A data-driven surrogate-assisted evolutionary algorithm applied to a many-objective blast furnace optimization problem

By Tinkle Chugh, Nirupam Chakraborti, Karthik Sindhya, Yaochu Jin. 2017

120 citations recorded by the source corpus.

ABSTRACT A new data-driven reference vector-guided evolutionary algorithm has been successfully implemented to construct surrogate models for various objectives pertinent to an industrial blast furnace. A total of eight objectives have been modeled using the operational data of the furnace using 12 process variables identified through a principal component analysis and optimized simultaneously. The capability of this algorithm to handle a large number of objectives, which has been lacking earlier, results in a more efficient setting of the operational parameters of the furnace, leading to a precisely optimized hot metal production process.

Subfields: Control and Systems Engineering, Mechanical Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

1. Handing Wang
2. John James Doherty
3. Yaochu Jin
4. Bing Xue
5. Mengjie Zhang
6. Gary G. Yen

In Mechanical Engineering

1. Handing Wang
2. John James Doherty
3. Yaochu Jin
4. Kaisa Miettinen
5. Chaoli Sun
6. Tinkle Chugh

Citations in the corpus

• Surrogate-Assisted Evolutionary Deep Learning Using an End-to-End Random Forest-Based Performance Predictor (2020, methodology): “So far, the base algorithms commonly applied in offline SAEAs are data preprocessing [43], data mining [42], and ensemble learning [44], since they can effectively and robustly address the problems having limited training data.”
• Data-Driven Evolutionary Optimization: An Overview and Case Studies (2019, methodology): “In [37], 156 reference vectors were generated and 10 000 function evaluations using the Kriging models were performed.”
• Offline Data-Driven Evolutionary Optimization Using Selective Surrogate Ensembles (2019, methodology): “A wide range of real-world optimization problems can be solved only using offline data-driven optimization approaches, as no new data can be made available during the optimization [6], [37], [38].”
• Committee-Based Active Learning for Surrogate-Assisted Particle Swarm Optimization of Expensive Problems (2017, methodology): “In the literature, polynomial regression (PR) models [14], support vector machines [15], radial basis function (RBF) networks [16], [17], artificial neural networks [9], and Gaussian processes, also known as Kriging [18], [19] have been used to construct surrogates.”