Application of the PLS-PH algorithm for identification of closed-loop systems

System identification deals with the problem of building the mathematical models of dynamical systems according to the input and output data. The open-loop system identification (Observer/Kalman Filter SystemIdentification, OKID) for stable systems without requiring feedback control is introduced first. For identifying marginally stable or unstable system, however, feedback control is required to ensure the overall system stability. The algorithm of closed-loop system identification (CLID) with known feedback dynamics is shown next.

Objectives: Closed-loop identification is reported to provide better results for identification of systems for control applications. This study conducted closed-loop identification on an Aspen Plus® dynamic simulation based on a pilot-plant distillation column to develop discrete-time linear time-invariant models. Methods/Statistical Analysis: Identification data was generated using set-point perturbations in control variables under proportional-integral control. Identified models were compared with a model identified using open-loop data using 20-step ahead predictions. Findings: Results indicate that closed-loop identification provides more precise prediction models than open-loop identification in this case study. 20-step predictions for closed loop models exceeded 90% fit, whereas the open loop model predictions provided a 70% fit and missed the steady-state values. Application/Improvements: Thus closed-loop identification is more appropriate for applications in model-based controllers. Keywords: Aspen Plus, Closed-Loop Identification, Distillation Column, Identification for Control, System Identification

Aiming at the large delay and large inertia in cone storage and irrigation, this paper adopts machine learning and predictive control, proposes a closed-loop N4SID (numerical subspace state system identification) algorithm, which is adjusted by IMC based on Smith predictor PI controller and parameter tuning are given, and the steps designed in cascade control are given. The experimental results verify the effectiveness of the proposed method.Compared with closed-loop SVA and open-loop methods, the method proposed in this paper has better verification results and pole assignment. According to this model, the PI controller is adjusted using IMC based on Smith Smith predictor. Compared with the traditional ZN adjustment method, this method shows good results in a conical system. In addition, the PI parameters can be adjusted to obtain robust control using the H∞-based mixed sensitivity algorithm. The contribution of this paper is the use of closed subspace system identification to identify the MIMO state space. The developed model validates the IMC tuned PI controller based on the Smith predictor in the factory.

There are six main algorithms for real-time identification of FIR systems from binary measurements on the output. The objective of this paper is to propose a first short comparison of these methods based on the description of each method and on some numerical simulations. This comparison should help the user in choosing an algorithm if necessary.

This study addresses the challenges of infinite impulse response (IIR) system identification by introducing an improved cooperation search algorithm (ICSA). Improved cooperation search algorithm enhances the original cooperation search algorithm (CSA) through the integration of a pattern search algorithm and opposition-based learning, aiming to improve both exploration and exploitation capabilities. The algorithm's performance was evaluated against diverse IIR plants of varying orders using convergence analysis, scatter plots, and statistical metrics. Results demonstrate ICSA's superiority over CSA, achieving significantly lower mean squared error (MSE) values across different system orders and model types. Notably, ICSA outperformed CSA by up to 27 orders of magnitude for matched-order models and up to 95.85% for reduced-order models. The algorithm also exhibited more consistent performance, with substantially lower standard deviations in many cases. Statistical validation through the Wilcoxon signed-rank test further confirmed ICSA's enhanced performance. This research highlights ICSA's efficacy in producing efficient IIR systems, demonstrating its potential for more accurate system identification compared to existing methods. Cite this article as: C. Ersalı and B. Hekimoğlu, "Improved cooperation search optimization algorithm for infinite impulse response system identification," Electrica, 24(3), 733-747, 2024.

The central nervous system controls body functions and initiates actions through an integrated system of multiple feedback loops. System identification can be a valuable tool to assess the system dynamics. The challenge is to assess the functioning of an intact feedback system in vivo, where cause and effect are intermingled. In this paper we show the errors which can occur when estimating system dynamics using standard (open-loop) system identification algorithms in the presence of feedback loops. Furthermore, we show how these issues can be addressed by using closed-loop algorithms. A closed-loop system identification approach is essential to assess the separate feedback loops of the central nervous system in an intact functional system.

Modal parameter identification of a multiple-span post-tensioned concrete bridge using hybrid vibration testing data

This dissertation presents a new method for the statistical performance analysis of subspace system identification algorithms. A perturbation expansion of the singular value decomposition is used to approximate the effects of process and measurement noise on the identified system poles. Eigenvalue variance results are obtained that do not depend on asymptotic statistics and are therefore applicable for short data records. These performance measures are conditional upon the specific input and the parameters of the actual system being identified. This method is demonstrated on two variations of the Numerical Subspace State-Space System Identification (N4SID) algorithm. The accuracy of these theoretical performance measures is validated using simulation. Finally, this new method is applied to the first step of three well known subspace identification algorithms to determine the effects of row and column weighting on the variance of identified poles.

System identification based structural damage aggravation detection in a large masonry building

Experimental modal analysis of a single-link flexible robotic manipulator with curved geometry using applied system identification methods

In this paper, a laboratory experiment, which was developed to teach undergraduate students at the University of Pretoria, Pretoria, South Africa, some of the main issues regarding closed-loop system identification, is discussed. In this experiment, a plant is identified both from open-loop and closed-loop data. The model obtained from the open-loop data is used as reference to evaluate a closed-loop system identification approach. A motivation for closed-loop system identification and a laboratory experiment in this field is given. The experiment is outlined, each step is discussed, and the experiment is evaluated. This experiment shows that closed-loop system identification can be taught in an uncomplicated manner.

Fast ℓ1-recursive total least squares algorithm for sparse system identification

This paper introduces a new adaptive algorithm in system identification. This adaptive algorithm is a variation of greedy algorithm.

This work proposes an arctangent least mean square/fourth algorithm developed by incorporating the standard least mean square/fourth algorithm cost function with the arctangent framework for adaptive system identification. The performance of the proposed algorithm is verified through various simulations which shows that the proposed algorithm outperforms the conventional least mean square/fourth algorithm.

This paper presents a new method to identify the model of a small-scale helicopter in frequency domain using harmony search (HS) algorithm. The dynamics of the small-scale helicopter are simplified to four single-input/single-output (SISO) linear subsystems near the hover point, and the HS optimisation algorithm is used to identify each subsystem's parameters. Time-domain verification is made to check the validity of the identified models. The verification results show that the identified models are accurate and effective enough to describe the dynamics of the helicopter. The identified models show that the dynamics of the roll, pitch and yaw channels are mainly dominated by the lightly damped second-order modes. Identification and verification results show that the application of HS algorithm in system identification is suitable and useful.