A Stochastic Optimization based on Sample Average Approximation for a Boiler Process. Issue 7 (2022)

• Record Type: Journal Article
• Authors: de Almeida, Gustavo Matheus; Park, Song Won; Lee, Chang Jun
• Is Part Of: IFAC-PapersOnLine. Volume 55:Issue 7(2022)
• Page Start: 550
• Page End: 555
• Publication Date: 2022
• Subjects: Stochastic Optimization -- SAA -- PSO -- SVM -- Chemical recovery boiler -- Pulp mill; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2022.07.501
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: The goal of this study is to investigate stochastic optimal solutions for a boiler process in a pulp mill. The objective function is a steam generation while two pollutant emissions should be complied with their regulations. Support Vector Regression (SVR) is employed to build empirical models for representing a boiler process and air temperatures are considered as uncertainties. To make stochastic problems, Sample Average Approximation (SAA) based on Monte-Carlo sampling is introduced and Particle Swarm Optimization (PSO) technique is applied to investigate stochastic solutions. The results show that the stochastic optimal solutions can provide improved performances compared to the deterministic approach.