Predicting Cycle-to-Cycle Variations in Liquid Methane Engines Using CTGAN-Augmented Machine Learning

It is imperative to comprehend the cyclical variations inherent in liquid methane engines (LMEs) across both design and operational domains. The theoretical thermal efficiency of LMEs is high at higher compression ratios, but the combustion instability also increases. Obtaining relevant metrics from bench experiments is difficult and time-consuming; therefore, in this study, we model tabular data using Conditional GAN (CTGAN) to model the tabular data and generated more virtual samples based on the experimental results of the key metrics (peak pressure, maximum pressure rise rate, and average effective pressure). Through this, a machine learning model was proposed that couples a random forest (RF) model with a Bayesian optimization machine learning model for predicting cyclic variation. The findings indicate that the Bayesian-optimized RF model demonstrates superiority in predicting the metrics with greater accuracy and reliability compared to the gradient boosting (XGBoost) and support vector machine (SVM) models. The R2 value of the former model is consistently greater than 0.75, and the root mean square error (RMSE) is typically lower than 0.3. This paper highlights the promising potential of the Bayesian-optimized RF model in predicting unknown cyclic parameters.