Artificial Neural Network and Adaptive Neuro-Fuzzy Interface System Modelling to Predict Thermal Performances of Thermoelectric Generator for Waste Heat Recovery

Garud, Kunal Sandip; Seo, Jae-Hyeong; Cho, Chongpyo; Lee, Moo‐Yeon

doi:10.3390/sym12020259

Cited by 41 publications

(21 citation statements)

References 40 publications

(59 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…66 All input-output values of training data set are imported in the neuro-fuzzy modular in form of neurons. 67 Depending on the imported training data, type, number and boundary range of membership functions are decided. This is done in the grid partition section of the modular.…”

Section: Adaptive Neuro-fuzzy Interface System (Anfis)mentioning

confidence: 99%

“…These decided rules are trained using suitable training algorithm such as, back propagation or hybrid. 52,67 In addition, maximum epoch number is defined for training. Training of rules is done using suitable algorithm till maximum epoch or till point where error between the forecasted and actual output values of training data set is below permissible value.…”

Section: Adaptive Neuro-fuzzy Interface System (Anfis)mentioning

confidence: 99%

“…In neuro‐fuzzy modeling, total input‐output data is split into training and validation groups 66 . All input‐output values of training data set are imported in the neuro‐fuzzy modular in form of neurons 67 . Depending on the imported training data, type, number and boundary range of membership functions are decided.…”

Section: Artificial Intelligence (Ai) Techniquesmentioning

confidence: 99%

See 2 more Smart Citations

A review on modeling of solar photovoltaic systems using artificial neural networks, fuzzy logic, genetic algorithm and hybrid models

2020

Self Cite

View full text Add to dashboard Cite

The uncertainty associated with modeling and performance prediction of solar photovoltaic systems could be easily and efficiently solved by artificial intelligence techniques. During the past decade of 2009 to 2019, artificial neural network (ANN), fuzzy logic (FL), genetic algorithm (GA) and their hybrid models are found potential artificial intelligence tools for performance prediction and modeling of solar photovoltaic systems. In addition, during this decade there is no extensive review on applicability of ANN, FL, GA and their hybrid models for performance prediction and modeling of solar photovoltaic systems. Therefore, this article focuses on extensive review on design, modeling, maximum power point tracking, fault detection and output power/efficiency prediction of solar photovoltaic systems using artificial intelligence techniques of the ANN, FL, GA and their hybrid models. In addition, the selected articles on the solar radiation prediction using ANN, FL, GA and their hybrid models are also summarized. Total of 122 articles are reviewed and summarized in the present review for the period of 2009 to 2019 with 90 articles in the field of {ANN, FL, GA and their hybrid models} + solar photovoltaic systems and 32 articles in the field of {ANN, FL, GA and their hybrid models} + solar radiation. The review shows the suitability and reliability of ANN, FL, GA and hybrid models for accurate prediction of the solar radiation and the performance characteristics of solar photovoltaic systems. In addition, this review presents the guidance for the researchers and engineers in the field of solar photovoltaic systems to select the suitable prediction tool for enhancement of the performance characteristics of the solar photovoltaic systems and the utilization of the available solar radiation.

show abstract

Section: Adaptive Neuro-fuzzy Interface System (Anfis)mentioning

confidence: 99%

Section: Adaptive Neuro-fuzzy Interface System (Anfis)mentioning

confidence: 99%

Section: Artificial Intelligence (Ai) Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

A review on modeling of solar photovoltaic systems using artificial neural networks, fuzzy logic, genetic algorithm and hybrid models

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Equations 5- 7are used to calculate the coefficient of determination (R 2 ), root mean square error (RMSE) and coefficient of variance (COV), respectively [43].…”

Section: Battery Temperature Rise Rate =mentioning

confidence: 99%

“…Based on the results discussed in Sections 5.4.1 and 5.4.2, ANN model with LM-Tan-20 algorithm is suggested to accurately predict the heating performances of battery and HVAC for the integrated system with serial and parallel circuits. Kunal et al proposed an ANN model with the optimum structure as the Levenberg-Marquardt training algorithm and Tan-sigmoidal transfer function for the accurate performance prediction [43]…”

Section: Integrated System With Serial Circuitmentioning

confidence: 99%

Experimental Study on Heating Performances of Integrated Battery and HVAC System with Serial and Parallel Circuits for Electric Vehicle

et al. 2021

Self Cite

View full text Add to dashboard Cite

The objective of the present study is to conduct experiments for investigating heating performances of integrated system with serial and parallel circuits for battery and heating ventilation and air conditioning system (HVAC) of electric vehicles under various operating conditions. In addition, the artificial neural network (ANN) model is proposed to accurately predict the heating performances of integrated system with serial and parallel circuits for battery and HVAC. A test bench of integrated system with serial and parallel circuits has been developed for establishing the trade-off between battery heating and HVAC heating. The heating performances namely, battery out temperature, battery temperature rise rate, battery heating capacity, HVAC heating capacity and total heating capacity are evaluated experimentally for the integrated system with serial and parallel circuits. The behavior of various heating performances is evaluated under influence of flow rate and heater power. Battery out temperature reaches 40 °C within 10 min with rise rate of 2.17 °C/min for the integrated system with serial circuit and that within 20 min with rise rate of 1.22 °C/min for the integrated system with parallel circuit. Integrated system with serial circuit shows higher HVAC heating capacity than integrated system with parallel circuit which are 5726.33 W and 3869.15 W, respectively. ANN model with back-propagation algorithm, Levenberg-Marquardt training variant, Tan-sigmoidal transfer function and 20 hidden neurons presents the accurate prediction of heating performances of the integrated system with serial and parallel circuits for battery and HVAC.

show abstract

Computational fluid dynamics based Taguchi analysis on shear stress in microfluidic cerebrovascular channels

Garud

Jeong

Lee

2023

Numer Methods Biomed Eng

Self Cite

View full text Add to dashboard Cite

The cerebrovascular blood vessels feed necessary agents such as oxygen, glucose, and so forth. to the brain which maintains the smooth functioning of the human body. However, the blood-brain barrier as a vascular border restricts the entry of drugs that can be necessary for the treatment of neurological disorders. The fluid shear stress in the cerebrovascular blood vessels may regulate the drug delivery in the interface between the cerebrovascular blood vessels and the brain. The intensity of influence by various factors that affects the shear stress in the cerebrovascular blood vessels is scarcely addressed in the present study. A hybrid approach of computational fluid dynamics and Taguchi analysis is proposed to evaluate the influence of various geometrical and operating factors on the shear stress in the microfluidic cerebrovascular channel. Furthermore, the non-Newtonian behavior of blood flow is considered to evaluate the shear stress in the microfluidic cerebrovascular channel. The Newtonian and six non-Newtonian fluids models of Carreau, Carreau-Yasuda, Casson, Cross, Ostwald-de Waele, and Herschel-Bulkley are numerically tested under various conditions of the flow rate, width, and height of the channel to find the viscosity influence on the shear stress. The Taguchi analysis consisting of range and variance analyses is applied to the L 16 orthogonal array to evaluate the effect of various factors on shear stress in terms of influence order, range, F value, and percentage contribution. The parameters for the considered six non-Newtonian fluid models are proposed to accurately map the viscosity behavior with shear strain compared to the actual blood flow behavior. The Newtonian, Carreau, and Carreau-Yasuda non-Newtonian fluid models are found accurately with maximum errors between the experimental and numerical shear stress results as 2.17%, 1.30%, and 1.48%, respectively. The shear stress decreases with an increase in the width and height of the channel and a decrease in the viscosity for all flow rates. The porosity is evaluated as a highly influential factor followed by the flow rate, width, and height of the channel in decreasing order based on their effects on the shear stress. The modified shear stress equation is proposed with an accuracy of 0.96 by integrating the effect of porosity in addition to width, height, flow rate, and viscosity. The in-vitro microfluidic cerebrovascular model could be designed and manufactured based on the proposed results on influence order, F value, and

show abstract

Artificial Neural Network and Adaptive Neuro-Fuzzy Interface System Modelling to Predict Thermal Performances of Thermoelectric Generator for Waste Heat Recovery

Cited by 41 publications

References 40 publications

A review on modeling of solar photovoltaic systems using artificial neural networks, fuzzy logic, genetic algorithm and hybrid models

A review on modeling of solar photovoltaic systems using artificial neural networks, fuzzy logic, genetic algorithm and hybrid models

Experimental Study on Heating Performances of Integrated Battery and HVAC System with Serial and Parallel Circuits for Electric Vehicle

Computational fluid dynamics based Taguchi analysis on shear stress in microfluidic cerebrovascular channels

Contact Info

Product

Resources

About