Successive approximate model based multi-objective optimization for an industrial straight grate iron ore induration process using evolutionary algorithm

Mitra, Kishalay; Majumder, Sushanta

doi:10.1016/j.ces.2011.03.041

Cited by 26 publications

(17 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to its strong nonlinear routing capability between inputs and outputs, a feed forward network was adopted consisting of an input layer, a hidden layer, and an output layer. The tangent sigmoid function is used as the hidden nodes activation function [10] and is given as Eq. (1).…”

Section: Ann Model Developmentmentioning

confidence: 99%

“…The above-mentioned configured network was trained by utilizing the Levenberg-Marquardt algorithm [10] for tuning the parameters, which gives a unique relationship between the input variables and output variable. During the training, the output of each of the nodes is calculated gradually up to the final layer using the randomized original guess values of the weights.…”

Section: Ann Model Developmentmentioning

confidence: 99%

“…During the training, the output of each of the nodes is calculated gradually up to the final layer using the randomized original guess values of the weights. Using the Levenberg-Marquardt algorithm [10], the error function is minimized, i.e., between the final output layer and real targeted value. The output from a single neural node is determined by summing all the weighted inputs and bias to the node and then subjecting it to the activation function of the node.…”

Section: Ann Model Developmentmentioning

confidence: 99%

“…Mathematical model development plays a crucial role for the optimal operation of a process. In recent years, artificial neural networks (ANNs) have found widespread applications [10]. They can handle even incomplete information and are efficient in determining quick predictions [11].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Data‐Driven Modeling of Biodiesel Production Using Artificial Neural Networks

Mogilicharla

Reddy

2021

Chem Eng & Technol

View full text Add to dashboard Cite

Data-driven modeling of biodiesel production was developed by simultaneous transesterification and esterification of rapeseed oil and myristic acid with methanol, without catalyst or with different amounts of sulfated zirconia catalyst. An artificial neural network (ANN)-based model was created with experimental literature data. The input data, i.e., reaction time, catalyst, temperature, and methanol-to-oil ratio, and output data, i.e., total fatty acid methyl ester and oleic acid methyl ester, were considered to develop the model. Multiple input single output (MISO) ANN architecture was taken to predict the above targeted two output parameters. The proposed ANN model is computationally efficient and works reasonably well when tested on biodiesel production for solving the MISO model.

show abstract

Section: Ann Model Developmentmentioning

confidence: 99%

Section: Ann Model Developmentmentioning

confidence: 99%

Section: Ann Model Developmentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Data‐Driven Modeling of Biodiesel Production Using Artificial Neural Networks

Mogilicharla

Reddy

2021

Chem Eng & Technol

View full text Add to dashboard Cite

show abstract

“…The sample selection for MOPs is more complicated than for SOPs, because one needs to consider both convergence and diversity [2]. In the literature, several approaches have been used, such as selecting a set of uniformly distributed samples in the objective space [3,9,33] or a set of isolated samples in the decision space [1,36], and using ExI [55], LCB [38] or expected hypervolume improvement [37,42].…”

Section: Updating the Surrogatesmentioning

confidence: 99%

Surrogate-Assisted Evolutionary Optimization of Large Problems

Chugh

Sun

Wang

et al. 2019

Studies in Computational Intelligence

View full text Add to dashboard Cite

This chapter presents some recent advances in surrogate-assisted evolutionary optimization of large problems. By large problems, we mean either the number of decision variables is large, or the number of objectives is large, or both. These problems pose challenges to evolutionary algorithms themselves, constructing surrogates and surrogate management. To address these challenges, we proposed two algorithms, one called kriging-assisted reference vector guided evolutionary algorithm (K-RVEA) for many-objective optimization, and the other called cooperative swarm optimization algorithm (SA-COSO) for high-dimensional single-objective optimization. Empirical studies demonstrate that K-RVEA works well for manyobjective problems having up to ten objectives, while SA-COSA outperforms the state-of-the-art algorithms on 200-dimensional single-objective test problems.

show abstract

Multi‐Objective Optimization Applications in Chemical Engineering

Sharma

Rangaiah

2013

Multi‐Objective Optimization in Chemical Engineering

View full text Add to dashboard Cite

Successive approximate model based multi-objective optimization for an industrial straight grate iron ore induration process using evolutionary algorithm

Cited by 26 publications

References 47 publications

Data‐Driven Modeling of Biodiesel Production Using Artificial Neural Networks

Data‐Driven Modeling of Biodiesel Production Using Artificial Neural Networks

Surrogate-Assisted Evolutionary Optimization of Large Problems

Multi‐Objective Optimization Applications in Chemical Engineering

Contact Info

Product

Resources

About