Machine learning-aided process design using limited experimental data: A microwave-assisted ammonia synthesis case study

Abstract

An open research question lies in how machine learning (ML) can accelerate the design optimization of chemical processes which are at very early experimental development stage with limited data availability. As an example, this article investigates the design of an intensified microwave-assisted ammonia production reactor with 46 experimental data. We present an integrated approach of neural networks and synthetic minority oversampling technique to quantify the nonlinear input-output relationships of this process. For ammonia concentration predictions at discrete operating conditions, the approach demonstrates 96.1% average accuracy over other ML methods (e.g., support vector regression 84.2%). The approach has also been applied for continuous optimization, identifying the optimal synthesis conditions at 597.37 K, 0.55MPa with feed flow rate of 1.67 ×10⁻³ m³/s kg and hydrogen to nitrogen ratio of 1 which is consistent with experimental observations. The data-driven model enables to integrate this reactor with existing ammonia production infrastructure and benchmark with conventional techniques.