Optimizing the performance of screw compressors is critical for achieving high efficiency and reducing costs in various industrial and engineering applications. Often, the design and optimization processes are time-consuming owing to the underlying iterative complex analyses. In this context, the present research investigates the potential of Gaussian Process Regression (GPR) and Bayesian optimization for the prediction and optimization of the performance of an oil-flooded screw compressor. Specifically, the GPR-based surrogate model is developed to predict the compressor performance characteristics based on its four main geometrical design parameters such as wrap angle, relative length, tip speed of the male rotor and built-in volume ratio. The model is trained using a dataset comprising 19,200 data points relating the input design parameters with the compressor performance, obtained using physics-based multi-chamber thermodynamic models. While four different learning algorithms such as Support Vector Machine (SVM), Artificial Neural Network (ANN), Polynomial regression and GPR are explored, the GPR performed the best resulting in an R2 value of 0.99 for the test dataset after hyperparameter tuning. Further, the model is also experimentally validated on a completely unseen dataset, showing very good predictions with a maximum error of 5%. The resulting surrogate model is then used to optimize the compressor design parameters using Bayesian optimization. The results are compared with optimization using Genetic Algorithm (GA) and physics-based multi-chamber thermodynamic model. It was shown the proposed approach results in similar optimal design parameters but with a significantly less optimization time by a factor of 7. The study highlight the potential of machine learning-based prediction and optimization of screw compressors in engineering applications.
Read full abstract