This study employs statistical analysis to develop an artificial neural network (ANN) along with a computational fluid dynamics (CFD)-based methodology that can develop robust and accurate erosion prediction models. Solid particle erosion plays a critical role in the design and reliability of equipment employed in the oil and gas industry. Significant erosion occurs due to solid particle loading, especially in applications involving sand production. Computational fluid dynamics has emerged as powerful tool to predict erosion in recent years. The ability to simulate multiphase flows in complex geometries using CFD makes it a valuable and less-expensive method to predict erosion. Various empirical relations have been established to predict erosion using CFD. These methods often predict erosion regions accurately, but are typically highly inaccurate in predicting an erosion rate. An order-of-magnitude error is observed in many cases.
An extensive set of experimental data was available experiments conducted on 90-degree elbow, which was used for exploratory analysis and as target data set for simulations. The current in-house erosion model is studied as a baseline. Exploratory data analysis was performed on CFD output parameters to identify influences and correlation to solid particle erosion. An artificial neural network with multilayer feed-forward model with back-propagation algorithm and Levenberg-Marquardt training was developed. This model, along with Bayesian regularization, reduced cumulative error to less than 10%, compared to more than 40% in the baseline Baker Hughes model.