Electrical and Electronic Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 28
-
ItemNo Preview AvailableTRACKING AND REGRET BOUNDS FOR ONLINE ZEROTH-ORDER EUCLIDEAN AND RIEMANNIAN OPTIMIZATION(SIAM PUBLICATIONS, 2022)
-
ItemCloseness of Solutions for Singularly Perturbed Systems via Averaging( 2018-09-20)This paper studies the behavior of singularly perturbed nonlinear differential equations with boundary-layer solutions that do not necessarily converge to an equilibrium. Using the average of the fast variable and assuming the boundary layer solutions converge to a bounded set, results on the closeness of solutions of the singularly perturbed system to the solutions of the reduced average and boundary layer systems over a finite time interval are presented. The closeness of solutions error is shown to be of order O(\sqrt(\epsilon)), where \epsilon is the perturbation parameter.
-
ItemAdaptive Scan for Atomic Force Microscopy Based on Online Optimisation: Theory and Experiment( 2019-02-11)A major challenge in Atomic Force Microscopy (AFM) is to reduce the scan duration while retaining the image quality. Conventionally, the scan rate is restricted to a sufficiently small value in order to ensure a desirable image quality as well as a safe tip-sample contact force. This usually results in a conservative scan rate for samples that have a large variation in aspect ratio and/or for scan patterns that have a varying linear velocity. In this paper, an adaptive scan scheme is proposed to alleviate this problem. A scan line-based performance metric balancing both imaging speed and accuracy is proposed, and the scan rate is adapted such that the metric is optimised online in the presence of aspect ratio and/or linear velocity variations. The online optimisation is achieved using an extremum-seeking (ES) approach, and a semi-global practical asymptotic stability (SGPAS) result is shown for the overall system. Finally, the proposed scheme is demonstrated via both simulation and experiment.
-
ItemOrdinal Optimisation for the Gaussian Copula Model( 2019-11-05)We present results on the estimation and evaluation of success probabilities for ordinal optimisation over uncountable sets (such as subsets of R d ). Our formulation invokes an assumption of a Gaussian copula model, and we show that the success probability can be equivalently computed by assuming a special case of additive noise. We formally prove a lower bound on the success probability under the Gaussian copula model, and numerical experiments demonstrate that the lower bound yields a reasonable approximation to the actual success probability. Lastly, we showcase the utility of our results by guaranteeing high success probabilities with ordinal optimisation.
-
ItemActive Learning for Linear Parameter-Varying System Identification( 2020-05-02)Active learning is proposed for selection of the next operating points in the design of experiments, for identifying linear parameter-varying systems. We extend existing approaches found in literature to multiple-input multiple-output systems with a multivariate scheduling parameter. Our approach is based on exploiting the probabilistic features of Gaussian process regression to quantify the overall model uncertainty across locally identified models. This results in a flexible framework which accommodates for various techniques to be applied for estimation of local linear models and their corresponding uncertainty. We perform active learning in application to the identification of a diesel engine air-path model, and demonstrate that measures of model uncertainty can be successfully reduced using the proposed framework.
-
ItemTracking and regret bounds for online zeroth-order Euclidean and Riemannian optimisation( 2020-10-01)We study numerical optimisation algorithms that use zeroth-order information to minimise time-varying geodesically-convex cost functions on Riemannian manifolds. In the Euclidean setting, zeroth-order algorithms have received a lot of attention in both the time-varying and time-invariant cases. However, the extension to Riemannian manifolds is much less developed. We focus on Hadamard manifolds, which are a special class of Riemannian manifolds with global nonpositive curvature that offer convenient grounds for the generalisation of convexity notions. Specifically, we derive bounds on the expected instantaneous tracking error, and we provide algorithm parameter values that minimise the algorithm’s performance. Our results illustrate how the manifold geometry in terms of the sectional curvature affects these bounds. Additionally, we provide dynamic regret bounds for this online optimisation setting. To the best of our knowledge, these are the first regret bounds even for the Euclidean version of the problem. Lastly, via numerical simulations, we demonstrate the applicability of our algorithm on an online Karcher mean problem.
-
ItemGaussian Processes with Monotonicity Constraints for Preference Learning from Pairwise Comparisons(IEEE, 2018)In preference learning, it is beneficial to incorporate monotonicity constraints for learning utility functions when there is prior knowledge of monotonicity. We present a novel method for learning utility functions with monotonicity constraints using Gaussian process regression. Data is provided in the form of pairwise comparisons between items. Using conditions on monotonicity for the predictive function, an algorithm is proposed which uses the weighted average between prior linear and maximum a posteriori (MAP) utility estimates. This algorithm is formally shown to guarantee monotonicity of the learned utility function in the dimensions desired. The algorithm is tested in a Monte Carlo simulation case study, in which the results suggest that the learned utility by the proposed algorithm performs better in prediction than the standalone linear estimate, and enforces monotonicity unlike the MAP estimate.
-
ItemA machine learning approach for tuning model predictive controllers(IEEE, 2018-01-01)Many industrial domains are characterized by Multiple-Input-Multiple-Output (MIMO) systems for which an explicit relationship capturing the nontrivial trade-off between the competing objectives is not available. Human experts have the ability to implicitly learn such a relationship, which in turn enables them to tune the corresponding controller to achieve the desirable closed-loop performance. However, as the complexity of the MIMO system and/or the controller increase, so does the tuning time and the associated tuning cost. To reduce the tuning cost, a framework is proposed in which a machine learning method for approximating the human-learned cost function along with an optimization algorithm for optimizing it, and consequently tuning the controller, are employed. In this work the focus is on the tuning of Model Predictive Controllers (MPCs), given both the interest in their implementations across many industrial domains and the associated high degrees of freedom present in the corresponding tuning process. To demonstrate the proposed approach, simulation results for the tuning of an air path MPC controller in a diesel engine are presented.
-
ItemExtremum-Seeking-Based Adaptive Scan for Atomic Force Microscopy(IEEE, 2017)Improving the imaging speed in Atomic Force Microscopy (AFM) is of high interest due to its typically prolonged imaging duration. Conventionally, the line rate of the scan is fixed at a conservative value in order to ensure a safe tip-sample contact force even in the worst case of sample aspect ratio and linear scan speed. In this paper, an adaptive scan method is proposed to adapt the scan line rate based on the extremum-seeking control framework. A performance metric balancing both imaging speed and accuracy is proposed, and an extremum-seeking approach is designed to optimise the metric based on error feedback. Semi-global practical asymptotic stability (SGPAS) result is shown, and the proposed method is demonstrated via simulation.
-
ItemModel Predictive Control for Lithium-Ion Battery Optimal Charging(IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2018-04)Charging time and lifetime are important performances for lithium-ion (Li-ion) batteries, but are often competing objectives for charging operations. Model-based charging controls are challenging due to the complicated battery system structure that is composed of nonlinear partial differential equations and exhibits multiple time-scales. This paper proposes a new methodology for battery charging control enabling an optimal tradeoff between the charging time and battery state-of-health (SOH). Using recently developed model reduction approaches, a physics-based low-order battery model is first proposed and used to formulate a model-based charging strategy. The optimal fast charging problem is formulated in the framework of tracking model predictive control (MPC). This directly considers the tracking performance for provided state-of-charge and SOH references, and explicitly addresses constraints imposed on input current and battery internal state. The capability of this proposed charging strategy is demonstrated via simulations to be effective in tracking the desirable SOH trajectories. By comparing with the constant-current constant-voltage charging protocol, the MPC-based charging appears promising in terms of both the charging time and SOH. In addition, this obtained charging strategy is practical for real-time implementation.