Application of Nonlinear-Autoregressive-Exogenous model to predict the hysteretic behaviour of passive control systems

Chan, Ricky; Yuen, Jason K.K.; Lee, Eric Wai Ming; Arashpour, Mehrdad

doi:10.1016/j.engstruct.2014.12.007

Cited by 45 publications

(24 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The NARX neural network model can realize an overall input/output black-box mapping by the multilayer perceptron incorporating time delay unit and output feedback in the input layer (Chan et al, 2015). As shown in Figure 2, the NARX model is expressed in terms of the discrete-time input-output equation as:…”

Section: Narx Neural Network Identification Modeling Of Mr Dampermentioning

confidence: 99%

An Optimal NARX Neural Network Identification Model for a Magnetorheological Damper With Force-Distortion Behavior

Liu

Chen

et al. 2020

Front. Mater.

View full text Add to dashboard Cite

This paper presents an optimal NARX neural network identification model for a magnetorheological (MR) damper with the force-distortion behavior. An intensive experimental study is conducted for designing the NARX network architecture to enhance modeling accuracy and availability, and the activation function selection, weights, and biases of the selected network are optimized by differential evolution algorithm. Different experimental training and validation samples are used for network training. The prediction capability of the optimal NARX model is verified by new measured test data. The test and comparative results show that the optimal NARX network model can satisfactorily emulate the dynamic behavior of MR damper and effectively capture its distortion behavior occurred with the increased current. The developed inverse NARX network model can effectively estimate the required current and track desired damping force. Moreover, the effects of different noise disturbance on the NARX network model performance are analyzed, and the model error varies slightly with a small noise disturbance. The accuracy of the results supports the use of this modeling technique for identifying irregular non-linear models of MR damper and similar devices.

show abstract

Section: Narx Neural Network Identification Modeling Of Mr Dampermentioning

confidence: 99%

An Optimal NARX Neural Network Identification Model for a Magnetorheological Damper With Force-Distortion Behavior

Liu

Chen

et al. 2020

Front. Mater.

View full text Add to dashboard Cite

show abstract

“…Nonlinear random demand rates and process times were accommodated into the model. In a similar approach to Lee, Fung et al (2013) and Chan, Yuen et al (2015) demand rates and process times were not fit to the theoretical statistical distributions such as exponential or triangular, in order to increase the modeling precision. Instead, ARENA input analyzer was used to divide the actual data into groups and calculate the proportion in each group.…”

Section: Simulation Experimental Frameworkmentioning

confidence: 99%

“…Improvements made by a ratedriven environment can be extended by controlling the number of houses under construction or work-in-process ( ). Maintaining a constant work-in-process (CONWIP) has positive effects on tangible performance metrics of production homebuilders (Liu 2010, Arashpour andArashpour 2015). In fact, this workflow control protocol turns the network of trades into a closed queuing system where unauthorized jobs from outside cannot enter.…”

Section: Introductionmentioning

confidence: 99%

Quantitative Analysis of Rate-Driven and Due Date–Driven Construction: Production Efficiency, Supervision, and Controllability in Residential Projects

Arashpour

Wakefield

Blismas

et al. 2016

J. Constr. Eng. Manage.

Self Cite

View full text Add to dashboard Cite

Concerns about production efficiency, quality and affordability in the residential construction indicate there may be benefits in adopting alternative production control strategies to those traditionally used. Reducing adverse effects of exogenous variability in demand and endogenous variability in process are the ultimate goals of production control strategies. For residential construction this means controlling the number of houses under construction and controlling the start rate of new house constructions. The aim of this investigation is to compare and contrast the outcomes of these two production management strategies. Production data of two volume house builders in Victoria and Queensland, Australia, were collected. Tangible performance metrics of builders were analyzed and compared using principles of the queuing theory. Then numerous simulation experiments were designed and run in order to analyze different what-if scenarios in the building environment. A special purpose simulation template was developed in order to define a cap for production and limit the number of houses under construction based on actual demand and available capacity. The findings reveal that rate-driven construction outperforms due-date-driven construction in terms of three studied performance measures. This investigation adopts an original and quantitative approach towards three production aspects of efficiency, supervision and controllability. Therefore it contributes to the body-of-knowledge by developing an in-depth insight into superior performance of the rate-driven control strategy with the Page 1 of 28 intention of improving production output and long term sustainability of residential and other sub-sectors of the construction industry.

show abstract

“…It also converges much faster and generalizes better than other networks (Lin et al, 1996;Çoruh et al, 2014). It has been demonstrated that NARX is capable of capturing the dynamics of nonlinear complex systems (Diaconescu, 2008;Chan et al, 2015). Moreover, NARX performs favorably on long-term dependencies (Rahimi et al, 2018).…”

Section: Introductionmentioning

confidence: 98%

Prediction of Long-Term Near-Surface Temperature Based on NA-CORDEX Output

Li¹,

Li²,

Zhang³

et al. 2019

J ENVIRON INFORM LET

View full text Add to dashboard Cite

Temperature is one of the most important parameters in climate modeling, as it has significant impacts on various geophysical processes such as evaporation and precipitation. Applying multiple climate models for prediction generally outperforms the use of individual climate models, and neural networks perform well at capturing nonlinear relationships, which can provide more reliable temperature projections. In this study, three neural network algorithms, including Multi-layer Perceptron (MLP), Time-lagged Feed-forward Neural Networks (TLFN) and Nonlinear Auto-Regressive Networks with exogenous inputs (NARX), were used to develop data-driven models for predicting daily mean near-surface temperature based on North American Coordinated Regional Downscaling Experiment (NA-CORDEX) output. A case study of Big Trout Lake in Ontario, Canada was carried out to demonstrate the applications and to evaluate the performance of the proposed neural network based models. The results showed that MLP, TLFN, and NARX performed well in generating accurate daily near-surface temperature predictions with the coefficient of determination (R 2) values above 0.84. The three neural network based models had similar performance with no significant difference in terms of root mean square error and R 2. Neural network based climate prediction models outperformed each of the individual regional climate models and generated smoother predicttions with less fluctuation. This study provides a technical basis for generating reliable predictions of daily temperature using neural networks based model.

show abstract

Application of Nonlinear-Autoregressive-Exogenous model to predict the hysteretic behaviour of passive control systems

Cited by 45 publications

References 27 publications

An Optimal NARX Neural Network Identification Model for a Magnetorheological Damper With Force-Distortion Behavior

An Optimal NARX Neural Network Identification Model for a Magnetorheological Damper With Force-Distortion Behavior

Quantitative Analysis of Rate-Driven and Due Date–Driven Construction: Production Efficiency, Supervision, and Controllability in Residential Projects

Prediction of Long-Term Near-Surface Temperature Based on NA-CORDEX Output

Contact Info

Product

Resources

About