Estimation of Turbidity in Water Treatment Plant using Hammerstein-Wiener and Neural Network Technique

Gaya, Muhammad Sani; Zango, Muttaqa Uba; Yusuf, Lukman; Mustapha, Mamunu; Muhammad, Bashir Bala; Sani, Ashiru; Tijjani, Aminu Tijjani Aminu; Wahab, Norhaliza Abdul; Khairi, Mohd

doi:10.11591/ijeecs.v5.i3.pp666-672

Cited by 41 publications

(26 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HW model has the ability to be utilized in form of a black-box model. Whereby, it gives a flexible use of various parameters and (1) variables, and ensures that the basic and primary knowledge regarding the process of physical characteristics [16]. HW provides more satisfactory performance in various applications as compared to linear systems like the MLR and the non-linear systems such as ANN, since it considered the dual properties of the data set of both the non-linearity and linear properties of the data set [13].…”

Section: Hammerstein-wiener Model (Hw)mentioning

confidence: 99%

Advanced chromatographic technique for performance simulation of anti-Alzheimer agent: an ensemble machine learning approach

et al. 2020

View full text Add to dashboard Cite

This work employs the application of three artificial intelligence (AI) techniques namely; support vector machine (SVM), Hammerstein-Wiener (HW) and multi-layer perceptron (MLP) for predicting the qualitative properties of an anti-Alzheimer agent using high-pressure liquid chromatography technique. The mobile phase (inform of acetonitrile and trifluoroacetic acid) and the column temperature was used as the predictors in modelling the maximum retention time (tR-max) and resolution (Resol.) as the output variables of the analyte. The measured and predicted values were checked using three performance indices including; Nash-Sutcliffe efficiency (NSE), correlation coefficient (CC) as the goodness of fits and a statistical error inform of root-mean-square error (RMSE). The results obtained demonstrated the promising ability of AI-based models in modelling the qualitative properties of the anti-Alzheimer agent. Observation of different outputs of the AI-based models at various time intervals showed the necessity of ensembling the outputs of the AI-based models. Therefore, simple average ensemble and support vector machine ensemble (SVM-E) were employed to enhance the performance skills of the simple models. The comparative performance of SVM-E inform of NSE indicated its ability in boosting and enhancing the performance skills of the single models SVM, MLP and HW models up to 5, 13 and 20% respectively in the testing stage for modelling tR-max.

show abstract

Section: Hammerstein-wiener Model (Hw)mentioning

confidence: 99%

Advanced chromatographic technique for performance simulation of anti-Alzheimer agent: an ensemble machine learning approach

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Fig. 5 illustrates the general overview of the structure of H-W that being used in this study [15]. It consists of a linear dynamic with two nonlinear steady-state blocks [16].…”

Section: B Hammerstein-wiener Modellingmentioning

confidence: 99%

The Correlation Model of Head Roll and Lateral Acceleration during Curve Driving via Hammerstein-Wiener

Saruchi¹,

Ariff²,

Zamzuri³

et al. 2019

IJITEE

View full text Add to dashboard Cite

Generally, passengers are more prone to Motion Sickness (MS) than the drivers. The difference of their severity level of MS is due to their different head movement towards the direction of the lateral acceleration. During cornering, the passengers tend to tilt their heads according to the direction, while the drivers tends to tilt their head opposite to the direction. Based on this fact, the passengers are able to reduce their MS level if they can imitate the driver’s head movement or lessen their head tilt angle towards the direction of the lateral acceleration. However, it is easier to design MS mitigation method based on the head tilt movement strategy if the mathematical expression of their head behaviour is known beforehand. On way to derive the mathematical expression is by modelling the relationship between the occupant’s head tilt movements and the vehicle’s lateral acceleration during curve driving. Therefore, this study proposed the usage of Hammerstein-Wiener (H-W) method for the modelling purpose. Experiment is set up to obtain the naturalistic data for the modelling process. The modelling process is carried out by varying the input output nonlinearities estimators. The results show that the estimated output responses from the H-W models are similar with the real responses taken from the experiment.The derived models for both passenger and driver have 68.88% and 66.32% of Best Fit (BF) percentages. With further study, the passenger’s and driver’s models which are developed by the proposed H-W modelling strategy are expected to contribute in MS minimisation studies

show abstract

“…1 . Finally, genetic information corresponding to pole-zero classification is initialized directly using mutation M.4 (26) times.…”

Section: Pole-zero Classificationmentioning

confidence: 99%

“…Block-oriented models are attractive for their simplicity and great capabilities to model nonlinear dynamic systems [23][24][25][26][27][28]. Specifically, Wiener-Hammerstein models have proved to be able describe several systems like a paralyzed 2 Complexity skeletal muscle [29,30], a limb reflex control system [31], a DC-DC converter [32], a heat exchanger system and a superheater-desuperheater in a boiler system [33], and a thermal process [34], among others [35].…”

Section: Introductionmentioning

confidence: 99%

WH‐EA: An Evolutionary Algorithm for Wiener‐Hammerstein System Identification

et al. 2018

View full text Add to dashboard Cite

Current methods to identify Wiener-Hammerstein systems using Best Linear Approximation (BLA) involve at least two steps. First, BLA is divided into obtaining front and back linear dynamics of the Wiener-Hammerstein model. Second, a refitting procedure of all parameters is carried out to reduce modelling errors. In this paper, a novel approach to identify Wiener-Hammerstein systems in a single step is proposed. This approach is based on a customized evolutionary algorithm (WH-EA) able to look for the best BLA split, capturing at the same time the process static nonlinearity with high precision. Furthermore, to correct possible errors in BLA estimation, the locations of poles and zeros are subtly modified within an adequate search space to allow a fine-tuning of the model. The performance of the proposed approach is analysed by using a demonstration example and a nonlinear system identification benchmark.

show abstract

Estimation of Turbidity in Water Treatment Plant using Hammerstein-Wiener and Neural Network Technique

Cited by 41 publications

References 8 publications

Advanced chromatographic technique for performance simulation of anti-Alzheimer agent: an ensemble machine learning approach

Advanced chromatographic technique for performance simulation of anti-Alzheimer agent: an ensemble machine learning approach

The Correlation Model of Head Roll and Lateral Acceleration during Curve Driving via Hammerstein-Wiener

WH‐EA: An Evolutionary Algorithm for Wiener‐Hammerstein System Identification

Contact Info

Product

Resources

About