Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ROM-Based Stochastic Optimization for a Continuous Manufacturing Process

Raul Cruz-Oliver, Luis Monzon, Edgar Ramirez-Laboreo, Jose-Manuel Rodriguez-Fortun

Abstract

This paper proposes a model-based optimization method for the production of automotive seals in an extrusion process. The high production throughput, coupled with quality constraints and the inherent uncertainty of the process, encourages the search for operating conditions that minimize nonconformities. The main uncertainties arise from the process variability and from the raw material itself. The proposed method, which is based on Bayesian optimization, takes these factors into account and obtains a robust set of process parameters. Due to the high computational cost and complexity of performing detailed simulations, a reduced order model is used to address the optimization. The proposal has been evaluated in a virtual environment, where it has been verified that it is able to minimize the impact of process uncertainties. In particular, it would significantly improve the quality of the product without incurring additional costs, achieving a 50% tighter dimensional tolerance compared to a solution obtained by a deterministic optimization algorithm.

ROM-Based Stochastic Optimization for a Continuous Manufacturing Process

Abstract

This paper proposes a model-based optimization method for the production of automotive seals in an extrusion process. The high production throughput, coupled with quality constraints and the inherent uncertainty of the process, encourages the search for operating conditions that minimize nonconformities. The main uncertainties arise from the process variability and from the raw material itself. The proposed method, which is based on Bayesian optimization, takes these factors into account and obtains a robust set of process parameters. Due to the high computational cost and complexity of performing detailed simulations, a reduced order model is used to address the optimization. The proposal has been evaluated in a virtual environment, where it has been verified that it is able to minimize the impact of process uncertainties. In particular, it would significantly improve the quality of the product without incurring additional costs, achieving a 50% tighter dimensional tolerance compared to a solution obtained by a deterministic optimization algorithm.
Paper Structure (16 sections, 7 equations, 7 figures, 2 tables)

This paper contains 16 sections, 7 equations, 7 figures, 2 tables.

Table of Contents

  1. Introduction
  2. System description and optimization strategy
  3. Process description
  4. Model-based process optimization
  5. Modeling
  6. Finite element model
  7. Reduced order model (ROM)
  8. Uncertainty modeling
  9. Optimization methodology
  10. Objectives and formulation
  11. Stochastic optimization algorithm
  12. Results
  13. Stochastic optimization repeatability
  14. Comparison with a deterministic strategy
  15. Further results and discussion
  16. ...and 1 more sections

Figures (7)

  • Figure 1: Extrusion line
  • Figure 4: Methodology outline. The blue and orange boxes correspond, respectively, to steps in the process and intermediate results. The result (green box) is the set of robust process parameters.
  • Figure 5: Probability density functions for the uncertain inputs
  • Figure 6: Variation in the geometry of the part at the beginning (a) and at the end (b) of the line
  • Figure 7: Cost distribution box plots of the Bayesian Optimization solutions. Percentile 99 highlighted in cyan, best solution marked in green.
  • ...and 2 more figures