Showing papers on "System identification published in 2020"

Data Informativity: A New Perspective on Data-Driven Analysis and Control

Abstract: The use of persistently exciting data has recently been popularized in the context of data-driven analysis and control. Such data have been used to assess system-theoretic properties and to construct control laws, without using a system model. Persistency of excitation is a strong condition that also allows unique identification of the underlying dynamical system from the data within a given model class. In this article, we develop a new framework in order to work with data that are not necessarily persistently exciting. Within this framework, we investigate necessary and sufficient conditions on the informativity of data for several data-driven analysis and control problems. For certain analysis and design problems, our results reveal that persistency of excitation is not necessary. In fact, in these cases, data-driven analysis/control is possible while the combination of (unique) system identification and model-based control is not. For certain other control problems, our results justify the use of persistently exciting data, as data-driven control is possible only with data that are informative for system identification.

SINDy-PI: a robust algorithm for parallel implicit sparse identification of nonlinear dynamics.

Abstract: Accurately modelling the nonlinear dynamics of a system from measurement data is a challenging yet vital topic. The sparse identification of nonlinear dynamics (SINDy) algorithm is one approach to discover dynamical systems models from data. Although extensions have been developed to identify implicit dynamics, or dynamics described by rational functions, these extensions are extremely sensitive to noise. In this work, we develop SINDy-PI (parallel, implicit), a robust variant of the SINDy algorithm to identify implicit dynamics and rational nonlinearities. The SINDy-PI framework includes multiple optimization algorithms and a principled approach to model selection. We demonstrate the ability of this algorithm to learn implicit ordinary and partial differential equations and conservation laws from limited and noisy data. In particular, we show that the proposed approach is several orders of magnitude more noise robust than previous approaches, and may be used to identify a class of ODE and PDE dynamics that were previously unattainable with SINDy, including for the double pendulum dynamics and simplified model for the Belousov-Zhabotinsky (BZ) reaction.

PySINDy: A Python package for the sparse identification of nonlinear dynamical systems from data

Abstract: Scientists have long quantified empirical observations by developing mathematical models that characterize the observations, have some measure of interpretability, and are capable of making predictions. Dynamical systems models in particular have been widely used to study, explain, and predict system behavior in a wide range of application areas, with examples ranging from Newton’s laws of classical mechanics to the Michaelis-Menten kinetics for modeling enzyme kinetics. While governing laws and equations were traditionally derived by hand, the current growth of available measurement data and resulting emphasis on data-driven modeling motivates algorithmic approaches for model discovery. A number of such approaches have been developed in recent years and have generated widespread interest, including Eureqa (Schmidt & Lipson, 2009), sure independence screening and sparsifying operator (Ouyang, Curtarolo, Ahmetcik, Scheffler, & Ghiringhelli, 2018), and the sparse identification of nonlinear dynamics (SINDy) (Brunton, Proctor, & Kutz, 2016). Maximizing the impact of these model discovery methods requires tools to make them widely accessible to scientists across domains and at various levels of mathematical expertise.

A shift in paradigm for system identification

Abstract: System identification is a mature research area with well established paradigms, mostly based on classical statistical methods. Recently, there has been considerable interest in so called k...

Training deep neural density estimators to identify mechanistic models of neural dynamics.

Abstract: Computational neuroscientists use mathematical models built on observational data to investigate what’s happening in the brain. Models can simulate brain activity from the behavior of a single neuron right through to the patterns of collective activity in whole neural networks. Collecting the experimental data is the first step, then the challenge becomes deciding which computer models best represent the data and can explain the underlying causes of how the brain behaves. Researchers usually find the right model for their data through trial and error. This involves tweaking a model’s parameters until the model can reproduce the data of interest. But this process is laborious and not systematic. Moreover, with the ever-increasing complexity of both data and computer models in neuroscience, the old-school approach of building models is starting to show its limitations. Now, Goncalves, Lueckmann, Deistler et al. have designed an algorithm that makes it easier for researchers to fit mathematical models to experimental data. First, the algorithm trains an artificial neural network to predict which models are compatible with simulated data. After initial training, the method can rapidly be applied to either raw experimental data or selected data features. The algorithm then returns the models that generate the best match. This newly developed machine learning tool was able to automatically identify models which can replicate the observed data from a diverse set of neuroscience problems. Importantly, further experiments showed that this new approach can be scaled up to complex mechanisms, such as how a neural network in crabs maintains its rhythm of activity. This tool could be applied to a wide range of computational investigations in neuroscience and other fields of biology, which may help bridge the gap between ‘data-driven’ and ‘theory-driven’ approaches.

Feedback Linearization Based on Gaussian Processes With Event-Triggered Online Learning

Abstract: Combining control engineering with nonparametric modeling techniques from machine learning allows for the control of systems without analytic description using data-driven models. Most of the existing approaches separate learning , i.e., the system identification based on a fixed dataset, and control , i.e., the execution of the model-based control law. This separation makes the performance highly sensitive to the initial selection of training data and possibly requires very large datasets. This article proposes a learning feedback linearizing control law using online closed-loop identification. The employed Gaussian process model updates its training data only if the model uncertainty becomes too large. This event-triggered online learning ensures high data efficiency and thereby reduces computational complexity, which is a major barrier for using Gaussian processes under real-time constraints. We propose safe forgetting strategies of data points to adhere to budget constraints and to further increase data efficiency. We show asymptotic stability for the tracking error under the proposed event-triggering law and illustrate the effective identification and control in simulation.

Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems

Abstract: We study the problem of system identification and adaptive control in partially observable linear dynamical systems. Adaptive and closed-loop system identification is a challenging problem due to correlations introduced in data collection. In this paper, we present the first model estimation method with finite-time guarantees in both open and closed-loop system identification. Deploying this estimation method, we propose adaptive control online learning (AdaptOn), an efficient reinforcement learning algorithm that adaptively learns the system dynamics and continuously updates its controller through online learning steps. AdaptOn estimates the model dynamics by occasionally solving a linear regression problem through interactions with the environment. Using policy re-parameterization and the estimated model, AdaptOn constructs counterfactual loss functions to be used for updating the controller through online gradient descent. Over time, AdaptOn improves its model estimates and obtains more accurate gradient updates to improve the controller. We show that AdaptOn achieves a regret upper bound of $\text{polylog}\left(T\right)$, after $T$ time steps of agent-environment interaction. To the best of our knowledge, AdaptOn is the first algorithm that achieves $\text{polylog}\left(T\right)$ regret in adaptive control of unknown partially observable linear dynamical systems which includes linear quadratic Gaussian (LQG) control.

Fractional order neural networks for system identification

Abstract: Neural networks and fractional order calculus have shown to be powerful tools for system identification. In this paper we combine both approaches to propose a fractional order neural network (FONN) for system identification. The learning algorithm was generalized considering the Grunwald-Letnikov fractional derivative. This new black box modeling approach is validated by the identification of three different systems (two benchmark systems and a real system). Comparisons vs others approaches showed that the proposed FONN model reached better accuracy with less number of parameters.

State-of-Charge Observer Design for Batteries With Online Model Parameter Identification: A Robust Approach

Abstract: The state-of-charge (SOC) indicates a lithium-ion battery's remaining capacity, and an accurate SOC estimation plays a crucial role in the battery's operation optimization and lifetime extension. This article studies a robust model-based SOC estimation strategy for batteries. Based on a battery equivalent circuit model, a robust recursive-least-squares algorithm is utilized for the model parameters online extraction, which avoids unnecessary experiments prior to SOC estimation for parameter identification. Compared with the conventional recursive least squares, it can effectively guarantee the parameter identification performance in spite of outliers in battery measurement signals. Then, a robust observer with the estimated model parameters is designed for the battery's SOC estimation, which can suppress the disturbance caused by unknown model errors. Theoretical analysis and extensive experimental results demonstrate the effectiveness of the designed SOC observer combined with robust recursive least-squares-based model identification.

An Iterative Approach for Accurate Dynamic Model Identification of Industrial Robots

Abstract: Dynamic model has broad applications in motion planning, feedforward controller design, and disturbance observer design. Particularly, with the increasing application of model-based control in industrial robots, there has been a resurgence of research interest in accurate identification of dynamic models. However, on the one hand, most existing identification methods directly rely on least squares or weighted least squares (WLS), which suffer from outliers and could lead to physical infeasible solutions. On the other hand, nonlinearity of the friction model is seldom treated in a unified way with linear regression. Moreover, recent researches have shown that proper exciting trajectories are crucial to the identification accuracy, but few of previous works take measurement noise into consideration when optimizing the exciting trajectories. In this article, we propose an iterative approach which integrates WLS, iteratively reweighted least squares with linear matrix inequality constraints, and nonlinear friction models so that the above-mentioned issues can be properly solved altogether. Our research also reveals that performance can be improved by including priori knowledge of measurement noise in the optimization of exciting trajectories. The proposed approach is supported by experimental analysis of four different combinations within the framework on a 6-DoF industrial robot.

Dynamic Mode Decomposition for Compressive System Identification

Abstract: Dynamic mode decomposition has emerged as a leading technique to identify spatiotemporal coherent structures from high-dimensional data, benefiting from a strong connection to nonlinear dynamical s...

An Adaptive Deep Belief Network With Sparse Restricted Boltzmann Machines

Abstract: Deep belief network (DBN) is an efficient learning model for unknown data representation, especially nonlinear systems. However, it is extremely hard to design a satisfactory DBN with a robust structure because of traditional dense representation. In addition, backpropagation algorithm-based fine-tuning tends to yield poor performance since its ease of being trapped into local optima. In this article, we propose a novel DBN model based on adaptive sparse restricted Boltzmann machines (AS-RBM) and partial least square (PLS) regression fine-tuning, abbreviated as ARP-DBN, to obtain a more robust and accurate model than the existing ones. First, the adaptive learning step size is designed to accelerate an RBM training process, and two regularization terms are introduced into such a process to realize sparse representation. Second, initial weight derived from AS-RBM is further optimized via layer-by-layer PLS modeling starting from the output layer to input one. Third, we present the convergence and stability analysis of the proposed method. Finally, our approach is tested on Mackey–Glass time-series prediction, 2-D function approximation, and unknown system identification. Simulation results demonstrate that it has higher learning accuracy and faster learning speed. It can be used to build a more robust model than the existing ones.

Maximum Likelihood Estimation in Data-Driven Modeling and Control.

Abstract: Recently, various algorithms for data-driven simulation and control have been proposed based on the Willems' fundamental lemma. However, when collected data are noisy, these methods lead to ill-conditioned data-driven model structures. In this work, we present a maximum likelihood framework to obtain an optimal data-driven model, the signal matrix model, in the presence of output noise. A data compression scheme is also proposed to enable more efficient use of large datasets. Two approaches in system identification and receding horizon control are developed based on the derived optimal estimator. The first one identifies a finite impulse response model in combination with the kernel-based method. This approach improves the least-squares-based estimator with less restrictive assumptions. The second one applies the signal matrix model as the predictor in predictive control. The control performance is shown to be better than existing data-driven predictive control algorithms, especially under high noise levels. Both approaches demonstrate that the derived estimator provides a promising framework to apply data-driven algorithms to noisy data.

Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework

Abstract: This paper develops a Pontryagin Differentiable Programming (PDP) methodology, which establishes a unified framework to solve a broad class of learning and control tasks. The PDP distinguishes from existing methods by two novel techniques: first, we differentiate through Pontryagin's Maximum Principle, and this allows to obtain the analytical derivative of a trajectory with respect to tunable parameters within an optimal control system, enabling end-to-end learning of dynamics, policies, or/and control objective functions; and second, we propose an auxiliary control system in the backward pass of the PDP framework, and the output of this auxiliary control system is the analytical derivative of the original system's trajectory with respect to the parameters, which can be iteratively solved using standard control tools. We investigate three learning modes of the PDP: inverse reinforcement learning, system identification, and control/planning. We demonstrate the capability of the PDP in each learning mode on different high-dimensional systems, including multi-link robot arm, 6-DoF maneuvering quadrotor, and 6-DoF rocket powered landing.

Constrained Event-Triggered H∞ Control Based on Adaptive Dynamic Programming With Concurrent Learning

Abstract: In this article, an event-triggered H∞ control method is proposed based on adaptive dynamic programming (ADP) with concurrent learning for unknown continuous-time nonlinear systems with control constraints. First, a system identification technique based on neural networks (NNs) is adopted to identify completely unknown systems. Second, a critic NN is employed to approximate the value function. A novel weight updating rule is developed based on the event-triggered control law and time-triggered disturbance law, which reduces controller execution times and guarantees the stability of the system. Subsequently, concurrent learning is applied to the weight updating rule to relax the demand for the traditional persistence of excitation condition that is difficult to implement online. Finally, the comparison between the time-triggered method and event-triggered method in simulation demonstrates the effectiveness of the developed constrained event-triggered ADP method.

Automatic Differentiation to Simultaneously Identify Nonlinear Dynamics and Extract Noise Probability Distributions from Data.

Abstract: The sparse identification of nonlinear dynamics (SINDy) is a regression framework for the discovery of parsimonious dynamic models and governing equations from time-series data. As with all system identification methods, noisy measurements compromise the accuracy and robustness of the model discovery procedure. In this work, we develop a variant of the SINDy algorithm that integrates automatic differentiation and recent time-stepping constrained motivated by Rudy et al. for simultaneously (i) denoising the data, (ii) learning and parametrizing the noise probability distribution, and (iii) identifying the underlying parsimonious dynamical system responsible for generating the time-series data. Thus within an integrated optimization framework, noise can be separated from signal, resulting in an architecture that is approximately twice as robust to noise as state-of-the-art methods, handling as much as 40% noise on a given time-series signal and explicitly parametrizing the noise probability distribution. We demonstrate this approach on several numerical examples, from Lotka-Volterra models to the spatio-temporal Lorenz 96 model. Further, we show the method can identify a diversity of probability distributions including Gaussian, uniform, Gamma, and Rayleigh.

Data-driven modeling of the chaotic thermal convection in an annular thermosyphon

Abstract: Identifying accurate and yet interpretable low-order models from data has gained a renewed interest over the past decade. In the present work, we illustrate how the combined use of dimensionality reduction and sparse system identification techniques allows us to obtain an accurate model of the chaotic thermal convection in a two-dimensional annular thermosyphon. Taking as guidelines the derivation of the Lorenz system, the chaotic thermal convection dynamics simulated using a high-fidelity computational fluid dynamics solver are first embedded into a low-dimensional space using dynamic mode decomposition. After having reviewed the physical properties the reduced-order model should exhibit, the latter is identified using SINDy, an increasingly popular and flexible framework for the identification of nonlinear continuous-time dynamical systems from data. The identified model closely resembles the canonical Lorenz system, having the same structure and exhibiting the same physical properties. It moreover accurately predicts a bifurcation of the high-dimensional system (corresponding to the onset of steady convection cells) occurring at a much lower Rayleigh number than the one considered in this study.