Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Accelerating process control and optimization via machine learning: A review

Ilias Mitrai, Prodromos Daoutidis

TL;DR

Recent advances in (i) the representation of decision-making problems for machine learning tasks, (ii) algorithm selection, and (iii) algorithm configuration for monolithic and decomposition-based algorithms are discussed.

Abstract

Process control and optimization have been widely used to solve decision-making problems in chemical engineering applications. However, identifying and tuning the best solution algorithm is challenging and time-consuming. Machine learning tools can be used to automate these steps by learning the behavior of a numerical solver from data. In this paper, we discuss recent advances in (i) the representation of decision-making problems for machine learning tasks, (ii) algorithm selection, and (iii) algorithm configuration for monolithic and decomposition-based algorithms. Finally, we discuss open problems related to the application of machine learning for accelerating process optimization and control.

Accelerating process control and optimization via machine learning: A review

TL;DR

Recent advances in (i) the representation of decision-making problems for machine learning tasks, (ii) algorithm selection, and (iii) algorithm configuration for monolithic and decomposition-based algorithms are discussed.

Abstract

Process control and optimization have been widely used to solve decision-making problems in chemical engineering applications. However, identifying and tuning the best solution algorithm is challenging and time-consuming. Machine learning tools can be used to automate these steps by learning the behavior of a numerical solver from data. In this paper, we discuss recent advances in (i) the representation of decision-making problems for machine learning tasks, (ii) algorithm selection, and (iii) algorithm configuration for monolithic and decomposition-based algorithms. Finally, we discuss open problems related to the application of machine learning for accelerating process optimization and control.

Paper Structure

This paper contains 29 sections, 4 equations, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. The algorithm configuration and selection problems
  3. The algorithm selection problem
  4. Algorithm configuration
  5. Relation between algorithm selection and configuration
  6. Decision-making problems as inputs to ML models
  7. Vectorial feature representation
  8. Graph Representation
  9. Graph representation with nodal and edge features
  10. Learning to select a solution strategy
  11. Learning to configure an algorithm
  12. Configuring monolithic solvers
  13. Initialization
  14. ML for preprocessing
  15. ML for branch and bound
  16. ...and 14 more sections

Figures (5)

  • Figure 1: High level overview of ML-based solution approaches for algorithm selection and configuration
  • Figure 2: Vectorial feature representation of an optimization problem
  • Figure 3: Graph representation of an optimization problem
  • Figure 4: Graph representation with features of a mixed integer linear optimization problem
  • Figure 5: Branch and bound tree for a mixed integer linear optimization problem with two binary variables

Theorems & Definitions (1)

  • Remark 1