Multiobjective Bayesian optimization on HPGR
(2025) In Master's Theses in Mathematical Sciences FMSM01 20252Mathematical Statistics
- Abstract
- When applying Bayesian optimization (BO) algorithms which utilizes Gaussian processes (GP) models, several components can be adapted to suit different systems and optimization objectives. In this paper, we explore and evaluate a set of such modifications to tailor the algorithm for
a high-pressure grinding rolls (HPGR) system. The system is represented by a steady-state simulator modeling the HPGR machine, used in ore comminution. The primary goal of the optimization is to evaluate the possibility of using Bayesian optimization on the HPGR-system to
generate recommendations for its control settings, and how the BO should be set up and tuned for this purpose. We investigate the effects of different covariance functions, mean functions,... (More) - When applying Bayesian optimization (BO) algorithms which utilizes Gaussian processes (GP) models, several components can be adapted to suit different systems and optimization objectives. In this paper, we explore and evaluate a set of such modifications to tailor the algorithm for
a high-pressure grinding rolls (HPGR) system. The system is represented by a steady-state simulator modeling the HPGR machine, used in ore comminution. The primary goal of the optimization is to evaluate the possibility of using Bayesian optimization on the HPGR-system to
generate recommendations for its control settings, and how the BO should be set up and tuned for this purpose. We investigate the effects of different covariance functions, mean functions, and acquisition functions on optimization performance by testing them on the default system
parameters, and validating the results on time series of varying feed material. Among the tested configurations, the final recommendation for the model settings were using the radial basis function (RBF) covariance and a constant mean function for all objectives and constraints. The
recommended acquisition function was a version of Expected Hypervolume Improvement (EHVI). (Less) - Popular Abstract
- How can optimal settings be found for a machine whose inner workings are too complex to model directly? This study shows that Bayesian optimization, a method for exploring unknown “black-box” systems, can reliably guide a key mining machine toward safer, more efficient operation.
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9216380
- author
- Mellring, Moa LU and Lacinai, Elliot
- supervisor
- organization
- course
- FMSM01 20252
- year
- 2025
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- Multi-objective optimization, Black-box optimization, Bayesian optimization (BO), Gaussian process (GP), high-pressure grinding rolls (HPGR), covariance function, mean-value function, acquisition function
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMS-3547-2025
- ISSN
- 1404-6342
- other publication id
- 2025:E109
- language
- English
- id
- 9216380
- date added to LUP
- 2025-12-22 15:12:00
- date last changed
- 2025-12-22 15:12:00
@misc{9216380,
abstract = {{When applying Bayesian optimization (BO) algorithms which utilizes Gaussian processes (GP) models, several components can be adapted to suit different systems and optimization objectives. In this paper, we explore and evaluate a set of such modifications to tailor the algorithm for
a high-pressure grinding rolls (HPGR) system. The system is represented by a steady-state simulator modeling the HPGR machine, used in ore comminution. The primary goal of the optimization is to evaluate the possibility of using Bayesian optimization on the HPGR-system to
generate recommendations for its control settings, and how the BO should be set up and tuned for this purpose. We investigate the effects of different covariance functions, mean functions, and acquisition functions on optimization performance by testing them on the default system
parameters, and validating the results on time series of varying feed material. Among the tested configurations, the final recommendation for the model settings were using the radial basis function (RBF) covariance and a constant mean function for all objectives and constraints. The
recommended acquisition function was a version of Expected Hypervolume Improvement (EHVI).}},
author = {{Mellring, Moa and Lacinai, Elliot}},
issn = {{1404-6342}},
language = {{eng}},
note = {{Student Paper}},
series = {{Master's Theses in Mathematical Sciences}},
title = {{Multiobjective Bayesian optimization on HPGR}},
year = {{2025}},
}