The Development of Machine Learning Models for Radial Compressor Monitoring With Instability Detection

Abstract

Modern radial compressors are designed for high performance and different applications while minimizing environmental impact. To extend the operating range efficiently, it is crucial to study these machines near their stability limits and understand the fluid dynamic mechanisms that trigger instability. Machine learning aids in developing pattern identification models for detecting compressor instability. In a prior study, a two-stage radial compressor for refrigerant gas underwent extensive simulation, capturing unsteady RANS conditions and generating a substantial dataset of pressure signals from multiple probes. Selected signals, coupled with detailed CFD post-processing, revealed fluid-dynamic structures near surge conditions. This study utilizes all pressure signals to assess the stage's operational state (stable, transient, or unstable/surge). Additionally, it aims to develop an algorithm that predicts flow patterns in different stage sections with minimal pressure signals at the rotor inlet, as a preliminary step towards creating a smart monitoring and diagnostic model for the compressor in a plant. The developed model consists of three sub-models, trained with CFD results obtained from URANS simulations. The three sub-models are a regression submodule, a classification submodule, and a forecasting algorithm. The regression submodule predicts diffuser static pressure fields, the classification submodule categorizes whether the compressor is in a critical condition or not, and the forecasting algorithm predicts the inducer pressure signals in the future impeller rotations according to the actual operation history. These sub-modules work together to forecast whether the compressor, according to the operation strategy, is going into instability conditions.