arXiv subjects

Rolf Findeisen

Publications and source records attributed to Rolf Findeisen.

At least 55 records · Page 3Linked to original sources

arXiv2023

Machine Learning Benchmarks for the Classification of Equivalent Circuit Models from Electrochemical Impedance Spectra

Analysis of Electrochemical Impedance Spectroscopy (EIS) data for electrochemical systems often consists of defining an Equivalent Circuit Model (ECM) using expert knowledge and then optimizing the model parameters to deconvolute various resistance, capacitive, inductive, or diffusion responses. For small data sets, this procedure can be conducted manually; however, it is not feasible to manually define a proper ECM for extensive data sets with a wide range of EIS responses. Automatic identification of an ECM would substantially accelerate the analysis of large sets of EIS data. We showcase machine learning methods to classify the ECMs of 9,300 impedance spectra provided by QuantumScape for the BatteryDEV hackathon. The best-performing approach is a gradient-boosted tree model utilizing a library to automatically generate features, followed by a random forest model using the raw spectral data. A convolutional neural network using boolean images of Nyquist representations is presented as an alternative, although it achieves a lower accuracy. We publish the data and open source the associated code. The approaches described in this article can serve as benchmarks for further studies. A key remaining challenge is the identifiability of the labels, underlined by the model performances and the comparison of misclassified spectra.

cs.LG↗

arXiv2023

Safe Machine-Learning-supported Model Predictive Force and Motion Control in Robotics

Many robotic tasks, such as human-robot interactions or the handling of fragile objects, require tight control and limitation of appearing forces and moments alongside sensible motion control to achieve safe yet high-performance operation. We propose a learning-supported model predictive force and motion control scheme that provides stochastic safety guarantees while adapting to changing situations. Gaussian processes are used to learn the uncertain relations that map the robot's states to the forces and moments. The model predictive controller uses these Gaussian process models to achieve precise motion and force control under stochastic constraint satisfaction. As the uncertainty only occurs in the static model parts -- the output equations -- a computationally efficient stochastic MPC formulation is used. Analysis of recursive feasibility of the optimal control problem and convergence of the closed loop system for the static uncertainty case are given. Chance constraint formulation and back-offs are constructed based on the variance of the Gaussian process to guarantee safe operation. The approach is illustrated on a lightweight robot in simulations and experiments.

cs.RO↗

arXiv2023

Model Predictive Control with Gaussian-Process-Supported Dynamical Constraints for Autonomous Vehicles

We propose a model predictive control approach for autonomous vehicles that exploits learned Gaussian processes for predicting human driving behavior. The proposed approach employs the uncertainty about the GP's prediction to achieve safety. A multi-mode predictive control approach considers the possible intentions of the human drivers. While the intentions are represented by different Gaussian processes, their probabilities foreseen in the observed behaviors are determined by a suitable online classification. Intentions below a certain probability threshold are neglected to improve performance. The proposed multi-mode model predictive control approach with Gaussian process regression support enables repeated feasibility and probabilistic constraint satisfaction with high probability. The approach is underlined in simulation, considering real-world measurements for training the Gaussian processes.

eess.SY↗

arXiv2023

LMI-based Data-Driven Robust Model Predictive Control

Predictive control, which is based on a model of the system to compute the applied input optimizing the future system behavior, is by now widely used. If the nominal models are not given or are very uncertain, data-driven model predictive control approaches can be employed, where the system model or input is directly obtained from past measured trajectories. Using a data informativity framework and Finsler's lemma, we propose a data-driven robust linear matrix inequality-based model predictive control scheme that considers input and state constraints. Using these data, we formulate the problem as a semi-definite optimization problem, whose solution provides the matrix gain for the linear feedback, while the decisive variables are independent of the length of the measurement data. The designed controller stabilizes the closed-loop system asymptotically and guarantees constraint satisfaction. Numerical examples are conducted to illustrate the method.

eess.SY↗

arXiv2023

Towards a modeling, optimization and predictive control framework for fed-batch metabolic cybergenetics

Biotechnology offers many opportunities for the sustainable manufacturing of valuable products. The toolbox to optimize bioprocesses includes \textit{extracellular} process elements such as the bioreactor design and mode of operation, medium formulation, culture conditions, feeding rates, etc. However, these elements are frequently insufficient for achieving optimal process performance or precise product composition. One can use metabolic and genetic engineering methods for optimization at the intracellular level. Nevertheless, those are often of static nature, failing when applied to dynamic processes or if disturbances occur. Furthermore, many bioprocesses are optimized empirically and implemented with little-to-no feedback control to counteract disturbances. The concept of cybergenetics has opened new possibilities to optimize bioprocesses by enabling online modulation of the gene expression of metabolism-relevant proteins via external inputs (e.g., light intensity in optogenetics). Here, we fuse cybergenetics with model-based optimization and predictive control for optimizing dynamic bioprocesses. To do so, we propose to use dynamic constraint-based models that integrate the dynamics of metabolic reactions, resource allocation, and inducible gene expression. We formulate a model-based optimal control problem to find the optimal process inputs. Furthermore, we propose using model predictive control to address uncertainties via online feedback. We focus on fed-batch processes, where the substrate feeding rate is an additional optimization variable. As a simulation example, we show the optogenetic control of the ATPase enzyme complex for dynamic modulation of enforced ATP wasting to adjust product yield and productivity.

eess.SY↗

arXiv2023

Machine Learning for Process Control of (Bio)Chemical Processes

The control of manufacturing processes must satisfy high quality and efficiency requirements while meeting safety requirements. A broad spectrum of monitoring and control strategies, such as model- and optimization-based controllers, are utilized to address these issues. Driven by rising demand for flexible yet energy and resource-efficient operations existing approaches are challenged due to high uncertainties and changes. Machine learning algorithms are becoming increasingly important in tackling these challenges, especially due to the growing amount of available data. The ability for automatic adaptation and learning from human operators offer new opportunities to increase efficiency yet provide flexible operation. Combining machine learning algorithms with safe or robust controls offers novel reliable operation methods. This chapter highlights ways to fuse machine learning and control for the safe and improved operation of chemical and biochemical processes. We outline and summarize both - learning models for control and learning the control components. We offer a general overview, including a literature review, to provide a guideline for utilizing machine learning techniques in control structures.

eess.SY↗

arXiv2022

Safe Hierarchical Model Predictive Control and Planning for Autonomous Systems

Planning and control for autonomous vehicles usually are hierarchical separated. However, increasing performance demands and operating in highly dynamic environments requires an frequent re-evaluation of the planning and tight integration of control and planning to guarantee safety. We propose an integrated hierarchical predictive control and planning approach to tackle this challenge. Planner and controller are based on the repeated solution of moving horizon optimal control problems. The planner can choose different low-layer controller modes for increased flexibility and performance instead of using a single controller with a large safety margin for collision avoidance under uncertainty. Planning is based on simplified system dynamics and safety, yet flexible operation is ensured by constraint tightening based on a mixed-integer linear programming formulation. A cyclic horizon tube-based model predictive controller guarantees constraint satisfaction for different control modes and disturbances. Examples of such modes are a slow-speed movement with high precision and fast-speed movements with large uncertainty bounds. Allowing for different control modes reduces the conservatism, while the hierarchical decomposition of the problem reduces the computational cost and enables real-time implementation. We derive conditions for recursive feasibility to ensure constraint satisfaction and obstacle avoidance to guarantee safety and ensure compatibility between the layers and modes. Simulation results illustrate the efficiency and applicability of the proposed hierarchical strategy.

eess.SY↗

arXiv2022

Flexible development and evaluation of machine-learning-supported optimal control and estimation methods via HILO-MPC

Model-based optimization approaches for monitoring and control, such as model predictive control and optimal state and parameter estimation, have been used for decades in many engineering applications. Models describing the dynamics, constraints, and desired performance criteria are fundamental to model-based approaches. Thanks to recent technological advancements in digitalization, machine learning methods such as deep learning, and computing power, there has been an increasing interest in using machine learning methods alongside model-based approaches for control and estimation. The number of new methods and theoretical findings using machine learning for model-based control and optimization is increasing rapidly. This paper outlines the basic ideas and principles behind an easy-to-use Python toolbox that allows to quickly and efficiently solve machine-learning-supported optimization, model predictive control, and estimation problems. The toolbox leverages state-of-the-art machine learning libraries to train components used to define the problem. It allows to efficiently solve the resulting optimization problems. Machine learning can be used for a broad spectrum of tasks, ranging from model predictive control for stabilization, setpoint tracking, path following, and trajectory tracking to moving horizon estimation and Kalman filtering. For linear systems, it enables quick code generation for embedded MPC applications. HILO-MPC is flexible and adaptable, making it especially suitable for research and fundamental development tasks. Due to its simplicity and numerous already implemented examples, it is also a powerful teaching tool. The usability is underlined, presenting a series of application examples.

eess.SY↗

arXiv2022

Efficient Stochastic Optimal Control through Approximate Bayesian Input Inference

Optimal control under uncertainty is a prevailing challenge for many reasons. One of the critical difficulties lies in producing tractable solutions for the underlying stochastic optimization problem. We show how advanced approximate inference techniques can be used to handle the statistical approximations principled and practically by framing the control problem as a problem of input estimation. Analyzing the Gaussian setting, we present an inference-based solver that is effective in stochastic and deterministic settings and was found to be superior to popular baselines on nonlinear simulated tasks. We draw connections that relate this inference formulation to previous approaches for stochastic optimal control and outline several advantages that this inference view brings due to its statistical nature.

cs.LG↗

arXiv2021

Control of Scanning Quantum Dot Microscopy

Scanning quantum dot microscopy is a recently developed high-resolution microscopy technique that is based on atomic force microscopy and is capable of imaging the electrostatic potential of nanostructures like molecules or single atoms. Recently, it could be shown that it not only yields qualitatively but also quantitatively cutting edge images even on an atomic level. In this paper we present how control is a key enabling element to this. The developed control approach consists of a two-degree-of-freedom control framework that comprises a feedforward and a feedback part. For the latter we design two tailored feedback controllers. The feedforward part generates a reference for the current scanned line based on the previously scanned one. We discuss in detail various aspects of the presented control approach and its implications for scanning quantum dot microscopy. We evaluate the influence of the feedforward part and compare the two proposed feedback controllers. The proposed control algorithms speed up scanning quantum dot microscopy by more than a magnitude and enable to scan large sample areas.

eess.SY↗

arXiv2021

A Polynomial Chaos Approach to Robust $\mathcal{H}_\infty$ Static Output-Feedback Control with Bounded Truncation Error

This article considers the $\mathcal{H}_\infty$ static output-feedback control for linear time-invariant uncertain systems with polynomial dependence on probabilistic time-invariant parametric uncertainties. By applying polynomial chaos theory, the control synthesis problem is solved using a high-dimensional expanded system which characterizes stochastic state uncertainty propagation. A closed-loop polynomial chaos transformation is proposed to derive the closed-loop expanded system. The approach explicitly accounts for the closed-loop dynamics and preserves the $\mathcal{L}_2$-induced gain, which results in smaller transformation errors compared to existing polynomial chaos transformations. The effect of using finite-degree polynomial chaos expansions is first captured by a norm-bounded linear differential inclusion, and then addressed by formulating a robust polynomial chaos based control synthesis problem. This proposed approach avoids the use of high-degree polynomial chaos expansions to alleviate the destabilizing effect of truncation errors, which significantly reduces computational complexity. In addition, some analysis is given for the condition under which the robustly stabilized expanded system implies the robust stability of the original system. A numerical example illustrates the effectiveness of the proposed approach.

eess.SY↗

arXiv2020

Online learning-based Model Predictive Control with Gaussian Process Models and Stability Guarantees

Model predictive control allows to provide high performance and safety guarantees in the form of constraint satisfaction. These properties, however, can be satisfied only if the underlying model, used for prediction, of the controlled process is sufficiently accurate. One way to address this challenge is by data-driven and machine learning approaches, such as Gaussian processes, that allow to refine the model online during operation. We present a combination of an output feedback model predictive control scheme and a Gaussian process-based prediction model that is capable of efficient online learning. To this end, the concept of evolving Gaussian processes is combined with recursive posterior prediction updates. The presented approach guarantees recursive constraint satisfaction and input-to-state stability with respect to the model-plant mismatch. Simulation studies underline that the Gaussian process prediction model can be successfully and efficiently learned online. The resulting computational load is significantly reduced via the combination of the recursive update procedure and by limiting the number of training data points while maintaining good performance.

eess.SY↗

arXiv2020

Controller tuning in power systems using singular value optimization

As the share of renewable generation in large power systems continues to increase, the operation of power systems becomes increasingly challenging. The constantly shifting mix of renewable and conventional generation leads to largely changing dynamics, increasing the risk of blackouts. We propose to retune the parameters of the already present controllers in the power systems to account for the seemingly changing operating conditions. To this end, we present an approach for fast and computationally efficient tuning of parameters of structured controllers. The goal of the tuning is to shift system poles to a specified region in the complex plane, e.g. for stabilization or oscillation damping. The approach exploits singular value optimization in the frequency domain, which enables scaling to large systems and is not limited to power systems. The efficiency of the approach is shown on three systems of increasing size with multiple initial parameterizations.

eess.SY↗

arXiv2020

Fusing Online Gaussian Process-Based Learning and Control for Scanning Quantum Dot Microscopy

Elucidating electrostatic surface potentials contributes to a deeper understanding of the nature of matter and its physicochemical properties, which is the basis for a wide field of applications. Scanning quantum dot microscopy, a recently developed technique allows to measure such potentials with atomic resolution. For an efficient deployment in scientific practice, however, it is essential to speed up the scanning process. To this end we employ a two-degree-of-freedom control paradigm, in which a Gaussian process is used as the feedforward part. We present a tailored online learning scheme of the Gaussian process, adapted to scanning quantum dot microscopy, that includes hyperparameter optimization during operation to enable fast and precise scanning of arbitrary surface structures. For the potential application in practice, the accompanying computational cost is reduced evaluating different sparse approximation approaches. The fully independent training conditional approximation, used on a reduced set of active training data, is found to be the most promising approach.

eess.SY↗

arXiv2019

Learning References with Gaussian Processes in Model Predictive Control applied to Robot Assisted Surgery

One of the key benefits of model predictive control is the capability of controlling a system proactively in the sense of taking the future system evolution into account. However, often external disturbances or references are not a priori known, which renders the predictive controllers shortsighted or uninformed. Adaptive prediction models can be used to overcome this issue and provide predictions of these signals to the controller. In this work we propose to learn references via Gaussian processes for model predictive controllers. To illustrate the approach, we consider robot assisted surgery, where a robotic manipulator needs to follow a learned reference position based on optical tracking measurements.

math.OC↗

arXiv2019

Constrained Gaussian Process Learning for Model Predictive Control

Many control tasks can be formulated as a tracking problem of a known or unknown reference signal. Examples are movement compensation in collaborative robotics, the synchronisation of oscillations for power systems or reference tracking of recipes in chemical process operation. Tracking performance as well as guaranteeing stability of the closed loop strongly depends on two factors: Firstly, it depends on whether the future desired tracking reference signal is known and, secondly, whether the system can track the reference at all. This paper shows how to use machine learning, i.e. Gaussian processes, to learn a reference from (noisy) data, while guaranteeing trackability of the modified desired reference predictions in the framework of model predictive control. Guarantees are provided by adjusting the hyperparameters via a constrained optimization. Two specific scenarios, i.e. asymptotically constant and periodical references, are discussed.

math.OC↗

arXiv2019

Scalable and Data Privacy Conserving Controller Tuning for Large-Scale Power Networks

The increasing share of renewable generation leads to new challenges in reliable power system operation, such as the rising volatility of power generation, which leads to time-varying dynamics and behavior of the system. To counteract the changing dynamics, we propose to adapt the parameters of existing controllers to the changing conditions. Doing so, however, is challenging, as large power systems often involve multiple subsystem operators, which, for safety and privacy reasons, do not want to exchange detailed information about their subsystems. Furthermore, centralized tuning of structured controllers for large-scale systems, such as power networks, is often computationally very challenging. For this reason, we present a hierarchical decentralized approach for controller tuning, which increases data security and scalability. The proposed method is based on the exchange of structured reduced models of subsystems, which conserves data privacy and reduces computational complexity. For this purpose, suitable methods for model reduction and model matching are introduced. Furthermore, we demonstrate how increased renewable penetration leads to time-varying dynamics on the IEEE 68 bus power system, which underlines the importance of the problem. Then, we apply the proposed approach on simulation studies to show its effectiveness. As shown, a similar system performance as with a centralized method can be obtained. Finally, we show the scalability of the approach on a large power system with more than 2500 states and about 1500 controller parameters.

eess.SY↗

arXiv2017

Comments on Truncation Errors for Polynomial Chaos Expansions

Methods based on polynomial chaos expansion allow to approximate the behavior of systems with uncertain parameters by deterministic dynamics. These methods are used in a wide range of applications, spanning from simulation of uncertain systems to estimation and control. For practical purposes the exploited spectral series expansion is typically truncated to allow for efficient computation, which leads to approximation errors. Despite the Hilbert space nature of polynomial chaos, there are only a few results in the literature that explicitly discuss and quantify these approximation errors. This work derives error bounds for polynomial chaos approximations of polynomial and non-polynomial mappings. Sufficient conditions are established, which allow investigating the question whether zero truncation errors can be achieved and which series order is required to achieve this. Furthermore, convex quadratic programs, whose argmin operator is a special case of a piecewise polynomial mapping, are studied due to their relevance in predictive control. Several simulation examples illustrate our findings.

eess.SY↗