Numerical Modeling Based Machine Learning Approach for the Optimization of Falling - Film Evaporator in Thermal Desalination Application

Scale formation that drastically increases thermal resistance and reduces freshwater production remains a critical challenge in thermal desalination. Novel designs of falling film evaporator and optimal operating condition hold great promise to mitigate scale formation, and increase performance ratio and fresh water production. In order to identify optimal conditions, batch numerical simulations of heat and mass transfer are conducted to create a database, with which machine learning and multi-objective optimization algorithm are performed. The deep neural network serves as surrogate model to efficiently generate function evaluations for optimization. Non-dominated sorting genetic algorithm is then introduced to determine and analyze the optimal pareto front for two and three objectives in desalination criteria. At pareto front, both performance ratio and water production rate increase at high temperature with increasing fouling resistance. This approach incorporates fouling resistance variation with different heating steam, feed seawater, and tube dimensions. Tradeoffs between mitigating scale formation and enhancing desalination performance are evaluated in optimizations for different objectives. Potential optima are identified and can be applied as guidelines to determine evaporator design and operating conditions