A Levy flight-based grey wolf optimizer combined with back-propagation algorithm for neural network training

Amirsadri, Shima; Mousavirad, Seyed Jalaleddin; Ebrahimpour-Komleh, Hossein

doi:10.1007/s00521-017-2952-5

Cited by 113 publications

(46 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The meta‐heuristic algorithms are divided to three principal categories concluded (a) Physics‐based (PB) algorithms (for instance gravitational search algorithm [GSA]), (b) Swarm intelligence (SI) algorithms (such as grey wolf optimizer [GWO] and particle swarm optimization [PSO]), and (c) artificial bee colony (ABC) and evolutionary algorithms (such as genetic algorithm [GA]) (Amirsadri, Mousavirad, & Ebrahimpour‐Komleh, ; Mirjalili, Mirjalili, & Lewis, ). GWO was first suggested by Mirjalili et al () which is a potent model in solving of complex equations such as drying process.…”

Section: Introductionmentioning

confidence: 99%

“…Anyway, mathematical modeling is very complex and time consuming to estimate the mass properties according to the input effects. Therefore, artificial neural networks (ANNs) technique as a powerful tool provides a platform where solve these problems with logical precision and low computation times instead of mathematical modeling in drying process (Afkhamipour, Mofarahi, Borhani, & Zanganeh, 2018 (Amirsadri, Mousavirad, & Ebrahimpour-Komleh, 2018;Mirjalili, Mirjalili, & Lewis, 2014). GWO was first suggested by Mirjalili et al (2014) which is a potent model in solving of complex equations such as drying process.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Use of artificial intelligence for the estimation of effective moisture diffusivity, specific energy consumption, color and shrinkage in quince drying

Taghinezhad

Kaveh

Jahanbakhshi

et al. 2020

J Food Process Engineering

View full text Add to dashboard Cite

In the study, drying process of quince fruit was accomplished in a microwave‐convective dryer (MCD). The experiments were carried out at microwave power levels of 100, 200, and 300 W, air temperatures of 40, 55, and 70°C, and air velocities of 0.5, 1, and 1.5 m/s. Nevertheless, three artificial intelligence techniques consisted of artificial neural networks (ANNs), particle swarm optimizer (PSO), and grey wolf optimizer (GWO) were evaluated to predict the parameters of Deff, SEC, ΔE, and Sb. In the evaluation the data by ANNs, input parameters of networks consisted the values of air temperature, microwave power, and air velocity. According to the results, the maximum values of effective moisture diffusivity ( Deff) and specific energy consumption (SEC) were 1.71 × 10−9 m2/s and 126.07 kWh/kg, respectively. In addition, minimum values of total change in color (ΔE) and shrinkage ( Sb) of quince achieved 10.85 and 33.85%, respectively. For predicting all parameters, three models used in the study represented good predictive capability with R2 > 0.97. The obtained results showed that the GWO model had better predictive performance than the ANN and PSO models. Practical Application Drying food and agricultural products by application of microwave‐hot air blend dryers can be a good alternative to hot air and microwave dryers. Microwave energy infiltrates the product and facilitates heat release from the product and thus reduces drying time compared to single dryers. The main aim of applying such different models, mathematical simulation or modeling in the drying technology of agricultural products is to transform physical qualities and their interactions into numerical quantities and mathematical relationships.

show abstract

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

Use of artificial intelligence for the estimation of effective moisture diffusivity, specific energy consumption, color and shrinkage in quince drying

Taghinezhad

Kaveh

Jahanbakhshi

et al. 2020

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…The meta‐heuristic algorithms are categorized into main groups includes Physics‐based algorithms, Swarm intelligence, and Artificial bee colony (Amirsadri, Mousavirad, & Ebrahimpour‐Komleh, ). The reason for increasing the application of such optimizer techniques is their high performance in estimating the global optimum.…”

Section: Introductionmentioning

confidence: 99%

“…The meta-heuristic algorithms are categorized into main groups includes Physics-based algorithms, Swarm intelligence, and Artificial bee colony (Amirsadri, Mousavirad, & Ebrahimpour-Komleh, 2017).…”

Section: Introductionmentioning

confidence: 99%

Using PSO and GWO techniques for prediction some drying properties of tarragon (Artemisia dracunculus L.)

Karami

Kaveh

Mirzaee‐Ghaleh

et al. 2018

J Food Process Engineering

View full text Add to dashboard Cite

In this article, the effects of air temperature and velocity on drying characteristics of tarragon (Artemisia dracunculus L.) were investigated. The experiments were done at four temperatures of 40, 50, 60, and 70 °C and three air velocities of 1, 1.5, and 2 m/s. According to the results, the drying term of tarragon reduced significantly with increasing drying air temperature. The values of effective moisture diffusivity (Deff) were ranged between 1.34 × 10−10 and 2.74 × 10−10 m2/s. Also, by increasing drying air temperature the values of specific energy consumption (SEC) were decreased. The values of SEC were between 20.50 and 66.90 MJ/kg. Also Deff and SEC values were modeled by particle swarm optimizer (PSO) and gray wolf optimizer (GWO) algorithms. Drying air velocity and air temperature were considered as input parameters for the models. Based on three statistical parameters includes R2, MSE, and MAE for predicting Deff and SEC, GWO performance was better than the PSO. Practical applications The purpose of drying crops is decreasing of moisture content for providing secure storage and significant influence on the quality of dried crops. In this research, the effective moisture diffusivity (Deff) and specific energy consumption (SEC) values were modeled by PSO and GWO algorithms. The procedure can be applied in postharvest processing of medicinal plants.

show abstract

“…Considering the complexity of objective function and the intermittent nature of PV, the GWO optimizer may be trapped into local minima. To improve the performance of the grey wolf algorithm, Lévy flight is used to produce more efficient results [31]. If GWO cannot find the optimum results in a certain number of iterations, a more efficient search based on Lévy flight is done to prevent trapping to a local optimum.…”

Section: A the Grey Wolf Optimizer (Gwo)mentioning

confidence: 99%

Optimal Voltage Control in Distribution Systems With Intermittent PV Using Multiobjective Grey-Wolf-Lévy Optimizer

Mahmoud

Hussein

Abdel-Nasser

et al. 2020

IEEE Systems Journal

View full text Add to dashboard Cite

The intermittent photovoltaic (PV) units significantly affect the performance of distribution systems, and they often cause several operational problems, most importantly, voltage rise/drop. At high PV penetration, excessive tap movements of transformers and high curtailed PV power are expected to completely solve the voltage violation problem. In this paper, we propose an optimal voltage control method for distribution systems considering the number of tap movements of transformers and the active power curtailment of PV units. The objective function of the proposed method comprises: 1) voltage drop violation (VDV), 2) voltage rise violation (VRV), 3) tap movement rate (TMR) of transformers, and 4) curtailed power of PV (CPPV). A multi-objective grey wolf optimizer integrated with a Lévy mutation operator (GWO-Lévy) is formulated to accurately solve the voltage control problem. A 24-hour simulation is performed on the 119-bus distribution system with PV and different types of loads. The performance of GWO-Lévy is compared with three other optimizers, finding that it achieves the best performance. The simulation results demonstrate the efficacy of the proposed method for solving the voltage violation problem with PV while simultaneously optimizing TMR and CPPV.

show abstract

A Levy flight-based grey wolf optimizer combined with back-propagation algorithm for neural network training

Cited by 113 publications

References 42 publications

Use of artificial intelligence for the estimation of effective moisture diffusivity, specific energy consumption, color and shrinkage in quince drying

Use of artificial intelligence for the estimation of effective moisture diffusivity, specific energy consumption, color and shrinkage in quince drying

Using PSO and GWO techniques for prediction some drying properties of tarragon (Artemisia dracunculus L.)

Optimal Voltage Control in Distribution Systems With Intermittent PV Using Multiobjective Grey-Wolf-Lévy Optimizer

Contact Info

Product

Resources

About