Showing papers on "System identification published in 2016"

Target-free approach for vision-based structural system identification using consumer-grade cameras

Abstract: Summary Recent reports on America's infrastructure have emphasized the importance of structural health monitoring of civil infrastructures. System identification is a key component of many structural health monitoring strategies. Current system identification methods estimate models of a structure by measuring displacements, accelerations, and strains with wired or wireless sensors. However, these methods typically involve installation of a limited number of sensors at discrete locations and require additional data acquisition devices. To overcome these limitations, computer vision-based techniques have been introduced recently that employ high-speed and high-resolution cameras. Such cameras can be quite costly and require tedious installation of targets. This paper investigates the potential of using consumer-grade cameras for structural system identification without the need to install targets. The underlying methods for target-free displacement measurements are introduced, including region of interest selection, feature detection, point tracking, and outlier removal. A set of experiments are conducted to assess the efficacy of the proposed approach by comparing the accuracy of the identified model with one obtained using a conventional wired system. Careful comparison of the results demonstrates the significant potential of the proposed approach. Copyright © 2016 John Wiley & Sons, Ltd.

Identification of Confirmatory Factor Analysis Models of Different Levels of Invariance for Ordered Categorical Outcomes

Abstract: This article considers the identification conditions of confirmatory factor analysis (CFA) models for ordered categorical outcomes with invariance of different types of parameters across groups. The current practice of invariance testing is to first identify a model with only configural invariance and then test the invariance of parameters based on this identified baseline model. This approach is not optimal because different identification conditions on this baseline model identify the scales of latent continuous responses in different ways. Once an invariance condition is imposed on a parameter, these identification conditions may become restrictions and define statistically non-equivalent models, leading to different conclusions. By analyzing the transformation that leaves the model-implied probabilities of response patterns unchanged, we give identification conditions for models with invariance of different types of parameters without referring to a specific parametrization of the baseline model. Tests based on this approach have the advantage that they do not depend on the specific identification condition chosen for the baseline model.

Data-Based Adaptive Critic Designs for Nonlinear Robust Optimal Control With Uncertain Dynamics

Abstract: In this paper, the infinite-horizon robust optimal control problem for a class of continuous-time uncertain nonlinear systems is investigated by using data-based adaptive critic designs. The neural network identification scheme is combined with the traditional adaptive critic technique, in order to design the nonlinear robust optimal control under uncertain environment. First, the robust optimal controller of the original uncertain system with a specified cost function is established by adding a feedback gain to the optimal controller of the nominal system. Then, a neural network identifier is employed to reconstruct the unknown dynamics of the nominal system with stability analysis. Hence, the data-based adaptive critic designs can be developed to solve the Hamilton–Jacobi–Bellman equation corresponding to the transformed optimal control problem. The uniform ultimate boundedness of the closed-loop system is also proved by using the Lyapunov approach. Finally, two simulation examples are presented to illustrate the effectiveness of the developed control strategy.

Online adaptive optimal control for continuous-time nonlinear systems with completely unknown dynamics

Abstract: An online adaptive optimal control is proposed for continuous-time nonlinear systems with completely unknown dynamics, which is achieved by developing a novel identifier-critic-based approximate dynamic programming algorithm with a dual neural network (NN) approximation structure. First, an adaptive NN identifier is designed to obviate the requirement of complete knowledge of system dynamics, and a critic NN is employed to approximate the optimal value function. Then, the optimal control law is computed based on the information from the identifier NN and the critic NN, so that the actor NN is not needed. In particular, a novel adaptive law design method with the parameter estimation error is proposed to online update the weights of both identifier NN and critic NN simultaneously, which converge to small neighbourhoods around their ideal values. The closed-loop system stability and the convergence to small vicinity around the optimal solution are all proved by means of the Lyapunov theory. The proposed ada...

Identification of Dynamic Models in Complex Networks With Prediction Error Methods: Predictor Input Selection

Abstract: This paper addresses the problem of obtaining an estimate of a particular module of interest that is embedded in a dynamic network with known interconnection structure. In this paper it is shown that there is considerable freedom as to which variables can be included as inputs to the predictor, while still obtaining consistent estimates of the particular module of interest. This freedom is encoded into sufficient conditions on the set of predictor inputs that allow for consistent identification of the module. The conditions can be used to design a sensor placement scheme, or to determine whether it is possible to obtain consistent estimates while refraining from measuring particular variables in the network. As identification methods the Direct and Two Stage Prediction-Error methods are considered. Algorithms are presented for checking the conditions using tools from graph theory.

Linear identification of nonlinear systems: A lifting technique based on the Koopman operator

Abstract: We exploit the key idea that nonlinear system identification is equivalent to linear identification of the so-called Koopman operator. Instead of considering nonlinear system identification in the state space, we obtain a novel linear identification technique by recasting the problem in the infinite-dimensional space of observables. This technique can be described in two main steps. In the first step, similar to a component of the Extended Dynamic Mode Decomposition algorithm, the data are lifted to the infinite-dimensional space and used for linear identification of the Koopman operator. In the second step, the obtained Koopman operator is “projected back” to the finite-dimensional state space, and identified to the nonlinear vector field through a linear least squares problem. The proposed technique is efficient to recover (polynomial) vector fields of different classes of systems, including unstable, chaotic, and open systems. In addition, it is robust to noise, well-suited to model low sampling rate datasets, and able to infer network topology and dynamics.

Gaussian Process-Based Predictive Control for Periodic Error Correction

Abstract: Many controlled systems suffer from unmodeled nonlinear effects that recur periodically over time. Model-free controllers generally cannot compensate these effects, and good physical models for such periodic dynamics are challenging to construct. We investigate nonparametric system identification for periodically recurring nonlinear effects. Within a Gaussian process (GP) regression framework, we use a locally periodic covariance function to shape the hypothesis space, which allows for a structured extrapolation that is not possible with more widely used covariance functions. We show that hyperparameter estimation can be performed online using the maximum a posteriori point estimate, which provides an accuracy comparable with sampling methods as soon as enough data to cover the periodic structure has been collected. It is also shown how the periodic structure can be exploited in the hyperparameter optimization. The predictions obtained from the GP model are then used in a model predictive control framework to correct the external effect. The availability of good continuous predictions allows control at a higher rate than that of the measurements. We show that the proposed approach is particularly beneficial for sampling times that are smaller than, but of the same order of magnitude as, the period length of the external effect. In experiments on a physical system, an electrically actuated telescope mount, this approach achieves a reduction of about 20% in root mean square tracking error.

The recursive least squares identification algorithm for a class of Wiener nonlinear systems

Abstract: Many physical systems can be modeled by a Wiener nonlinear model, which consists of a linear dynamic system followed by a nonlinear static function. This work is concerned with the identification of Wiener systems whose output nonlinear function is assumed to be continuous and invertible. A recursive least squares algorithm is presented based on the auxiliary model identification idea. To solve the difficulty of the information vector including the unmeasurable variables, the unknown terms in the information vector are replaced with their estimates, which are computed through the preceding parameter estimates. Finally, an example is given to support the proposed method.

Filtering-based iterative identification for multivariable systems

Abstract: This study applies the filtering technique to system identification to study the data filtering-based parameter estimation methods for multivariable systems, which are corrupted by correlated noise – an autoregressive moving average process. To solve the difficulty that the identification model contains the unmeasurable variables and noise terms in the information matrix, the authors present a hierarchical gradient-based iterative (HGI) algorithm by using the hierarchical identification principle. To improve the convergence rate, they apply the filtering technique to derive a filtering-based HGI algorithm and a filtering-based hierarchical least squares-based iterative (HLSI) algorithm. The simulation examples indicate that the filtering-based HLSI algorithm has the highest computational efficiency among these three algorithms.

Toolbox for development and validation of grey-box building models for forecasting and control

Abstract: As automatic sensing and information and communication technology get cheaper, building monitoring data becomes easier to obtain. The availability of data leads to new opportunities in the context of energy efficiency in buildings. This paper describes the development and validation of a data-driven grey-box modelling toolbox for buildings. The Python toolbox is based on a Modelica library with thermal building and Heating, Ventilation and Air-Conditioning models and the optimization framework in JModelica.org. The toolchain facilitates and automates the different steps in the system identification procedure, like data handling, model selection, parameter estimation and validation. To validate the methodology, different grey-box models are identified for a single-family dwelling with detailed monitoring data from two experiments. Validated models for forecasting and control can be identified. However, in one experiment the model performance is reduced, likely due to a poor information content in the identification data set.

Nonlinear Systems Identification Using Deep Dynamic Neural Networks.

Abstract: Neural networks are known to be effective function approximators. Recently, deep neural networks have proven to be very effective in pattern recognition, classification tasks and human-level control to model highly nonlinear realworld systems. This paper investigates the effectiveness of deep neural networks in the modeling of dynamical systems with complex behavior. Three deep neural network structures are trained on sequential data, and we investigate the effectiveness of these networks in modeling associated characteristics of the underlying dynamical systems. We carry out similar evaluations on select publicly available system identification datasets. We demonstrate that deep neural networks are effective model estimators from input-output data

Model Reduction of Bilinear Systems in the Loewner Framework

Abstract: The Loewner framework for model reduction is extended to the class of bilinear systems The main advantage of this framework over existing ones is that the Loewner pencil introduces a trade-off between accuracy and complexity Furthermore, through this framework, one can derive state-space models directly from input-output data without requiring initial system matrices The recently introduced methodology of Volterra series interpolation is also addressed Several numerical experiments illustrate the main features of this approach

A convex polynomial force-motion model for planar sliding: Identification and application

Abstract: We propose a polynomial force-motion model for planar sliding. The set of generalized friction loads is the 1-sublevel set of a polynomial whose gradient directions correspond to generalized velocities. Additionally, the polynomial is confined to be convex even-degree homogeneous in order to obey the maximum work inequality, symmetry, shape invariance in scale, and fast invertibility. We present a simple and statistically-efficient model identification procedure using a sum-of-squares convex relaxation. Simulation and robotic experiments validate the accuracy and efficiency of our approach. We also show practical applications of our model including stable pushing of objects and free sliding dynamic simulations.

System Identification and Robust Control of Multi-Input Multi-Output Active Magnetic Bearing Systems

Abstract: This paper studies the system identification and robust control of a multi-input multi-output (MIMO) active magnetic bearing (AMB) system. The AMB system under study is open-loop unstable, and the presence of right-half plane zeros and the rotor flexible modes bring additional degrees of difficulty to the control design of such a system. First, a closed-loop system identification is performed using frequency-domain-response data of the system. Genetic-algorithm-based weighted least squares method is employed to obtain the best frequency-weighted model of the system. As the cross-coupling channels have negligible gains in the low-frequency region, it is assumed that the system can be diagonalized. This allows the analysis of the system as a family of low-order single-input single-output (SISO) subsystems. On the other hand, the effects caused by the coupling channels become more significant at higher frequencies. Therefore, a similar method is used to obtain a high-order MIMO model of the system by including the cross-coupling effects. Next, SISO $H_\infty $ controllers and lead–lag-type compensators are designed on the basis of the SISO models of the systems. To strive for a better performance, MIMO $H_{2}$ and $H_\infty $ optimal controllers are synthesized on the basis of the MIMO model of the system. Extensive experimental studies are conducted on the performance of the designed SISO and MIMO controllers in real time by taking into consideration both constant disturbances while the rotor is stationary and sinusoidal disturbances caused by the centrifugal forces and the rotor mass imbalance while the rotor is in rotation. Unlike the recently published works, it is shown that the accurate modeling of the system being controlled is the key to the successful design of high-performance stable controllers that not only guarantee the internal stability of the system–controller interconnection but also that no further modifications are required before the real-time implementation of the designed controllers.

Fractional-order modeling of permanent magnet synchronous motor speed servo system

Abstract: A fractional-order modeling approach for a permanent magnet synchronous motor speed servo system is proposed applying a method combining electromagnetic part modeling and mechanical part modeling. Based on the proposed fractional-order model and system identification scheme, system identification experiments are performed on the electromagnetic part and the mechanical part of the permanent magnet synchronous motor speed servo system, respectively. The fractional-order model parameters of these two parts are identified with these experimental results, and the fractional-order model of the permanent magnet synchronous motor speed servo system is integrated from these two parts. Simulations and experiments in open-loop and closed-loop are performed based on the obtained fractional-order model and integer-order model. The advantage of the proposed fractional-order model for the permanent magnet synchronous motor speed servo system is demonstrated by the simulation and experimental results.