This thesis consists of four chapters including two main contributions on the application of machine learning and artificial intelligence on process modeling and controller design. Chapter 2 will talk about applying AI to controller design. This chapter proposes and implements a novel reinforcement learning (RL)--based controller design on chemical engineering examples. To address the issue of costly and unsafe training of model-free RL-based controllers, we propose an implementable RL-based controller design that leverages offline MPC calculations, that have already developed based on a step-response model. In this method, a RL agent is trained to imitate the MPC performance. Then, the trained agent is utilized in a model-free RL framework to interact with the actual process so as to continuously learn and optimize its performance under a safe operating range of processes. This contribution is marked as the first implementable RL-based controller for practical industrial application. Chapter 3 will focus on AI applications in process modeling. As nonlinear dynamics are widely encountered and challenging to simulate, nonlinear MPC (NMPC) is recognized as a promising tool to tackle this challenge. However, the lack of a reliable nonlinear model remains a roadblock for this technique. To address this issue, we develop a novel data-driven modeling method that utilizes the nonlinear autoencoder, to result in a modeling technique where the nonlinearity in the model stems from the analysis of the measured variables. Moreover, a quadratic program (QP) based MPC is developed based on this model, by utilizing an autoencoder as a transformer between the controller and process. This work contributes as an extension of the classic Koopman operator modeling method and a remarkable linear MPC design that can outperform other NMPCs such as neural network-based MPC. / Thesis / Master of Applied Science (MASc)

Traditional generators have been decommissioned or replaced by renewable energy generation due to utility long-standing goals. However, instead of flattening the entire plant, the rotating mass of generator can be utilized as a storage unit (inertia resource) to mitigate the frequency swings during transient caused by the renewables. The goal of this work is to design a control strategy utilizing the decommissioned generator interfaced with power grid via a back-to-back converter to provide inertia support. This is referred to as decoupled synchronous machine system (DSMS). On top of that, the grid-side converter is capable of providing reactive power as an auxiliary voltage controller. However, in a practical setting, for power utilities, the detailed state equations of such device as well as the complicated nonlinear power system are usually unobtainable making the controller design a challenging problem. Therefore, a model free, purely data-driven strategy for the nonlinear controller design using Koopman operator-based framework is proposed. Besides, the time delay embedding technique is adopted together with Koopman operator theory for the nonlinear system identification. Koopman operator provides a linear representation of the system and thereby the classical linear control algorithms can be applied. In this work, model predictive control is adopted to cope with the constraints of the control signals. The effectiveness and robustness of the proposed system are demonstrated in Kundur two-area system and IEEE 39-bus system. / Doctor of Philosophy / Power system is facing an energy transformation from the traditional fuel to sustainable renewable such as solar, wind and so on. Unlike the traditional fuel energized generators, the renewable has very little inertia to maintain frequency stability. Therefore, this work proposes a new system referred to as decoupled synchronous machine system (DSMS) to support the grid frequency. DSMS consists of the rotating mass of generator and a back-to-back converter which can be utilized as an inertia resource to mitigate the frequency oscillations. In addition, the grid-side converter can provide reactive power to improve voltage performance during faults. This work aims to design a control strategy utilizing DSMS to support grid frequency and voltage. However, an explicit mathematical model of such device is unobtainable in a practical setting making data-driven control the only option. A data-driven technique which is Koopman operator-based framework together with time delay embedding algorithm is proposed to obtain a linear representation of the system. The effectiveness and robustness of the proposed system are demonstrated in Kundur two-area system and IEEE 39-bus system.

The Frobenius-Perron operator acting on integrable functions and the Koopman operator acting on essentially bounded functions for a given nonsingular transformation on the unit interval can be shown to have cyclic spectrum by referring to the theory of lattice homomorphisms on a Banach lattice. In this paper, it is verified directly that the peripheral point spectrum of the Frobenius-Perron operator and the point spectrum of the Koopman operator are fully cyclic. Under some restrictions on the underlying transformation, the Frobenius-Perron operator is known to be a well defined linear operator on the Banach space of functions of bounded variation. It is also shown that the peripheral point spectrum of the Frobenius-Perron operator on the functions of bounded variation is fully cyclic.

Au niveau atomique, le contrôle de spins est un objectif primordial en physique quantique. Malheureusement la présence de bruits gêne ce dernier. Le but est de trouver les conditions à imposer à l’environnement pour que le contrôle ne soit pas perturbé par le bruit. L’étude d’une chaîne de spins caractérisée par trois couplages : interactions d’Heisenberg, d’Ising-Z et d’Ising-X, évoluant librement est prise comme référence. Nous observons que l’interaction d’Heisenberg correspond à un couplage isotrope. Celle d’Ising-Z conserve l’ordre dans la chaîne tandis que celle d’Ising-X est très désordonnée. Nous rendons le système plus complexe en ajoutant du contrôle et en analysant le comportement adiabatique d’un système quantique. Ce dernier est composé d’un système et d’un environnement, dont le couplage est perturbatif. Trois régimes adiabatiques ont été mis en évidence. Des formules permettant d’obtenir la fonction d'onde au cours du temps ont alors été établies pour ces trois régimes. Cependant, dans la pratique, les systèmes quantiques ne sont en aucun cas isolés. L’interaction avec leur environnement peut entraîner des comportements plus complexes, rendant le contrôle très difficile. Nous avons alors étudié des systèmes de spins, couplés ou non, frappés par des trains d’impulsions magnétiques ultracourtes. Ces trains traversent un environnement classique (stationnaire, de dérive linéaire, Markovien, microcanonique) modifiant la force et le retard de chaque impulsion. La modification des trains par l’environnement classique est une des sources du désordre dans le système de spins. Ce désordre est transmis entre les spins par le couplage. Dans cette étude nous n’arrivons pas à contrôler le système lorsque les trains sont en présence des environnements précédents. Pour palier à ce problème, nous imposons aux impulsions magnétiques de traverser un environnement chaotique. Avant un temps t, appelé horizon de cohérence, le système couplé par une interaction d’Heisenberg et soumis à un environnement chaotique reste cohérent alors qu’après, la population et la cohérence d'un spin et du spin moyen du système tendent à se rapprocher de la distribution microcanonique. Pendant cet horizon, il est possible de réaliser du contrôle quantique soit par contrôle total (contrôle du système à chaque instant), soit par transmission d’information. Cette étude nous a permis de déterminer une formule empirique de l’horizon de cohérence. Finalement, nous nous sommes attachés à trouver une formule plus formelle de cet horizon. / At an atomic level, the spin control is an essential aim in quantum physics. Unfortunately, the presence of noises disturbs this last. The goal is to find the conditions which we have to impose to the environment in order that the control is not disturbed by the noise. The study of a spin chain characterized by three couplings (Heisenberg, Ising-Z and Ising-X interactions) freely evolving is taken as reference. We observe that the Heisenberg interaction corresponds to an isotropic coupling. The Ising-Z one conserves the order into the chain whereas the Ising-X one is really disordered. We consider a more complex quantum system by adding some control and analyzing its adiabatic behavior. This last is composed by a system and an environment, for which the coupling is perturbative. Three adiabatic regimes have been highlighted. Some formulas allowing to obtain the wave function across the time have been established for these three regimes. However, in practice, quantum systems are not isolated. The interaction with their environment can lead to more complex behaviors, driving the control more difficult. We have studied spin systems, coupled or not, kicked by some ultrashort magnetic pulse trains. These trains cross a classical environment (stationary, drift, Markovian, microcanonical) modifying the strength and the delay of each pulse. The modification of the trains by the environment is one of the sources of the disorder into the spin system. This disorder is transmitted between the spins by the coupling. In this study we do not succeed in controlling the system when the trains are in the presence of the previous environments. To remedy this situation, we force the magnetic pulses to cross a chaotic environment. Before a time t, called horizon of coherence, the system coupled by an Heisenberg interaction and submitted to a chaotic environment remains coherent whereas after, the population and the coherence of one spin and of the average spin of the system tend to go near the microcanonical distribution. During this horizon, it is possible to realize some quantum control either by total control (control of the system at every instants) or by information transmission. This study allows us to determine an empirical formula of the horizon of coherence. Finally, we have tried to find a more formal approach for this horizon.

<p>Every engineered system behaves slightly differently because of manufacturing and operational uncertainties. The ability to build system-specific predictive models that adapt to manufactured systems, also known as digital twins, opens up many possibilities for reducing operating and maintenance costs. Nonlinear dynamical systems with unknown governing equations and states characterize many engineered systems. As a result, learning their dynamics from data has become both the current research area and one of the biggest challenges. In this thesis, we do an investigation of different data driven approaches for modeling various engineered systems. Firstly, we develop a model to predict the transient and steady-state behavior of a turbocharger turbine using the Koopman operator which can be helpful for modelling, analysis and control design. Our approach is as follows. We use experimental data from a Cummins heavy-duty diesel engine to develop a turbine model using Extended Dynamic Mode Decomposition (EDMD), which approximates the action of the Koopman operator on a finite-dimensional subspace of the space of observables. The results demonstrate comparable performance with a tuned nonlinear autoregressive network with an exogenous input (NARX) model widely used in the literature. The performance of these two models is analyzed based on their ability to predict turbine transient and steady-state behavior. Furthermore, we assess the ability of liquid time-constant (LTC) networks to learn the dynamics of various oscillatory systems using noisy data. In this study, we analyze and compare the performance of the LTC network with various commonly used recurrent neural network (RNN) architectures like long short-term memory (LSTM) network, and gated recurrent units (GRU). Our approach is as follows. We first systematically generate synthetic data by exciting the system of interest with a band-limited white noise and simulating it using a forward Euler discretization scheme. After the output has been simulated, we then corrupt it with different levels of noise to replicate a practically measured signal and train the RNN architectures with that corrupted output. The model is then tested on various types of forcing excitations to analyze the robustness of these networks in capturing different behaviors exhibited by the system. We also analyze the ability of these networks to capture the resonance effect for various parameter settings. Case studies discussing standard benchmark oscillatory systems (i.e., spring-mass-damper (S-M-D) system, single degree of freedom (DOF) Bouc-Wen oscillator, and forced Van der pol oscillator) are used to test the performance of these methodologies. The results reveal that the LTC network showed better performance in modeling the S-M-D system and 1-DOF Bouc-Wen oscillator as compared to an LSTM network but was outperformed by the GRU network. None of the networks were able to model the forced Van der pol oscillator with a reasonable accuracy. Since the GRU network outperformed other networks in terms of the computational time and the model accuracy for most of the scenarios, we applied it to a real world experimental dataset (i.e. turbocharger turbine dynamics) to compare it against the EDMD and NARX model. The results showed better performance of the GRU network in modeling the transient behaviours of the turbine. However, it failed to predict the turbine outlet temperature with a reasonable accuracy in most of the regions for the steady state dataset. As future work, we plan to consider training the GRU network with a data sampling frequency of 100 Hz for a fair comparison with the NARX and the Koopman approach.</p>

No description available.

In many situations, fluid flows can exhibit a wide range of temporal and spatial phenomena. It has become common to extract physically important features, called modes, as a first step in the analysis of flows with high complexity. One of the most prominent modal analysis techniques in the context of fluid dynamics is Proper Orthogonal Decomposition (POD), which enables extraction of energetically coherent structures present in the flow field. This method does, however, suffer from the lack of connection with the mathematical theory of dynamical systems and its utility in the analysis of arbitrarily complex flows might therefore be limited. In the present work, we instead consider application of the Koopman Mode Decomposition (KMD), which is an approach based on spectral decomposition of the Koopman operator. This technique is employed for modal analysis of the incompressible, two-dimensional ow past two side-by-side cylinders at Re = 60 and with a non-dimensional cylinder gap spacing g* = 1. This particular configuration yields a wake ow which exhibits in-phase vortex shedding during finite time, while later transforming into the so-called flip-flopping phenomena, which is characterised by a slow, periodic switching of the gap ow direction during O(10) vortex shedding cycles. The KMD approach yields modal structures which, in contrary to POD, are associated with specific oscillation frequencies. Specifically, these structures are here vorticity modes. By studying these modes, we are able to extract the ow components which are responsible for the flip-flop phenomenon. In particular, it is found that the flip-flop instability is mainly driven by three different modal structures, oscillating with Strouhal frequencies St1 = 0:023, St2 = 0:121 and St3 = 0:144, where it is noted that St3 = St1 + St2. In addition, we study the in-phase vortex shedding regime, as well as the transient regime connecting the two states of the flow. The study of the in-phase vortex shedding reveals| - not surprisingly - the presence of a single fundamental frequency, while the study of the transient reveals a Koopman spectrum which might indicate the existence of a bifurcation in the phase space of the flow field; this idea has been proposed before in Carini et al. (2015b). We conclude that the KMD offers a powerful framework for analysis of this ow case, and its range of applications might soon include even more complex flows.

The study of nonlinear dynamical systems via the spectrum of the Koopman operator has emerged as a paradigm shift, from the Poincaré's geometric picture that centers the attention on the evolution of states, to the Koopman operator's picture that focuses on the evolution of observables. The Koopman operator-theoretic framework rests on the idea of lifting the states of a nonlinear dynamical system to a higher dimensional space; these lifted states are referred to as the Koopman eigenfunctions. To determine the Koopman eigenfunctions, one performs a nonlinear transformation of the states by relying on the so-called observables, that is, scalar-valued functions of the states. In other words, one executes a change of coordinates from the state space to another set of coordinates, which are denominated Koopman canonical coordinates. The variables defined on these intrinsic coordinates will evolve linearly in time, despite the underlying system being nonlinear. Since the Koopman operator is linear, it is natural to exploit its spectral properties. In fact, the theory surrounding the spectral properties of linear operators has well-known implications in electric power systems. Examples include small-signal stability analysis and direct methods for transient stability analysis based on the Lyapunov function. From the applications' standpoint, this framework based on the Koopman operator is attractive because it is capable of revealing linear and nonlinear modes by only applying well-established tools that have been developed for linear systems. With the challenges associated with the high-dimensionality and increasing uncertainties in the power systems models, researchers and practitioners are seeking alternative modeling approaches capable of incorporating information from measurements. This is fueled by an increasing amount of data made available by the wide-scale deployment of measuring devices such as phasor measurement units and smart meters. Along these lines, the Koopman operator theory is a promising framework for the integration of data analysis into our mathematical knowledge and is bringing an exciting perspective to the community. The present dissertation reports on the application of the Koopman operator for identification, estimation, and control of electric power systems. A dynamic state estimator based on the Koopman operator has been developed and compares favorably against model-based approaches, in particular for centralized dynamic state estimation. Also, a data-driven method to compute participation factors for nonlinear systems based on Koopman mode decomposition has been developed; it generalizes the original definition of participation factors under certain conditions. / PHD / Electric power systems are complex, large-scale, and given the bidirectional causality between economic growth and electricity consumption, they are constantly being expanded. In the U.S., some of the electric power grid facilities date back to the 1880s, and this aging system is operating at its capacity limits. In addition, the international pressure for sustainability is driving an unprecedented deployment of renewable energy sources into the grid. Unlike the case of other primary sources of electric energy such as coal and nuclear, the electricity generated from renewable energy sources is strongly influenced by the weather conditions, which are very challenging to forecast even for short periods of time. Within this context, the mathematical models that have aided engineers to design and operate electric power grids over the past decades are falling short when uncertainties are incorporated to the models of such high-dimensional systems. Consequently, researchers are investigating alternative data-driven approaches. This is not only motivated by the need to overcome the above challenges, but it is also fueled by the increasing amount of data produced by today’s powerful computational resources and experimental apparatus. In power systems, a massive amount of data will be available thanks to the deployment of measuring devices called phasor measurement units. Along these lines, the Koopman operator theory is a promising framework for the integration of data analysis into our mathematical knowledge, and is bringing an exciting perspective on the treatment of high-dimensional systems that lie in the forefront of science and technology. In the research work reported in this dissertation, the Koopman operator theory has been exploited to seek for solutions to some of the challenges that are threatening the safe, reliable, and efficient operation of electric power systems.