System Identification Algorithm Research Articles

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

System identification is widely used to estimate the dynamic characteristics of structures using either nonparametric or parametric approaches. Parametric system identification constructs mathematical models to estimate dynamic characteristics such as natural frequency, damping ratio, and mode shapes. Also, the same approach can be used to characterize damage if periodic measurements are available. In this paper, we report damage aggravation in a large neoclassical masonry structure using system identification. We took measurements in 2019 and 2023 in the Institute of Engineering, Dean Office building, which was damaged by the 2015 Gorkha, Nepal earthquake. The building is a neoclassical three storied construction with a central courtyard and an extension along the N-S direction. Without major interventions and strengthening, the building is still in use. Using the numerical algorithms for subspace state space system identification (N4SID), vibration frequencies of the structure are identified for both measurements. Also, mode shapes are identified, and damage aggravation is detected using natural frequency and MAC parameters. The first mode frequency along the N-S direction is reduced by 44% and that along the E-W direction is reduced by 1.15%, which indicates a major damage aggravation along the N-S (Y) direction.

Statistical Analysis of Block Coordinate Descent Algorithms for Linear Continuous-Time System Identification

Statistical Analysis of Block Coordinate Descent Algorithms for Linear Continuous-Time System Identification

Hybrid vibration testing for bridge modal system identification

Output-only system identification of a large post-tensioned concrete bridge using hybrid excitation was conducted. To boost ambient excitations, dynamic forcing applied by two light-weight electrodynamic shakers was adopted for hybrid testing. The bridge modal characteristics were identified using three output-only identification methods: auto-regressive time series model, eigensystem realization algorithm with observer/Kalman identification and data-driven stochastic subspace identification method. The accuracy and efficacy of the system identification algorithms when applied to hybrid dynamic responses were investigated and benchmarked against the results obtained from pure ambient vibration testing. More modes were identified from the hybrid excitation data compared to using only ambient vibrations. The study demonstrated that using output-only identification algorithms on vibration responses produced by hybrid excitations can be used for extracting more accurate and reliable modal parameters with enhanced accuracy and reliability for large-scale structures due to enhanced excitation energy and better coverage of relevant frequency bands.

Nonlinear autoregression-based non-destructive evaluation approach for railway tracks using an ultrasonic fiber bragg grating array

The safe operation of railway systems relies on rapid and accurate non-destructive damage detection and evaluation techniques to help rule out potential threats brought by rail track damages. In this paper, an innovative fiber Bragg grating (FBG) array-based sensing system is developed for rail defect inspection by integrating the ultrasonic testing technology, and a nonlinear autoregressive neural network with exogenous inputs (NARX) is proposed for rail damage detection based on measured ultrasonic signals. The developed sensing system can realize the high-speed and multiplexed ultrasonic signals demodulation. The NARX is proposed to process the ultrasonic signals obtained by the developed sensing system, and a specified probabilistic damage sensitive feature (DSF) is tailored to indicate rail health status, derived from the probability density function (PDF) of NARX prediction errors. To verify the proposed sensing system and damage identification algorithm, experimental studies considering four rail conditions (i.e., intact, cracked, bump, and welded conditions) are conducted in this study. First, baseline NARX models are priorly trained using ultrasonic signals acquired on an intact rail segment; then, DSFs corresponding to each condition are calculated enabling effective rail damage diagnosis. To optimize the training parameters of NARX models, three different training functions are utilized to select the most appropriate parameters that are sensitive to rail damages. Last, large-scale testing is conducted, further proving the applicability and reliability of the proposed rail damage evaluation approach. Through this study, it is suggested that integrating high-performance sensing technologies with effective data processing tools would maximumly enable efficient and robust non-destructive testing, especially on important infrastructures such as rails.

Intelligent Gangue Sorting System Based on Dual-Energy X-ray and Improved YOLOv5 Algorithm

Intelligent gangue sorting with high precision is of vital importance for improving coal quality. To tackle the challenges associated with coal gangue target detection, including algorithm performance imbalance and hardware deployment difficulties, in this paper, an intelligent gangue separation system that adopts the elevated YOLO-v5 algorithm and dual-energy X-rays is proposed. Firstly, images of dual-energy X-ray transmission coal gangue mixture under the actual operation of a coal mine were collected, and datasets for training and validation were self-constructed. Then, in the YOLOv5 backbone network, the EfficientNetv2 was used to replace the original cross stage partial darknet (CSPDarknet) to achieve the lightweight of the backbone network; in the neck, a light path aggregation network (LPAN) was designed based on PAN, and a convolutional block attention module (CBAM) was integrated into the BottleneckCSP of the feature fusion block to raise the feature acquisition capability of the network and maximize the learning effect. Subsequently, to accelerate the rate of convergence, an efficient intersection over union (EIOU) was used instead of the complete intersection over union (CIOU) loss function. Finally, to address the problem of low resolution of small targets leading to missed detection, an L2 detection head was introduced to the head section to improve the multi-scale target detection performance of the algorithm. The experimental results indicate that in comparison with YOLOv5-S, the same version of the algorithm proposed in this paper increases by 19.2% and 32.4% on mAP @.5 and mAP @.5:.95, respectively. The number of parameters decline by 51.5%, and the calculation complexity declines by 14.7%. The algorithm suggested in this article offers new ideas for the design of identification algorithms for coal gangue sorting systems, which is expected to save energy and reduce consumption, reduce labor, improve efficiency, and be more friendly to the embedded platform.

The q-gradient LMS spline adaptive filtering algorithm and its variable step-size variant

In this study, an innovation q-gradient least-mean-square (LMS) spline adaptive filtering (S-AF) algorithm (SAF-qLMS) on the basis of the theory of q-derivative is proposed. The q-calculus confronts the issue of slow convergence by mitigating the over-reliance of LMS-type algorithms on the diffusion of eigenvalues in the input correlation matrix. Compared to conventional derivatives, the SAF-qLMS exploits q-calculus to compute the secant of the cost function, enabling it to take larger steps in the search direction for q>1. Furthermore, for balancing the convergence rate and steady-state error of SAF-qLMS and solving the deficiency of the fixed step-size, the SAF-VqLMS based on variable step-size is further proposed. Finally, the convergence conditions of the SAF-qLMS are discussed. Simulations in a correlated Gaussian input environment confirm the outstanding performance of the proposed algorithms for nonlinear system identification.

A hybrid rotordynamic modeling method for a rotor system with flexible foundation and nonlinear support force: Numerical and experimental investigation

The dynamic characteristics of a flexible foundation would greatly affect the dynamic behavior of the rotor system. In this paper, a hybrid dynamic model method in time domain combines the finite element (FE) method and the subspace-based identification method to model a rotor system with the consideration of a flexible foundation and nonlinear support forces. The state-space model of flexible foundation is identified by the subspace state-space system identification algorithm with measured frequency response functions (FRFs). To solve the calculation problem of the hybrid dynamic model in time domain, a general algorithm named the hybrid model fusion solution (HMFS) method is proposed, which combines the linear and nonlinear nodes separation method used in the FE model and the trapezoidal rule used in the state-space model, improving the calculation efficiency of solving transient response with nonlinear forces. Simulations for the hybrid dynamic model under constant speed and speed-up cases were carried out, resulting that the dynamic characteristics of the entire system can be represented when the nonlinear factors of rolling bearings and gravity were also taken into consideration. Additionally, owe to the consideration of tested dynamic behaviors of flexible base, experimental results in the laboratory test rig are well agreed with the numerical ones under two different test configurations. The investigation provides a complete modeling and highly efficient solution framework for the rotor system with a flexible foundation and nonlinear rolling bearings, with the abilities of further consideration of more nonlinear components such as squeeze film dampers and rubbing forces.

A Partial Approximate Least Absolute Deviation-Based Identification Algorithm for a Multivariable Closed-Loop System with Spike Noise

Considering the stability and safety of industrial production, the open-loop system cannot meet the requirements of industrial production, so more and more attention has been paid to multivariable closed-loop system identification. This study focuses on the identification of a multivariate closed-loop system with spike noise in which the model order of the feedback channel is lower than that of the forward channel. Combining principal component analysis (PCA), which is used to eliminate the correlation between the data matrix elements, and the derivable approximate least absolute criterion function, partial approximate least absolute deviation (PALAD) for multivariable closed-loop system identification is proposed. By introducing a deterministic function to replace the absolute value in partial approximate least absolute deviation, the non-differentiable problem of the least absolute deviation function can be solved, and the identifiability of the multivariable closed-loop system in the case mentioned above is theoretically verified. Simulation experiments show the validity of the PALAD algorithm. Compared with the partial least squares (PLS) method, PALAD can effectively restrain the spike noise that follows an SαS distribution and shows stronger robustness when white and spike noises exist simultaneously.

A new backward shift algorithm for system identification by a good choice of frequencies

AbstractIn this study, we propose a novel backward shift algorithm for pole estimation of linear time‐invariant (LTI) systems. By making adjustments, we address the question: How should the frequencies of input signals be chosen? We select the frequencies based on algebraic accuracy in the numerical integral and use the Gaussian–Legendre formula in this process. After poles are located, the discrete Fourier transform (DFT) and the new backward shift algorithm (new BSA) along with the least squares (LS) method are used to identify the systems. Two examples show that the proposed method for pole estimation performs better and the corresponding identification algorithm is practical.

An improved proportionate arctangent framework based LMS/F algorithm for system identification

This paper proposes an improved proportionate arctangent framework that relies on a least mean square/fourth (IPALMS/F) algorithm for the physical sparse system identification problem. The ALMS/F algorithm has significant robustness against impulsive noise, whereas the improved proportionate concept when utilized with the ALMS/F takes advantage of the sparse characteristic to increase convergence time. Finally, the IPALMS/F algorithm is implemented using a recursive adaptive sparse exponential functional link neural network (RASETFLN) nonlinear filter and is named the RASETFLN-IPALMS/F algorithm which resulted in enhanced performance compared to other existing filters in terms of robustness in an impulsive environment, convergence rate, and steady-state error for system identification and acoustic echo cancellation.

Identification of fractional Hammerstein model for electrical stimulated muscle: An application of fuzzy-weighted differential evolution

Fractional order representations model complex systems with less parameters, improved accuracy and enhanced robustness in control systems but the system identification of fractional order systems is highly complicated and challenging task because of substantial nonlinearity of the input, unknown linear/nonlinear parameters of the blocks, and unknown fractional order. In this paper, parameter estimation technique is proposed based on fuzzy-weighted differential evolution algorithm for fractional electrically stimulated muscle models, which is generalization of fractional Hammerstein controlled autoregressive model vital for rehabilitation of spinal cord injury (SCI) patients. The system identification problem of fractional electrically stimulated muscle models (FESMMs) is formulated via mean square error approximation between the true and estimated response of FESMMs. The parameters of FESMMs are identified by employing fuzzy weighted differential evolution algorithm optimization knacks of with polynomial, cubic spline and sigmoidal input nonlinearities on various noise variances in the system dynamics. Comparison of results from actual to calculated responses indicates closeness up to 4 decimal places of accuracy for FESMM with polynomial type nonlinearity, up to 6 decimal places for FESMM with sigmoidal type kernel, and up to 5 decimal for FESMM with cubic spline type nonlinearity for different low and high signal to noise scenarios i.e., σ2=0.0022,0.022,0.22, which verify the precision, efficacy, stability and reliability of the fuzzy weighted differential evolution algorithm for system identification of FESMMs in rehabilitation scenarios of SCI.

Speeding up System Identification Algorithms on a Parallel RISC-V MCU for Fast Near-Sensor Vibration Diagnostic

Speeding up System Identification Algorithms on a Parallel RISC-V MCU for Fast Near-Sensor Vibration Diagnostic

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

In this paper, the principal time-domain system identification methods are studied and used to carry out the experimental modal analysis of a single-link flexible manipulator with curved geometry in a comparative fashion. The identification process carried out in this study is aimed at deriving first-order state-space dynamical models and second-order configuration-space dynamical models of the single-link flexible manipulator by using an array of fundamental system identification procedures, which includes the ARX (AutoRegressive eXogenous method), SSEST (State-Space ESTimation method), N4SID (Numerical Algorithm for Subspace State-Space System Identification), ERA/OKID (Eigensystem Realization Algorithm combined with the Observer/Kalman Filter Identification method), and TFEST (Transfer Function ESTimation method) methods. The main goal of this paper is, therefore, to perform a comparative study between the most fundamental system identification procedures applied to the numerical and experimental analysis of the structural vibrations of a flexible manipulator having a curved geometric shape. First, this paper poses the theoretical foundations for the development of the numerical study and the experimental testing to be performed for the case study. Subsequently, the flexible manipulator analyzed in this work is modeled with various levels of complexity, which range from a simple lumped parameter model to a linear finite element model developed by integrating the interconnections between the SOLIDWORKS and ANSYS software. By doing so, the computational procedures applied to the time-domain experimental measurements of the dynamic behavior of the flexible manipulator allow for reconstructing first-order and second-order mechanical models of the structural system of interest in the MATLAB simulation environment. The numerical results and the experimental tests reported in this investigation demonstrate the effectiveness of all the time-domain system identification approaches considered in the paper.

Stability by assigning structures by applying the multivariable subspace identification algorithm for a wind system with a DFIG

In this paper, a controller for a doubly fed induction generator (DFIG) connected to a wind system is proposed. This control assigning its own structures as an optimal control method, the electric model in the DFIG state space is also shown, for which it is expected to estimate a linear model through the subspace technique and thus to design the controller. It will be possible to show that a structure assignment controller is undoubtedly a good option for the control of multivariable systems. The results of the output signals will be analyzed when applying the controller, assigning their own structures, which will allow us to observe that the response and disturbance times are below two tenths of a second.

Publisher Correction: A hybrid Modified Artificial Bee Colony and extended Kalman filter algorithm for structural system identification

Publisher Correction: A hybrid Modified Artificial Bee Colony and extended Kalman filter algorithm for structural system identification

A Novel NLMS Algorithm for System Identification

In this paper, we propose a novel normalized least mean squares (NLMS) algorithm for system identification applications. Our approach involves analyzing the mean squared deviation performance of the NLMS algorithm using a random walk model to select two optimal parameters, the step size and regularization parameters, for the rapid convergence of the colored input signals. We verified that the proposed algorithm exhibited faster convergence than existing algorithms, even in scenarios of sudden system changes.

Momentum‐innovation recursive least squares identification algorithm for a servo turntable system based on the output error model

AbstractIn this article, the parameter identification problem of the output error model is investigated under the application requirement of online parameter identification of a two‐degree‐of‐freedom servo turntable system. To eliminate the influence of colored noise in the observed output signal of the output error model on the algorithm identification accuracy, the momentum factor is introduced into the innovation term of the recursive least squares algorithm, and the momentum‐innovation recursive least squares (MI‐RLS) algorithm is proposed. Further, to improve the convergence speed and identification accuracy of the algorithm while avoiding increasing the algorithm complexity significantly, a reframed multi‐innovation strategy is introduced, and a momentum reframed multi‐innovation least squares (MR‐MILS) algorithm is developed. After analyzing the complexity of the proposed algorithms, the convergence performances of the two algorithms are verified using the theory of martingale convergence, and the results show that the reframed multi‐innovation strategy can accelerate the convergence speed of the MR‐MILS algorithm. The effectiveness of the proposed identification approach is demonstrated via simulation results.

Maximum likelihood based multi‐innovation stochastic gradient identification algorithms for bilinear stochastic systems with ARMA noise

SummaryThis paper considers the parameter estimation problem for bilinear stochastic systems with autoregressive moving average (ARMA) noise using the stochastic gradient method. First, the identification model is derived by eliminating the state variables. Based on the obtained identification model, a multi‐innovation generalized extended stochastic gradient (MI‐GESG) algorithm is proposed using the multi‐innovation identification theory. Furthermore, to enhance the parameter estimation accuracy, a maximum likelihood based MI‐GESG (ML‐MI‐GESG) algorithm is developed by using the maximum likelihood identification principle. Finally, an illustrative simulation example is provided to testify the proposed algorithms. The simulation results show the effectiveness of the proposed algorithms for identifying bilinear systems.

Retracted: Selective Partial Update Adaptive Filtering Algorithms for Block-Sparse System Identification

Retracted: Selective Partial Update Adaptive Filtering Algorithms for Block-Sparse System Identification

Nonlinear Identification through eXtended Outputs (NIXO) with numerical and experimental validation using geometrically nonlinear structures

This work presents a novel technique for nonlinear system identification that operates in the frequency domain and fits a model to measured spectra to estimate the parameters in a modal domain nonlinear equation of motion (EOM). Nonlinear terms are added to the linear EOM in the form of polynomials, and the proposed algorithm estimates the polynomial coefficients as well as the underlying linear Frequency Response Function (FRF). This method is an extension to a popular nonlinear system identification algorithm called NIFO, from Nonlinear Identification through Feedback of the Outputs. However, NIFO identifies the nonlinear parameters as complex numbers that may be different at each frequency line, even though the mechanical system is expected to be governed by an EOM in which the nonlinear parameters are real and constant with frequency. This might be problematic, because any variation in the identified nonlinear parameters will distort the linear FRFs estimated by NIFO, and those linear FRFs are important to tell the user whether all of the significant nonlinearity has been extracted from the system. The proposed algorithm, here dubbed Nonlinear Identification through eXtended Outputs (NIXO), estimates the nonlinear parameters as frequency-independent and real. Additionally, it is demonstrated that for the systems studied here that the algorithm works when random and swept-sine inputs are used to excite the tested structure, while NIFO only worked well when random inputs were used. The method is first evaluated numerically using benchmark case studies, starting with the SDOF equation and then reduced models of a clamped-clamped flat beam, and the results are compared to those obtained with NIFO. Then the algorithm is applied to swept-sine measurements from a 3D-printed flat beam and the results are validated by computing the primary nonlinear normal mode of the identified model and comparing it with measurements.