arXiv subjects

Michel Verhaegen

Publications and source records attributed to Michel Verhaegen.

At least 37 records · Page 2Linked to original sources

arXiv2018

Sparsity Preserving Optimal Control of Discretized PDE Systems

We focus on the problem of optimal control of large-scale systems whose models are obtained by discretization of partial differential equations using the Finite Element (FE) or Finite Difference (FD) methods. The motivation for studying this pressing problem originates from the fact that the classical numerical tools used to solve low-dimensional optimal control problems are computationally infeasible for large-scale systems. Furthermore, although the matrices of large-scale FE or FD models are usually sparse banded or highly structured, the optimal control solution computed using the classical methods is dense and unstructured. Consequently, it is not suitable for efficient centralized and distributed real-time implementations. We show that the a priori (sparsity) patterns of the exact solutions of the generalized Lyapunov equations for FE and FD models are banded matrices. The a priori pattern predicts the dominant non-zero entries of the exact solution. We furthermore show that for well-conditioned problems, the a priori patterns are not only banded but also sparse matrices. On the basis of these results, we develop two computationally efficient methods for computing sparse approximate solutions of generalized Lyapunov equations. Using these two methods and the inexact Newton method, we show that the solution of the generalized Riccati equation can be approximated by a banded matrix. This enables us to develop a novel computationally efficient optimal control approach that is able to preserve the sparsity of the control law. We perform extensive numerical experiments that demonstrate the effectiveness of our approach.

math.OC↗

arXiv2017

Fault Estimation Filter Design with Guaranteed Stability Using Markov Parameters

For additive actuator and sensor faults, we propose a systematic method to design a state-space fault estimation filter directly from Markov parameters identified from fault-free data. We address this problem by parameterizing a system-inversion-based fault estimation filter with the identified Markov parameters. Even without building an explicit state-space plant model, our novel approach still allows the filter gain design for stabilization and suboptimal $\mathcal{H}_2$ performance. This design freedom cannot be achieved by other existing data-driven fault estimation filter designs so far. Another benefit of our proposed design is the convenience of determining the state order: a higher state order of the filter leads to better estimation performance, at the cost of heavier computational burden. In contrast, order determination is cumbersome when using an identified state-space plant model for the filter design, because of the complicated propagation of the model mismatch into the fault estimation errors. Simulations using an unstable aircraft system illustrate the effectiveness of the proposed new method.

eess.SY↗

arXiv2017

System Identification through Online Sparse Gaussian Process Regression with Input Noise

There has been a growing interest in using non-parametric regression methods like Gaussian Process (GP) regression for system identification. GP regression does traditionally have three important downsides: (1) it is computationally intensive, (2) it cannot efficiently implement newly obtained measurements online, and (3) it cannot deal with stochastic (noisy) input points. In this paper we present an algorithm tackling all these three issues simultaneously. The resulting Sparse Online Noisy Input GP (SONIG) regression algorithm can incorporate new noisy measurements in constant runtime. A comparison has shown that it is more accurate than similar existing regression algorithms. When applied to non-linear black-box system modeling, its performance is competitive with existing non-linear ARX models.

stat.ML↗

arXiv2017

A sequential Monte Carlo approach to Thompson sampling for Bayesian optimization

Bayesian optimization through Gaussian process regression is an effective method of optimizing an unknown function for which every measurement is expensive. It approximates the objective function and then recommends a new measurement point to try out. This recommendation is usually selected by optimizing a given acquisition function. After a sufficient number of measurements, a recommendation about the maximum is made. However, a key realization is that the maximum of a Gaussian process is not a deterministic point, but a random variable with a distribution of its own. This distribution cannot be calculated analytically. Our main contribution is an algorithm, inspired by sequential Monte Carlo samplers, that approximates this maximum distribution. Subsequently, by taking samples from this distribution, we enable Thompson sampling to be applied to (armed-bandit) optimization problems with a continuous input space. All this is done without requiring the optimization of a nonlinear acquisition function. Experiments have shown that the resulting optimization method has a competitive performance at keeping the cumulative regret limited.

stat.ML↗

arXiv2017

Subspace Identification of Large-Scale 1D Homogeneous Networks

This paper considers the identification of large-scale 1D networks consisting of identical LTI dynamical systems. A new subspace identification method is developed that only uses local input-output information and does not rely on knowledge about the local state interaction. The identification of the local system matrices (up to a similarity transformation) is done via a low dimensional subspace retrieval step that enables the estimation of the Markov parameters of a locally lifted system. Using the estimated Markov parameters, the state-space realization of a single subsystem in the network is determined. The low dimensional subspace retrieval step exploits various key structural properties that are present in the data equation such as a low rank property and a {\em two-layer} Toeplitz structure in the data matrices constructed from products of the system matrices. For the estimation of the system matrices of a single subsystem, it is formulated as a structured low-rank matrix factorization problem. The effectiveness of the proposed identification method is demonstrated by a simulation example.

eess.SY↗

arXiv2016

N2SID: Nuclear Norm Subspace Identification

The identification of multivariable state space models in innovation form is solved in a subspace identification framework using convex nuclear norm optimization. The convex optimization approach allows to include constraints on the unknown matrices in the data-equation characterizing subspace identification methods, such as the lower triangular block-Toeplitz of weighting matrices constructed from the Markov parameters of the unknown observer. The classical use of instrumental variables to remove the influence of the innovation term on the data equation in subspace identification is avoided. The avoidance of the instrumental variable projection step has the potential to improve the accuracy of the estimated model predictions, especially for short data length sequences. This is illustrated using a data set from the DaSIy library. An efficient implementation in the framework of the Alternating Direction Method of Multipliers (ADMM) is presented that is used in the validation study.

eess.SY↗

arXiv2016

Gray Box Identification of State-Space Models Using Difference of Convex Programming

Gray-box identification is prevalent in modeling physical and networked systems. However, due to the non-convex nature of the gray-box identification problem, good initial parameter estimates are crucial for a successful application. In this paper, a new identification method is proposed by exploiting the low-rank and structured Hankel matrix of impulse response. This identification problem is recasted into a difference-of-convex programming problem, which is then solved by the sequential convex programming approach with the associated initialization obtained by nuclear-norm optimization. The presented method aims to achieve the maximum impulse-response fitting while not requiring additional (non-convex) conditions to secure non-singularity of the similarity transformation relating the given state-space matrices to the gray-box parameterized ones. This overcomes a persistent shortcoming in a number of recent contributions on this topic, and the new method can be applied for the structured state-space realization even if the involved system parameters are unidentifiable. The method can be used both for directly estimating the gray-box parameters and for providing initial parameter estimates for further iterative search in a conventional gray-box identification setup.

eess.SY↗

arXiv2016

Online Optimization with Costly and Noisy Measurements using Random Fourier Expansions

This paper analyzes DONE, an online optimization algorithm that iteratively minimizes an unknown function based on costly and noisy measurements. The algorithm maintains a surrogate of the unknown function in the form of a random Fourier expansion (RFE). The surrogate is updated whenever a new measurement is available, and then used to determine the next measurement point. The algorithm is comparable to Bayesian optimization algorithms, but its computational complexity per iteration does not depend on the number of measurements. We derive several theoretical results that provide insight on how the hyper-parameters of the algorithm should be chosen. The algorithm is compared to a Bayesian optimization algorithm for a benchmark problem and three applications, namely, optical coherence tomography, optical beam-forming network tuning, and robot arm control. It is found that the DONE algorithm is significantly faster than Bayesian optimization in the discussed problems, while achieving a similar or better performance.

cs.LG↗

arXiv2016

Sparse solution of the Lyapunov equation for large-scale interconnected systems

We consider the problem of computing an approximate banded solution of the continuous-time Lyapunov equation $\underline{A}\underline{X}+\underline{X}\underline{A}^{T}=\underline{P}$, where the coefficient matrices $\underline{A}$ and $\underline{P}$ are large, symmetric banded matrices. The (sparsity) pattern of $\underline{A}$ describes the interconnection structure of a large-scale interconnected system. Recently, it has been shown that the entries of the solution $\underline{X}$ are spatially localized or decaying away from a banded pattern. We show that the decay of the entries of $\underline{X}$ is faster if the condition number of $\underline{A}$ is smaller. By exploiting the decay of entries of $\underline{X}$, we develop two computationally efficient methods for approximating $\underline{X}$ by a banded matrix. For a well-conditioned and sparse banded $\underline{A}$, the computational and memory complexities of the methods scale linearly with the state dimension. We perform extensive numerical experiments that confirm this, and that demonstrate the effectiveness of the developed methods. The methods proposed in this paper can be generalized to (sparsity) patterns of $\underline{A}$ and $\underline{P}$ that are more general than banded matrices. The results of this paper open the possibility for developing computationally efficient methods for approximating the solution of the large-scale Riccati equation by a sparse matrix.

math.OC↗

arXiv2016

Robust Air Data Sensor Fault Diagnosis With Enhanced Fault Sensitivity Using Moving Horizon Estimation

This paper investigates robust fault diagnosis of multiple air data sensor faults in the presence of winds. The trade-off between robustness to winds and sensitivity to faults is challenging due to simultaneous influence of winds and latent faults on monitored sensors. Different from conventional residual generators that do not consider any constraints, we propose a constrained residual generator using moving horizon estimation. The main contribution is improved fault sensitivity by exploiting known bounds on winds in residual generation. By analyzing the Karush-Kuhn-Tucker conditions of the formulated moving horizon estimation problem, it is shown that this improvement is attributed to active inequality constraints caused by faults. When the weighting matrices in the moving horizon estimation problem are tuned to increase robustness to winds, its fault sensitivity does not simply decrease as one would expect in conventional unconstrained residual generators. Instead, its fault sensitivity increases when the fault is large enough to activate some inequality constraints. This fault sensitivity improvement is not restricted to this particular application, but can be achieved by any general moving horizon estimation based residual generator. A high-fidelity Airbus simulator is used to illustrate the advantage of our proposed approach in terms of fault sensitivity.

eess.SY↗

arXiv2016

Mean and variance of the LQG cost function

Linear Quadratic Gaussian (LQG) systems are well-understood and methods to minimize the expected cost are readily available. Less is known about the statistical properties of the resulting cost function. The contribution of this paper is a set of analytic expressions for the mean and variance of the LQG cost function. These expressions are derived using two different methods, one using solutions to Lyapunov equations and the other using only matrix exponentials. Both the discounted and the non-discounted cost function are considered, as well as the finite-time and the infinite-time cost function. The derived expressions are successfully applied to an example system to reduce the probability of the cost exceeding a given threshold.

eess.SY↗

arXiv2015

Identification of Structured LTI MIMO State-Space Models

The identification of structured state-space model has been intensively studied for a long time but still has not been adequately addressed. The main challenge is that the involved estimation problem is a non-convex (or bilinear) optimization problem. This paper is devoted to developing an identification method which aims to find the global optimal solution under mild computational burden. Key to the developed identification algorithm is to transform a bilinear estimation to a rank constrained optimization problem and further a difference of convex programming (DCP) problem. The initial condition for the DCP problem is obtained by solving its convex part of the optimization problem which happens to be a nuclear norm regularized optimization problem. Since the nuclear norm regularized optimization is the closest convex form of the low-rank constrained estimation problem, the obtained initial condition is always of high quality which provides the DCP problem a good starting point. The DCP problem is then solved by the sequential convex programming method. Finally, numerical examples are included to show the effectiveness of the developed identification algorithm.

math.OC↗

arXiv2015

Direct identification of fault estimation filter for sensor faults

We propose a systematic method to directly identify a sensor fault estimation filter from plant input/output data collected under fault-free condition. This problem is challenging, especially when omitting the step of building an explicit state-space plant model in data-driven design, because the inverse of the underlying plant dynamics is required and needs to be stable. We show that it is possible to address this problem by relying on a system-inversion-based fault estimation filter that is parameterized using identified Markov parameters. Our novel data-driven approach improves estimation performance by avoiding the propagation of model reduction errors originating from identification of the state-space plant model into the designed filter. Furthermore, it allows additional design freedom to stabilize the obtained filter under the same stabilizability condition as the existing model-based system inversion. This crucial property enables its application to sensor faults in unstable plants, where existing data-driven filter designs could not be applied so far due to the lack of such stability guarantees (even after stabilizing the closed-loop system). A numerical simulation example of sensor faults in an unstable aircraft system illustrates the effectiveness of the proposed new method.

eess.SY↗

arXiv2015

Data-Driven Robust Receding Horizon Fault Estimation

This paper presents a data-driven receding horizon fault estimation method for additive actuator and sensor faults in unknown linear time-invariant systems, with enhanced robustness to stochastic identification errors. State-of-the-art methods construct fault estimators with identified state-space models or Markov parameters, but they do not compensate for identification errors. Motivated by this limitation, we first propose a receding horizon fault estimator parameterized by predictor Markov parameters. This estimator provides (asymptotically) unbiased fault estimates as long as the subsystem from faults to outputs has no unstable transmission zeros. When the identified Markov parameters are used to construct the above fault estimator, zero-mean stochastic identification errors appear as model uncertainty multiplied with unknown fault signals and online system inputs/outputs (I/O). Based on this fault estimation error analysis, we formulate a mixed-norm problem for the offline robust design that regards online I/O data as unknown. An alternative online mixed-norm problem is also proposed that can further reduce estimation errors when the online I/O data have large amplitudes, at the cost of increased computational burden. Based on a geometrical interpretation of the two proposed mixed-norm problems, systematic methods to tune the user-defined parameters therein are given to achieve desired performance trade-offs. Simulation examples illustrate the benefits of our proposed methods compared to recent literature.

eess.SY↗

arXiv2014

Focal-plane wavefront sensing with high-order adaptive optics systems

We investigate methods to calibrate the non-common path aberrations at an adaptive optics system having a wavefront-correcting device working at an extremely high resolution (larger than 150x150). We use focal-plane images collected successively, the corresponding phase-diversity information and numerically efficient algorithms to calculate the required wavefront updates. The wavefront correction is applied iteratively until the algorithms converge. Different approaches are studied. In addition of the standard Gerchberg-Saxton algorithm, we test the extension of the Fast & Furious algorithm that uses three images and creates an estimate of the pupil amplitudes. We also test recently proposed phase-retrieval methods based on convex optimisation. The results indicate that in the framework we consider, the calibration task is easiest with algorithms similar to the Fast & Furious.

astro-ph.IM↗

arXiv2014

Fast & Furious focal-plane wavefront sensing

We present two complementary algorithms suitable for using focal-plane measurements to control a wavefront corrector with an extremely high spatial resolution. The algorithms use linear approximations to iteratively minimize the aberrations seen by the focal-plane camera. The first algorithm, Fast & Furious (FF), uses a weak-aberration assumption and pupil symmetries to achieve fast wavefront reconstruction. The second algorithm, an extension to FF, can deal with an arbitrary pupil shape; it uses a Gerchberg-Saxton style error reduction to determine the pupil amplitudes. Simulations and experimental results are shown for a spatial light modulator controlling the wavefront with a resolution of 170 x 170 pixels. The algorithms increase the Strehl ratio from ~0.75 to 0.98-0.99, and the intensity of the scattered light is reduced throughout the whole recorded image of 320 x 320 pixels. The remaining wavefront rms error is estimated to be ~0.15 rad with FF and ~0.10 rad with FF-GS.

astro-ph.IM↗

arXiv2014

Sparse approximate inverses of Gramians and impulse response matrices of large-scale interconnected systems

In this paper we show that inverses of well-conditioned, finite-time Gramians and impulse response matrices of large-scale interconnected systems described by sparse state-space models, can be approximated by sparse matrices. The approximation methodology established in this paper opens the door to the development of novel methods for distributed estimation, identification and control of large-scale interconnected systems. The novel estimators (controllers) compute local estimates (control actions) simply as linear combinations of inputs and outputs (states) of local subsystems. The size of these local data sets essentially depends on the condition number of the finite-time observability (controllability) Gramian. Furthermore, the developed theory shows that the sparsity patterns of the system matrices of the distributed estimators (controllers) are primarily determined by the sparsity patterns of state-space matrices of large-scale systems. The computational and memory complexity of the approximation algorithms are $O(N)$, where $N$ is the number of local subsystems of the interconnected system. Consequently, the proposed approximation methodology is computationally feasible for interconnected systems with an extremely large number of local subsystems.

eess.SY↗

arXiv2014

Distributed System Identification with ADMM

This paper presents identification of both network connected systems as well as distributed systems governed by PDEs in the framework of distributed optimization via the Alternating Direction Method of Multipliers. This approach opens first the possibility to identify distributed models in a global manner using all available data sequences and second the possibility for a distributed implementation. The latter will make the application to large scale complex systems possible. In addition to outlining a new large scale identification method, illustrations are shown for identifying both network connected systems and discretized PDEs.

eess.SY↗