Machine Learning-Aided Process Design for Microwave-Assisted Ammonia Production

Abstract

Machine learning (ML) has become a powerful tool to analyze complex relationships between multiple variables and to unravel valuable information from big datasets. However, an open research question lies in how ML can accelerate the design and optimization of processes in the early experimental development stages with limited data. In this work, we investigate the ML-aided process design of a microwave reactor for ammonia production with exceedingly little experimental data. We propose an integrated approach of synthetic minority oversampling technique (SMOTE) regression combined with neural networks to quantitatively design and optimize the microwave reactor. To address the limited data challenge, SMOTE is applied to generate synthetic data based on experimental data at different reaction conditions. Neural network has been demonstrated to effectively capture the nonlinear relationships between input features and target outputs. The softplus activation function is used for a smoother prediction compared to the Rectified Linear Unit activation function. Ammonia concentration is predicted using pressure, temperature, feed flow rate, and feed composition ratio as input variables. For point-wise prediction based on discrete operating conditions, the proposed SMOTE integrated neural network approach outperforms with 96.1% accuracy compared to neural networks (without SMOTE), support vector regression, and linear regression. The multi-variate prediction trends are also validated which are critical for design optimization.