on the case of inaccurate models, and analyze learning-based MPC schemes that include, in addition to the primary cost, a learning cost that aims at generating informative data by inducing excitation in the system. In particular, we first propose a nonlinear MPC framework that ensures desired performance bounds for the resulting closed-loop, and then we focus on linear systems subject to uncertain parameters and noisy output measurements. In order to ensure that the desired learning phase occurs in closed-loop operations, we then propose an MPC framework that is able to guarantee closed-loop learning of the controlled system. In the last part of the thesis, we investigate the scenario where the system is known but evolves in a partially unknown environment. In such a setup, we focus on a learning-based MPC scheme that incentivizes safe exploration if and only if this might yield to a performance improvement.

This book shows how machine learning (ML) methods can be used to enhance cyber security operations, including detection, modeling, monitoring as well as defense against threats to sensitive data and security systems. Filling an important gap between ML and cyber security communities, it discusses topics covering a wide range of modern and practical ML techniques, frameworks and tools.