Autoregressive Exogenous Model Research Articles

The Reduced-Order Model for Droplet Drift of Aerial Spraying under Random Lateral Wind

The droplet drift during aerial spraying process of oilseed rape, which is induced by complex flow field including random lateral wind, is difficult to predict and suppress. In this study, the high-fidelity computational fluid dynamics (CFD) technique is employed to simulate the two-phase flow of droplets in the rotor flow field, and the influence of main operation parameters on spraying effect is investigated numerically. Furthermore, the mechanism of droplet deposition in various operation conditions is discussed according to the analysis of unsteady flow field characteristics. However, the simulation via CFD technique is time-consuming, and it is not suitable for multidisciplinary work and optimization design. To address such issue, a filter white Gaussian noise signal is used to mimic the random lateral wind, and the droplet drift distance is obtained numerically. Based on the input and output dataset of CFD, the recursive algorithm including nonlinear autoregressive exogenous model and surrogate-based recurrence framework and the deep learning method for time-series prediction called long short-term memory neural network are used to build the efficient reduced-order model, respectively. Numerical simulations show that the droplet drift distance can be predicted by measurable lateral wind speed via the reduced-order model approach, which agreed well with the results obtained via the CFD method. In addition, the reduced-order model could decrease computation cost by 6 orders of magnitude with an acceptable accuracy, which indicates that the proposed method could be used for the design of off-line closed-loop controller of a variable spraying system.

Comparison of adaptive pitch control strategies for a wind turbine benchmark model

PurposeThe wind turbine (WT) is a complex system subjected to wind disturbances. Because the aerodynamics is nonlinear, the control is thus challenging. For the variation of wind speed when rated power is delivered at rated wind speed, the power is limited to the rate by the pitching of the blades of the turbine. This paper aims to address pitch control with the WT benchmark model. The possible use of appropriate adaptive controller design that modifies the control action automatically identifying any change in system parameters is explored.Design/methodology/approachTo deal with pitch control problem when wind speed exceeds the rated wind speed of the WT, six digital self-tuning controller (STC) with different structures such as proportional integral (PI), proportional derivative (PD), Dahlin’s, pole placement, deadbeat and Takahashi has been taken herein. The system model is identified as a second-order autoregressive exogenous (ARX) model by three techniques for comparison: recursive least square method (RLS), RLS with exponential forgetting and RLS with adaptive directional forgetting identification methods. A comparative study of three identification methods, six adaptive controllers with the conventional PI controller and sliding mode controller (SMC), are shown.FindingsAs per the results, the best improvement in control of the output power by pitching in full load region of benchmark model is achieved by self-tuning PD controller based on RLS with adaptive directional forgetting method. The adaptive control design has a future in WT control applications.Originality/valueA comparative study of identification methods, six adaptive controllers with the conventional PI controller and SMC, are shown here. As per the results, the best improvement in control of the output power by pitching in the full load region of the benchmark model has been achieved by self-tuning PD controller. The best identification method or the system is RLS with an adaptive directional forgetting method. Instead of a step input response design for the controllers, the controller design has been carried out for the stochastic wind and the performance is adjudged by the normalized sum of square tracking error (NSSE) index. The validation of the proposed self-tuning PD controller has been shown in comparison to the conventional controller with Monte-Carlo analysis to handle model parameter alteration and erroneous measurement issues.

Adaptive model predictive control for actuation dynamics compensation in real-time hybrid simulation

Hybrid simulation is used to obtain the dynamic response of a system whose components consist of physical and numerical substructures. The coupling of these substructures is achieved by actuation systems, which are commanded in closed-loop control setting. To ensure high fidelity of such hybrid simulations, performing them in real-time is necessary. However, real-time hybrid simulation poses challenges since the inherent dynamics of the actuation system introduce time delays, thus modifying the dynamic response of the investigated system. Therefore, a tracking controller is required to adequately compensate for such time delays. In this study, a novel tracking controller is proposed for dynamics compensation in real-time hybrid simulations. It is based on adaptive model predictive control, a linear time-varying Kalman filter, and a real-time model identification algorithm. Within the latter, auto-regressive exogenous polynomial models are identified in real-time to estimate the changing plant dynamics. A parametric virtual case study, encompassing a virtual motorcycle, is used to validate the performance and robustness of the proposed controller. Results demonstrate the effectiveness of the proposed controller for real-time hybrid simulations.

Dynamic Modeling of a Nonlinear Two-Wheeled Robot Using Data-Driven Approach

A system identification of a two-wheeled robot (TWR) using a data-driven approach from its fundamental nonlinear kinematics is investigated. The fundamental model of the TWR is implemented in a Simulink environment and tested at various input/output operating conditions. The testing outcome of TWR’s fundamental dynamics generated 12 datasets. These datasets are used for system identification using simple autoregressive exogenous (ARX) and non-linear auto-regressive exogenous (NLARX) models. Initially the ARX structure is heuristically selected and estimated through a single operating condition. We conclude that the single ARX model does not satisfy TWR dynamics for all datasets in term of fitness. However, NLARX fitted the 12 estimated datasets and 2 validation datasets using sigmoid nonlinearity. The obtained results are compared with TWR’s fundamental dynamics and predicted outputs of the NLARX showed more than 98% accuracy at various operating conditions.

Investigation of Three-Dimensional Condensation Film Problem over an Inclined Rotating Disk Using a Nonlinear Autoregressive Exogenous Model.

This paper analyzed the three-dimensional (3D) condensation film problem over an inclined rotating disk. The mathematical model of the problem is governed by nonlinear partial differential equations (NPDE's), which are reduced to the system of nonlinear ordinary differential equations (NODE's) using a similarity transformation. Furthermore, the system of NODEs is solved by the supervised machine learning strategy of the nonlinear autoregressive exogenous (NARX) neural network model with the Levenberg–Marquardt algorithm. The dimensionless profiles of velocity, acceleration, and temperature are investigated under the effect of variations in the Prandtl number and normalized thickness of the film. The results demonstrate that increasing the Prandtl number causes an increase in the fluid's temperature profile. The solutions obtained by the proposed algorithm are compared with the state-of-the-art techniques that show the accuracy of the approximate solutions by NARX-BLM. The mean percentage errors in the results by the proposed algorithm for Θ(η), Ψ(η), k(η), −s(η), and (θ(η)) are 0.0000180%, 0.000084%, 0.0000135%, 0.000075%, and 0.00026%, respectively. The values of performance indicators, such as mean square error and absolute errors, are approaching zero. Thus, it validates the worth and efficiency of the design scheme.

A nonlinear autoregressive exogenous (NARX) model to predict nitrate concentration in rivers.

Forecasting nitrate concentration in rivers is essential for environmental protection and careful treatment of drinking water. This study shows that nonlinear autoregressive with exogenous inputs neural networks can provide accurate models to predict nitrate plus nitrite concentrations in waterways. The Susquehanna River and the Raccoon River, USA, were chosen as case studies. Water discharge, water temperature, dissolved oxygen, and specific conductance were considered exogenous inputs. The forecasting sensitivity to changes in the exogenous input parameters and time series length was also assessed. For Kreutz Creek at Strickler station (Pennsylvania), the prediction accuracy increased with the number of exogenous input variables, with the best performance achieved considering all the variables (R2 = 0.77). The predictions were accurate also for the Raccoon River (Iowa), although only the water discharge was considered exogenous input (South Raccoon River at Redfield-R2 = 0.94). Both short- and long-term predictions were satisfactory.

Mitigation of carbon footprint with 100% renewable energy system by 2050: The case of Galapagos islands

In this paper, a technical-economic study of the 100% renewable energy sources in the Galapagos islands is done. Historical consumption data for 2011–2020 have been considered to forecast the load curve. To achieve this goal, the load is forecasting by Nonlinear autoregressive exogenous neuronal network model for 2030 and 2050. The study focuses on supplying the energy demand of the islands with renewable sources, analyzing possible scenarios based on the current electricity system. The methodology studies the capacity of renewable sources to balance supply and demand through dispatch simulations using the EnergyPLAN software. The results show energy flows, costs and long-term energy balances (2050), with 100% renewable energy from several wind and photovoltaic combinations. Moreover, The precision of the demand forecast was 98.12% with a mean square error of 0.013%. The total annual cost decreases while the capacities of the renewable sources increase to a certain point of equilibrium. As salient features of the developed approach, various sensitivity analyzes are presented that allow understanding the uncertainties, scope and limitations of the proposed models.

A novel dynamic nonlinear partial least squares based on the cascade structure

AbstractFor the collinearity problem of input variables in actual industrial process modeling, a novel dynamic nonlinear partial least squares (PLS) approach is presented to solve this problem. In the proposed method, a novel cascade structure which is composed of an autoregressive exogenous model and a radial basis function neural network is introduced as the inner model of the conventional PLS method, so that the newly established PLS method has both dynamic and nonlinear characteristics. In this improvement, an external model for extracting the latent variables of input and output is established through the original PLS model, which eliminates the collinearity between original dependent variables, and then the aforementioned cascade framework is employed to describe the dynamic and nonlinear relationships between the input and output score variables. Furthermore, in order to estimate the unknown parameters of the established dynamic nonlinear inner model, a stochastic gradient algorithm and a forgetting factor stochastic gradient algorithm are presented. Additionally, a simple cross validation method is used to determine the orders of the inner model. Finally, a numerical simulation example and an application example are given to demonstrate the effectiveness of the proposed approach.

Correlation based neuro-fuzzy Wiener type wind power forecasting model by using special separate signals

The wind power system is characterized by complex structures, numerous effect elements, and complicated physical relationships, which bring great difficulties to establish the wind power forecasting model and result in the unsatisfactory prediction accuracy of wind power. In this paper, a correlation based neuro-fuzzy Wiener type wind power forecasting model is proposed by using special separate signals to decouple dynamic linear and static nonlinear characteristics of wind power systems for high-accuracy wind power forecasting. This method introduces an autoregressive exogenous model and fuzzy neural network to explore the underlying distribution characteristics of wind power systems by correlation analysis of the linear and nonlinear information contained in time-series data of the wind power system. In addition, in order to eliminate outliers in the original data set, an abnormal data cleaning approach combining quartile and two-stage clustering algorithm is employed to reduce the computation time and improve the model accuracy. Moreover, the convergence of the Wiener model is proved by the Lyapunov function. Simulation results verify the high accuracy and generalization ability of the proposed model both in the gale and breeze seasons.

A Learning-Based Method for Speed Sensor Fault Diagnosis of Induction Motor Drive Systems

This paper proposes a speed sensor fault diagnosis methodology based on a learning-based data-driven principle in induction motor drive systems. The proposed method is derived from signal estimation and residual evaluation. First, a speed estimator is designed with a nonlinear autoregressive exogenous (NARX) learning model and a randomized learning technique called random vector functional link (RVFL) network. A data pre-processing method by Discrete Wavelet Transform (DWT) is applied to better trace the signal trends, in order to further improve the speed estimation accuracy. After the estimation, the residual between measured and estimated signals can be obtained, and a decision-making mechanism is developed for fault diagnosis based on an outlier test. The offline test results show that the proposed method can accurately estimate the speed signal with a 1.554e-4 root mean square error (RMSE) and outperforms state-of-the-art methods. Moreover, real-time tests are also carried out to verify the feasibility and stability during the online stage. Moreover, the proposed approach does not require any motor parameters and other additional hardware, which makes it quite suitable for online practical applications.

Modeling and Control of Priority Queueing in Software Defined Networks via Machine Learning

Software Defined Networking (SDN) is a new architectural paradigm that enables programmable control of a network to make it more flexible and easier to manage. SDN architectures decouple control and forwarding functionalities, and enable switches and routers to be remotely configurable/ programmable in run-time by a controller. Modeling and optimization of such modern heterogeneous network infrastructures are key factors to achieve better performance, e.g. in terms of traffic flow improvement while reducing bandwidth allocation. Identifying an accurate model of a network device in SDNs (e.g., a switch or a router) is crucial in order to apply advanced techniques such as Model Predictive Control (MPC). However, such a problem is very challenging due to non-linearities and unavailability of internal variables measurements in real devices. To this aim, a promising direction is given by an appropriate integration of System Identification and Machine Learning techniques to obtain predictive models using historical data collected from the network thanks to the SDN paradigm. In this paper we apply a novel data-driven methodology to learn accurate models of the dynamical input-output behavior of a network’s switch device by appropriately combining AutoRegressive eXogenous (ARX) model identification with Regression Trees (RTs) and Random Forests (RFs). The advantage of such model is that it can be directly used to apply MPC (which just requires Quadratic Programming to be solved) to optimally control the queues’ bandwidth of the switch ports within the SDN paradigm.We validate our approach on an experimental emulation setup using the Mininet network emulator environment and a real dataset obtained from measurements of an Italian Internet Service Provider (Sonicatel S.r.l.). To this aim, we first develop a model of a real network switch, then implement MPC using the RYU controller, and finally demonstrate the benefits of the proposed dynamic queueing control methodology in terms of packet losses reduction and bandwidth saving, i.e. in terms of improvement of the Quality of Service.

Inferential Statistics and Machine Learning Models for Short-Term Wind Power Forecasting

The inherent randomness, intermittence and volatility of wind power generation compromise the quality of the wind power system, resulting in uncertainty in the system's optimal scheduling. As a result, it's critical to improve power quality and assure real-time power grid scheduling and grid-connected wind farm operation. Inferred statistics are utilized in this research to infer general features based on the selected information, confirming that there are differences between two forecasting categories: Forecast Category 1 (0–11 h ahead) and Forecast Category 2 (12–23 h ahead). In z-tests, the null hypothesis provides the corresponding quantitative findings. To verify the final performance of the prediction findings, five benchmark methodologies are used: Persistence model, LMNN (Multilayer Perceptron with LM learning methods), NARX (Nonlinear autoregressive exogenous neural network model), LMRNN (RNNs with LM training methods) and LSTM (Long short-term memory neural network). Experiments using a real dataset show that the LSTM network has the highest forecasting accuracy when compared to other benchmark approaches including persistence model, LMNN, NARX network, and LMRNN, and the 23-steps forecasting accuracy has improved by 19.61%.

Investigation of Inverter Temperature Prediction Model in Wind Farm Based on SCADA Data

The inverter is one of the key components of wind turbine, and it is a complex circuit composed of a series of components such as a variety of electronic components and power devices. Therefore, it is difficult to accurately identify the operation states of inverter and some problems regarding its own circuit, especially in the early stages of failure. However, if the inverter temperature prediction model can be established, the early states can be identified through the judgment of the output temperature. Accordingly, considering whether the inverter heats up normally from the perspective of heat dissipation, a method for the early operation state identification of the inverter is provided in this paper. A variable selection method based on fusion analysis of correlation and physical relationship is adopted to extract variables as input variables, which have high correlation with inverter temperature. Then multi-input and multi-output temperature prediction model of inverter is established based on a non-linear autoregressive exogenous model (NARX) network, and the prediction temperature residual is used as the real-time standard to evaluate the inverter states. For validating this, the validity and reliability of the established temperature prediction model are verified through case analysis, and the performance comparison with various models demonstrates that the proposed method has higher accuracy. The construction method of the prediction model can be used for reference to other aspects of wind turbine. All these bring huge benefits to wind energy industry.

Simultaneous adaption of the gain and phase of a generalized transfer function for aortic pressure waveform estimation

GoalThis paper proposes and validates a completely adaptive transfer function (CATF) based on an autoregressive exogenous (ARX) model which adjusts the gain and phase of a generalized transfer function (GTF) simultaneously to estimate the aortic pressure waveform from a brachial pressure waveform. MethodsInvasive aortic and brachial pressure waveforms were recorded from 34 subjects for the validation of the proposed method. Individual transfer functions (ITFs) were trained based on the pressure waveforms using an ARX model. The GTF was derived by averaging the ITFs. CATF was then obtained by adjusting both the gain and phase of the GTF using regression formulas calculated from the ITFs and brachial hemodynamic parameters. Meanwhile the quantitative contributions of the adaption of gain and phase of the GTF were investigated respectively. The root-mean-square-error of the total waveform and absolute errors of common hemodynamic indices including systolic and diastolic blood pressures (SBP and DBP, respectively), pulse pressure (PP) and augmentation index were used to evaluate the performance of the proposed method in the data divided into low, middle and high PP amplification groups. ResultsThe CATF achieved lower errors for DBP and PP in the low PP amplification group (1.79 versus 2.10 mmHg and 5.08 versus 6.23 mmHg, respectively, both P < 0.05) and PP in the middle amplification group (1.43 versus 1.92 mmHg, P < 0.05) compared with the GTF. SignificanceThe proposed method provides a step towards the development of an improved and clinically useful non-invasive approach for estimating the aortic pressure waveform from a peripheral pressure waveform.

Incorporating Prior Information in Adaptive Model Predictive Control for Multivariable Artificial Pancreas Systems.

Adaptive model predictive control (MPC) algorithms that recursively update the glucose prediction model are shown to be promising in the development of fully automated multivariable artificial pancreas systems. However, the recursively updated glycemic prediction models do not explicitly consider prior knowledge in the identification of the model parameters. Prior information of the glycemic effects of meals and physical activity can improve model accuracy and yield better glycemic control algorithms. A glucose prediction model based on regularized partial least squares (rPLS) method where the prior information is encoded as the regularization term is developed to provide accurate predictions of the future glucose concentrations. An adaptive MPC is developed that incorporates dynamic trajectories for the glucose setpoint and insulin dosing constraints based on the estimated plasma insulin concentration (PIC). The proposed adaptive MPC algorithm is robust to disturbances caused by unannounced meals and physical activities even in cases with missing glucose measurements. The effectiveness of the proposed adaptive MPC based on rPLS is investigated with in silico subjects of the multivariable glucose-insulin-physiological variables simulator (mGIPsim). The efficacy of the proposed adaptive MPC strategy in regulating the blood glucose concentration (BGC) of people with T1DM is assessed using the average percent time in range (TIR) for glucose, defined as 70 to 180 mg/dL inclusive, and the average percent time in hypoglycemia (<70 and >54 mg/dL) and level 2 hypoglycemia (≤54 mg/dL). The TIR for a cohort of 20 virtual subjects of mGIPsim is 81.9% ± 7.4% (with no hypoglycemia or severe hypoglycemia) for the proposed MPC compared with 73.9% ± 7.6% (0.2% ± 0.1% in hypoglycemia and 0.1% ± 0.1% in level 2 hypoglycemia) for an MPC based on a recursive autoregressive exogenous (ARX) model. The adaptive MPC algorithm that incorporates prior knowledge in the recursive updating of the glucose prediction model can contribute to the development of fully automated artificial pancreas systems that can mitigate meal and physical activity disturbances.

Cutting Process Model Design of Cutter Suction Dredger Based on Auto Regressive eXogenous and Radial Basis Function model

The dredging operation of the strander dredger is complex, and the mathematical model established according to its key equipment characteristics is not possible to describe such a system having time degeneration and non-linear. Therefore, based on the analysis of mud formation process of dredger, RBF-ARX model is used to model the cutting process, and mud concentration is taken as the output. This modeling method is a combination model based on the theory of Auto-Regressive eXogenous (ARX) model and Gauss radial basis function (Radial Basis Function) neural network (RBF). The comparison between the simulation results and the actual data shows that the model can accurately describe the dynamic characteristics of cutter suction dredger in the cutting process.

A novel artificial neural network for power quality improvement in AC microgrid

The microgrid concept provides a flexible power supply to the utility where the conventional grid is unable to supply. The microgrid structure is based on renewable energy sources known as distributed generators (DGs) and the power network. Nevertheless, the power quality (PQ) is a great challenge in the microgrid concept. Particularly the inclusion of renewable energy sources into the conventional grids increases the problems in the quality of power, like voltage sag/swell, oscillatory transient, voltage flickering, and voltage notching which reduces the quality and reliability of the power supply. In this paper, a microgrid is considered which consists of PV cells as DG, battery energy storage system (BESS), and a novel control strategy known as the nonlinear autoregressive exogenous model (NARX). The proposed controller is an improved artificial neural network (ANN). The various case studies like sag/swell, unbalanced condition, and voltage deviation have been simulated with the model. The comprehensive simulation results are compared with the proportional-integral (PI) controller. Hence in this paper, the robustness of the proposed controller has been studied through different situations.

Concurrent auto-regressive latent variable model for dynamic anomaly detection

With Industry 4.0, temporal relations between process and quality variables become increasingly complex. Some dynamic supervised learning algorithms are designed to extract their dynamic cross-relations, but auto-correlations among quality variables are rarely considered, which, however, can provide additional valuable information. This article proposes a novel dynamic auto-regressive latent variable model (DALVM) to capture both auto and cross correlations from high-dimensional time series data. DALVM is designed to maximize the covariance between current quality score and the weighted sum of past quality and process scores, and an auto-regressive exogenous inner model is developed for consistency purpose. Further, a concurrent anomaly detection system is developed based on DALVM, referred to as ConDALVM, which conducts subsequent decompositions in the extracted latent spaces. ConDALVM realizes a comprehensive monitoring for both static and dynamic anomalies in process and quality spaces. The superiority of the methods is demonstrated through a numerical simulation and two industrial processes.

Adaptive compound control based on generalized Bouc-Wen inverse hysteresis modeling in piezoelectric actuators.

This paper focuses on the study of the dynamic hysteresis compensation and control of piezoelectric actuators so as to improve the swing accuracy of the piezoelectric fast steering mirror mechanism in the photoelectric compound-axis control system. Moreover, in view of the rate dependence and asymmetry of piezoelectric hysteresis, and the complex inversion process of the generalized Bouc-Wen hysteresis model, the Hammerstein dynamic inverse hysteresis model of the piezoelectric actuator is established. To be specific, the static nonlinearity and rate dependence of the piezoelectric inverse hysteresis are represented by the generalized Bouc-Wen inverse model and the auto-regressive exogenous model, respectively, and the parameters of the model are identified by the adaptive beetle swarm optimization algorithm. In the process of the open-loop feedforward compensation, the dynamic positioning accuracy of the piezoelectric actuator is greatly affected by various disturbances and the uncertainty of the hysteresis compensation model. In this context, a compound control strategy that combines the feedforward compensation with the single-neuron adaptive proportion-integration-differentiation control is proposed based on the Hammerstein dynamic inverse hysteresis model of the piezoelectric actuator. The experimental results verify the effectiveness and superiority of the proposed control strategy.

Neural Forecasting System of Regional Cooperative Systems Innovative Activity Results

The analysis of changes in the external and internal environment of organisations, requirements for ensuring long-term sustainability and competitiveness in modern conditions suggests the need to develop instrumental support for decision-making support processes in the implementation of innovative projects of cooperative formations. Significant expenditures of financial and time resources allow to determine the priority problem – the insufficient development of systems for reducing uncertainty in interaction with the processes of scientific and industrial cooperation, which determine the disproportions of the resulting economic indicators of the functioning of innovative activity in the region. The proposed solution is an implemented multiplatform software for neuro-cluster analysis of multiformat data, which is based on fuzzy data prediction algorithms based on a nonlinear autoregressive exogenous model. An important feature of the implemented software is an algorithm for optimising the processing of predicted data, based on distributed processing of big data using Microsoft Server operating system.