System Identification Model Research Articles

Auxiliary model nonlinear innovation least squares algorithm for identification ship 4-DOF via full-scale test data

For the ship motion with large inertia coupled system identification modeling inaccuracy, the ship scale effect and the existence of partial unmeasured ship data problems. In this paper, an auxiliary model nonlinear innovation least squares identification algorithm is proposed. The new algorithm uses the output of the auxiliary model instead of the unmeasurable variables in the full-scale test data of the ship, and optimizes the error using the tangent function. Compared with the existing algorithm, the error of the improved algorithm decreases with the increase of time and continuously approaches to zero, which greatly improves the identification accuracy and convergence efficiency. The results show that the improved algorithm has significant identification accuracy and reliability. The identification method designed in this paper can be applied to the field of ship intelligent navigation engineering.

Auxiliary model-based maximum likelihood multi-innovation recursive least squares identification for multiple-input multiple-output systems

The aim of this paper is to propose novel identification methods for multiple-input multiple-output systems. Through decomposing a system into subsystems, the system identification model is derived. Based on the obtained sub-model, an auxiliary model-based maximum likelihood recursive least squares algorithm is derived for parameter estimation. For further enhancing the estimation accuracy, the auxiliary model-based maximum likelihood multi-innovation recursive least squares algorithm (AM-ML-MIRLS) is proposed based on the proposed algorithm. Simulation results test the proposed algorithms are all effective, and proves that the proposed AM-ML-MIRLS algorithm has the superior performances in capturing the dynamic properties of the system.

Assessment of hybrid machine learning models for non-linear system identification of fatigue test rigs

The prediction of system responses for a given fatigue test bench drive signal is a challenging problem, since highly dynamic loads from measurement campaigns must be reproduced accurately. Linear frequency response function models are commonly used for this system identification task, but energy intensive experimental iterations are required to account for system non-linearities. Two novel hybrid modeling strategies are suggested, which augment existing approaches using non-linear Long Short-Term Memory networks. These are trained and deployed on short subsequences of measurement data and recombined using a windowing technique, which enables their application to measurement data with high sampling rates. In addition to fatigue test bench commissioning, these hybrid models can also be employed in the field of virtual sensing. The approach is tested using non-linear experimental data from a servo-hydraulic test rig and this dataset is made publicly available. A variety of metrics in time and frequency domains, as well as fatigue strength under variable amplitudes, are employed in the evaluation. It is shown, that hybrid models can successfully use frequency response function models as a linear baseline estimate, which is further improved by Long Short-Term Memory networks to enable non-linear predictions.

Identification of nonlinear system model and inverse model based on conditional invertible neural network

In applications such as adaptive inverse control, internal model control, and active noise control, the identification accuracy of the system model and the inverse model directly affects the performance. However, it is not easy to identify inverse models for nonlinear systems. Moreover, existing methods require two identification calculations to obtain the system model and the inverse model. Therefore, an identification method of nonlinear system model and inverse model based on conditional invertible neural network (cINN) is proposed. The invertible structure of cINN enables simultaneous approximation of complex nonlinear functions and simultaneous acquisition of the corresponding inverse functions. Consequently, both the nonlinear system model and the inverse model can be identified concurrently through cINN. Moreover, the identification performance of the cINN-based method is validated and applied to disturbance cancellation in a classical nonlinear simulation system. Finally, the inverse model of the actuator is identified by cINN, and the inverse model is applied to the nonlinear compensation of the actuator.

Exploiting the capacity of deep networks only at the training stage for nonlinear black-box system identification

To benefit from the modeling capacity of deep models in system identification without worrying about inference time, this study presents a novel training strategy that uses deep models only during the training stage. For this purpose, two separate models with different structures and goals are employed. The first one is a deep generative model aiming at modeling the distribution of system output(s), called the teacher model, and the second one is a shallow basis function model, named the student model, fed by system input(s) to predict the system output(s). That means these isolated paths must reach the same ultimate target. As deep models show a great performance in modeling highly nonlinear systems, aligning the representation space learned by these two models makes the student model inherit the teacher model’s approximation power. The proposed objective function consists of the objective of each student and teacher model, adding up with a distance penalty between the learned latent representations. The simulation results on three nonlinear benchmarks show a comparative performance with examined deep architectures applied on the same benchmarks. Algorithmic transparency and structure efficiency are also achieved as byproducts.

Tracking the impact of heavy metals on human health and ecological environments in complex coastal aquifers using improved machine learning optimization.

The rising heavy metal (HM) pollution in coastal aquifers in rapidly urbanizing areas such as Dammam leads to significant risks to public health and environmental sustainability, challenging compliance with Environmental Protection Agency (EPA) guidelines, World Health Organization (WHO) standards, and Sustainable Development Goals (SDGs) related to clean water and life on land. This study developed the predictive-based monitoring of HM concentrations, including cadmium (Cd), chromium (Cr), and mercury (Hg) in the coastal aquifers of Dammam, influenced by industrial, agricultural, and urban activities. For this purpose, dynamic system identification and machine learning (ML) models integrated with three ensemble techniques, namely, simple averaging (SAE), weighted averaging (WAE), and neuro-ensemble (N-ESB), were employed to enhance the accuracy, reliability, and efficiency of environmental monitoring systems. The experimental data were calibrated and validated in addition to k-fold cross-validation to ensure the predictive skills of the models. The methodology integrates extensive data collection across varied land uses in Dammam and accurate model calibration and validation phases to develop highly accurate predictive models. The findings proved that the N-ESB and Hammerstein-Wiener (HW) models surpassed other models in predicting the concentrations of all HM. For Cd, the N-ESB model achieved a root mean square error (RMSE = 0.0010mg/kg). Similarly, Cr demonstrated superior performance (RMSE = 0.0179mg/kg). Further numerical results indicated that the HW algorithm proved the most effective for Hg, with RMSE = 0.0000mg/kg. The quantitative comparison suggested that the N-ESB model's consistently high performance and low error rates make it an optimal choice for real-time, precise monitoring and management of HM pollution in coastal aquifers. The outcomes of this research highlighted the importance of integrating advanced predictive modeling techniques in environmental science, providing significant and practical implications for policymaking and ecological management.

Application of the Mask R‐CNN model to cold front identification in Eurasia

AbstractCold fronts often bring catastrophic weather events, which are exacerbated under global warming. Thus, the automatic and objective identification of cold fronts will be helpful for accurate forecasting and comprehensive analysis of cold fronts. Recently, machine learning methods have been applied to meteorological study. In this study, a cold front identification method based on the deep learning model Mask R‐CNN is proposed to automatically identify cold fronts from massive data. The Mask R‐CNN method shows high accuracy after the comparison with traditional methods and is effective for identifying the cold fronts in both continuous time and extreme precipitation events. Based on the obtained cold‐front samples, we conduct some statistical analysis. The results show that the frequency of cold front is unevenly distributed over Eurasia, with the highest in the Daxing'anling region and the mid‐latitude storm axis, especially in winter. The method and results presented in this study may have some implications for the application of deep learning models in weather system identification.

Heart Signal Acquisition Based System Autoregressive Identification Models

A system identification (SI) model can be constructed without any prior knowledge of the nature or physics of the relationship that has been involved. It is therefore appropriate to examine the question of (heart rate). In this paper, a simple and efficient hardware design is implemented to acquire the heart signal with the help of several linear models of SI. The relationships between different system identification models are discussed with detailed justification of the aid of these typical types. And then characterize the methods that fit the system structure to measure data input and output, as well as the most basic characteristics of the resulting models. For evaluation, compare between SI models to validate the results.

Identification of the existing Integrated Farming Systems in Udaipur District of Rajasthan

The integrated farming system (IFS) is an integrative whole-farm-oriented technique mainly used to resolve the problems of small and marginal farmers to enhance income and employment, living standards, etc. Due to numerous crises and challenges such as unawareness, poverty, droughts, dry climate, the small and marginal distribution of land, etc., the identification of an appropriate integrated farming system model is highly required. So, this research aims to deliver a solution for the identification and finalization of the IFS model which is a critical task in front of farm families, Agri-scientists, policy-makers, and business organizations. This study is conducted through a field survey in the district of Udaipur, Rajasthan. This work experimented with randomly selecting 4 panchayat samitis out of 20 panchayat samitis, 4 villages selected from each panchayat samiti ee to identify existing integrated farming systems among farm families. This study observed the prominent integrated farming system model among the considered models. This work identifies the IFS models which are the most prominent farming system (M1: crop+ dairy) and are adopted by most farm families. This research work also identified integrated farming models M1 and M2 as the most preferred, profitable, and very suitable for business decision-making. Similarly, M3 and M4 are also good but less preferred than M1 and M2.

Scenario based optimisation over uncertain system identification models

Models of dynamical systems are often built from observed data using system identification techniques, and the uncertainty in the model parameters is commonly described using confidence regions to which the true model parameters belong with a certain probability. In this paper we propose methods which use the scenario approach to solve robust optimisation problems for model based design where there is uncertainty in the model parameters. The methods draw samples (scenarios) of the uncertain model parameters and solve an optimisation problem only involving the drawn scenarios. Both a Bayesian system identification setting where the model parameters are stochastic, and a non-Bayesian system identification setting where the model parameters are treated as being deterministic are considered. The Bayesian and non-Bayesian settings require different treatment, and whereas standard scenario optimisation theory can be directly utilised in the Bayesian setting, this is not the case in the non-Bayesian setting. For that reason the model class is restricted to linear regression models with deterministic regressors in the non-Bayesian case. Algorithms are proposed for drawing samples of the parameters such that the uncertainties in the system identification models are reflected in the samples. Theoretical results are given bounding the probability that the found solution to the scenario optimisation problem will give a worse performance when applied to the true system than seen on the drawn scenarios. The methods are illustrated in simulation examples showing good performance.

Data-Driven Bayesian Inference for Stochastic Model Identification of Nonlinear Aeroelastic Systems

The objective of this work is to propose a data-driven Bayesian inference framework to efficiently identify parameters and select models of nonlinear aeroelastic systems. The framework consists of the use of Bayesian theory together with advanced kriging surrogate models to effectively represent the limit cycle oscillation response of nonlinear aeroelastic systems. Three types of sampling methods, namely, Markov chain Monte Carlo, transitional Markov chain Monte Carlo, and the sequential Monte Carlo sampler, are implemented into Bayesian model updating. The framework has been demonstrated using a nonlinear wing flutter test rig. It is modeled by a two-degree-of-freedom aeroelastic system and solved by the harmonic balance methods. The experimental data of the flutter wing is obtained using control-based continuation techniques. The proposed methodology provided up to a 20% improvement in accuracy compared to conventional deterministic methods and significantly increased computational efficiency in the updating and uncertainty quantification processes. Transitional Markov chain Monte Carlo was identified as the optimal choice of sampling method for stochastic model identification. In selecting alternative nonlinear models, multimodal solutions were identified that provided a closer representation of the physical behavior of the complex aeroelastic system than a single solution.

Unmanned Aerial Vehicle-Based Structural Health Monitoring and Computer Vision-Aided Procedure for Seismic Safety Measures of Linear Infrastructures.

Computer vision in the structural health monitoring (SHM) field has become popular, especially for processing unmanned aerial vehicle (UAV) data, but still has limitations both in experimental testing and in practical applications. Prior works have focused on UAV challenges and opportunities for the vibration-based SHM of buildings or bridges, but practical and methodological gaps exist specifically for linear infrastructure systems such as pipelines. Since they are critical for the transportation of products and the transmission of energy, a feasibility study of UAV-based SHM for linear infrastructures is essential to ensuring their service continuity through an advanced SHM system. Thus, this study proposes a single UAV for the seismic monitoring and safety assessment of linear infrastructures along with their computer vision-aided procedures. The proposed procedures were implemented in a full-scale shake-table test of a natural gas pipeline assembly. The objectives were to explore the UAV potential for the seismic vibration monitoring of linear infrastructures with the aid of several computer vision algorithms and to investigate the impact of parameter selection for each algorithm on the matching accuracy. The procedure starts by adopting the Maximally Stable Extremal Region (MSER) method to extract covariant regions that remain similar through a certain threshold of image series. The feature of interest is then detected, extracted, and matched using the Speeded-Up Robust Features (SURF) and K-nearest Neighbor (KNN) algorithms. The Maximum Sample Consensus (MSAC) algorithm is applied for model fitting by maximizing the likelihood of the solution. The output of each algorithm is examined for correctness in matching pairs and accuracy, which is a highlight of this procedure, as no studies have ever investigated these properties. The raw data are corrected and scaled to generate displacement data. Finally, a structural safety assessment was performed using several system identification models. These procedures were first validated using an aluminum bar placed on an actuator and tested in three harmonic tests, and then an implementation case study on the pipeline shake-table tests was analyzed. The validation tests show good agreement between the UAV data and reference data. The shake-table test results also generate reasonable seismic performance and assess the pipeline seismic safety, demonstrating the feasibility of the proposed procedure and the prospect of UAV-based SHM for linear infrastructure monitoring.

Flight-Data-Based High-Fidelity System Identification of DJI M600 Pro Hexacopter

Research and industrial application can require custom high-level controllers for industrial drones. Thus, this paper presents the high-fidelity dynamic and control model identification of the DJI M600 Pro hexacopter. This is a widely used multicopter in the research and industrial community due to its high payload capability and reliability. To support these communities, the focus of control model identification was on the exploration and implementation of DJI Onboard Software Development Kit (OSDK) functionalities, also including some unconventional special modes. Thus, the resulting model can be controlled with the same OSDK functionalities as the real drone, making control development and application time effective. First, the hardware and software structure of the additional DJI M600 onboard system are introduced. Then, the postulated dynamic and control system models are shown. Next, real flight test campaigns generating data for system identification are presented. Then, the mass and inertial properties are estimated for TB47S and TB48S battery sets and the custom Forerunner UAV payload. Dynamic system model identification includes the aerodynamic effects and considers hover, vertical, and horizontal forces together with static horizontal wind components and finally the rotational moments and dynamics. The control system components were identified following the structure of OSDK, including vertical, horizontal, and yaw loops. After identification, the model was validated and refined based on an unused flight test and software-in-the-loop simulation data. The simulation is provided by DJI and was also compared to real flight results. This comparison showed that the DJI simulation covers the dynamics of the real drone well, but it requires being connected to the drone and needs the controllers onboard to be implemented in advance, which limits applicability and increases development time. This was another motivation to introduce a standalone simulation in Matlab Simulink, which covers all the important modes of OSDK control and can be run solely in Matlab without any hardware support. The constructed model will be published for the benefit of the research and industrial community.

Uncertainty Evaluation of a Gas Turbine Model Based on a Nonlinear Autoregressive Exogenous Model and Monte Carlo Dropout.

Gas turbines are thermoelectric plants with various applications, such as large-scale electricity production, petrochemical industry, and steam generation. In order to optimize the operation of a gas turbine, it is necessary to develop system identification models that allow for the development of studies and analyses to increase the system's reliability. Current strategies for modeling complex and non-linear systems can be based on artificial intelligence techniques, using autoregressive neural networks of the NARX and LSTM type. In this context, this work aims to develop a model of a gas turbine capable of estimating the rotation speed of the turbine and simultaneously estimating the uncertainty associated with the estimation. These methodologies are based on artificial neural networks and the Monte Carlo dropout simulation method. The results were obtained from experimental data from a 215 MW gas turbine, getting the best model with a MAPE of 0.02% and an uncertainty associated with the turbine rotation speed of 2.2 RPM.

Digital twin of heat exchange station

The article describes the identification of a heat exchanger system using PLC for measurement, followed by system model identification and reconstruction in Matlab Simulink and SIMIT. The root-mean-square error of the identified system was 2.49 % on training data and 5.33 % in the validation scenario. The system model is suitable for predicting and simulating errors and anomalies; it can be used for the optimisation of control processes or system parameters. Therefore, the model can serve as an educational tool, allowing training of students, operators and other experts. They can experiment without fear of damaging components and without having to wait for the long-time transients of a real system.

Application of Improved WOA in Hammerstein Parameter Resolution Problems under Advanced Mathematical Theory

With the development of industrial demand, precise identification of system models is currently required in the field of industrial control, which limits the whale search algorithm. In response to the fact that whale optimization algorithms are prone to falling into local optima and the identification of important Hammerstein models ignores the issue of noise outliers in actual industrial environments, this study improves the whale algorithm and constructs a Hammerstein model identification strategy for nonlinear systems under heavy‐tailed noise using the improved whale algorithm. Results showed that it had a lower rank average and an average success rate of 95.65%. It found the global optimum when the number of iterations reached around 150 and had faster convergence speed and accuracy. In identifying Hammerstein model under heavy‐tailed noise, the average prediction recognition accuracy of the improved whale algorithm was 92.38%, the determination coefficient was 0.89, the percentage fitting error was 0.03, and the system error was 0.02. This research achievement has certain value in the field of industrial control and can serve as a technical reference.

System Identification Techniques for Soft Sensors and Multiphase Flow Metering

Production rates estimation and forecasting is a complex problem in multiphase flow systems, such as oil wells. In the oil and gas industry, this task is normally performed by first principles simulation models, which are costly to maintain and adjust. An alternative to this process could be black-box models based on historical data to perform this task. This work proposes to perform an extensive evaluation of existing regressors to create a black-box system identification model to predict oil well liquid flow rates. Improvement strategies such as the creation of error models, time series decomposition, and the use of current-time data are also evaluated. The final results demonstrated the importance of pressure and temperature data for the well flow rate determination and identified the use of current-time data as the best tested technique to improve the performance of the final model.

Physics-informed and black-box Identification of robotic actuator with a flexible joint

In robotics, precise models are critical for ensuring safety and functionality. However, acquiring a precise model characterizing a system’s dynamics can be challenging. One of the alternatives to address this issue is system Identification, which aims to obtain models through physical and experimental observations. In this manner, the developments in machine learning algorithms, such as neural networks, have significantly improved the modeling of complex and nonlinear phenomena. In this work, a mass-spring-damper (MSD) system and a low-cost original elastomer-based Series Elastic Actuators (eSEA) assembly are used to evaluate the performance of system Identification models. The black-box models selected are variations of the AutoRegressive Moving Average with eXogenous input (ARMAX) algorithm. The gray-box model aims to estimate the parameters of 4 friction models; the optimization is done utilizing physics-informed neural networks (PINNs). For both case studies, the PINNs outperformed the black-box models. In the didactic example, the parameters obtained are close to the ground truth, and the highest determinant coefficient obtained is 0.99. The friction model that best represents the robotic actuator is the LuGre model, with the parameters obtained using the PINNs, outperforming the best black-box model by lowering the mean absolute error (MAE) by 30.83%. With a determinant coefficient of 0.94, the model shows a high capacity for describing the multiple nonlinearities present in the system.

Integration of Vehicle Dynamic Model and System Identification Model for Extending the Navigation Service Under Sensor Failures

Accurate and reliable localization is of great importance for autonomous vehicles (AV). Mainstream localization approaches in autonomous vehicles (AV) are limited by the reliability of onboard sensors, which could be vulnerable to sensor failure, such as signal outages of the camera and signal spoofing of the global navigation satellite systems (GNSS). Different from these active or passive sensors, the vehicle dynamic model (VDM), which is the application of physical laws to a vehicle in motion, is environmentally independent and is capable of providing vehicle motion estimation continuously. However, the performance of the VDM-based motion estimation is dominated by the accuracy of the system dynamics model. To tackle this issue, this study proposes a sensor-free localization method VDM-SI by integrating system identification into the design of vehicle dynamic models (VDM). A system identification process based on low-order process models is proposed to identify the system dynamics of the AV, where the identified system responses are taken as the control input of VDM to estimate the vehicular positioning. The localization experiments in two scenarios show that the mean absolute translation error of VDM-SI can be reduced by 70% compared to conventional VDM methods. In addition, VDM-SI is experimentally proven to improve the localization performance of sensor fusion-based localization systems with high noise levels. Furthermore, in the application of re-localization after sensors fail and recover, VDM-SI shows strength in enhancing the security of AVs in extreme conditions.

Model-based safety analysis with time resolution (MBSA-TR) method for complex aerothermal–mechanical systems of aero-engines

Current aero-engine safety assessments mostly rely on experience-based safety analysis methods such as Fault Tree Analysis (FTA) or Failure Modes and Effects Analysis (FMEA). The progressively significant dynamic characteristics of aero-engines during their transition between states render these methods incapable of providing accurate quantitative safety guidance, which is vital for complex aerothermal–mechanical systems. To solve this problem, a Model-Based Safety Analysis with Time Resolution (MBSA-TR) method was established, which included system modeling, fault modeling, and Safety Critical Parameter (SCP) identification. An integrated system model combining the main gas path and air system was built based on dynamics principles, and it was capable of reflecting the dynamic characteristics of aero-engines. The fault model included several time-resolved sub-modules and interacted bidirectionally with the system model at each time step to realize time-sequential fault propagation. SCPs were defined as parametric analysis objectives, and they were identified using an FTA-like identification framework. Finally, a case study of a typical turbofan engine with low-pressure compressor blade fractures as the primary fault was analyzed. The results showed that some hazard risks are incapable of detection without time resolution. Thus, time resolution is indispensable for the safety evaluation of complex aerothermal–mechanical systems of aero-engines.