City Research Online

Abstract

High-pressure sectors like mining and construction require multi-stage screw compressors that can operate reliably at pressures over 16 bar. Single-stage compressors frequently encounter constraints such as elevated temperatures, rotor bending deformation, imperfect cooling effect of the injected oil, condensate, and diminished bearing longevity, rendering them inadequate for these specifications. This paper introduces a comprehensive modelling and optimisation approach for multi-stage screw compressors, integrating a physics-based chamber model with machine learning via Gaussian process regression. The framework employs Bayesian optimisation to methodically refine stage-specific parameters, enhancing performance and dependability while ensuring computing economy. The innovation is in its capacity to precisely forecast the performance of both individual and final stages, experimentally validated with a two-stage air screw compressor for water-well applications, attaining an error margin below 5%. A case study illustrated the framework’s efficacy by decreasing specific power usage by 2% via the optimisation of fluid injection parameters. This approach represents a significant advancement in compressor technology, providing a scalable and efficient solution for designing and optimising multi-stage screw compressors in high-pressure applications.

Publication Type:	Article
Additional Information:	This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Publisher Keywords:	Bayesian optimisation, Chamber model, Compressor performance modelling, Fluid injection parameters, Gaussian process regression (GPR), Multi-stage screw compressors
Subjects:	T Technology > TA Engineering (General). Civil engineering (General)
Departments:	School of Science & Technology School of Science & Technology > Department of Engineering
SWORD Depositor:	Symplectic Administrator

Export

Downloads