Constructing first principles models is a challenging task for nonlinear and complex systems such as a wastewater treatment unit. In recent years, data-driven models are widely used to overcome the complexity. However, they often suffer from issues such as missing, low quality or noisy data. Transfer learning is a solution for this issue where knowledge from another task is transferred to target one to increase the prediction performance. In this work, the objective is increasing the prediction performance of an industrial wastewater treatment plant by transferring the knowledge of (i) an open-source simulation model that captures the underlying physics of the process, albeit with dissimilarities to the target plant, (ii) another industrial plant characterized by noisy and limited data but located in the same refinery, and (iii) the model in (ii) and making the objective function of the training problem physics informed where the physics information derived from the open-source model in (ii). The results have shown that test and validation performance are improved up to 27% and 59%, respectively.
Constructing first-principles models is usually a challenging and time-consuming task due to the complexity of the real-life processes. On the other hand, data-driven modeling, and in particular neural network models often suffer from issues such as overfitting and lack of useful and highquality data. At the same time, embedding trained machine learning models directly into the optimization problems has become an effective and state-of-the-art approach for surrogate optimization, whose performance can be improved by physics-informed training. In this study, it is proposed to upgrade piece-wise linear neural network models with physics informed knowledge for optimization problems with neural network models embedded. In addition to using widely accepted and naturally piece-wise linear rectified linear unit (ReLU) activation functions, this study also suggests piece-wise linear approximations for the hyperbolic tangent activation function to widen the domain. Optimization of three case studies, a blending process, an industrial distillation column and a crude oil column are investigated. For all cases, physics-informed trained neural network based optimal results are closer to global optimality. Finally, associated CPU times for the optimization problems are much shorter than the standard optimization results.