A neural network-based optimizing control system for a seawater-desalination solar-powered membrane distillation unit

• A solar-powered membrane distillation unit has been set-up and tested.
• A neural network-based model of the process has been developed and validated.
• The NN-model was adopted for a system optimization analysis.
• An optimizing feedforward control was developed and implemented.
• The controlled unit was tested and results compared with the non-controlled one.

Several schemes have been proposed so far for coupling desalination processes with the use of renewable energy. One of their main drawbacks, however, is the nature of the energy source that requires a discontinuous and non-stationary operation, with some control and optimization problems. In the present work, a solar powered membrane distillation system has been used for developing an optimizing control strategy. A neural network (NN) model of the system has been trained and tested using experimental data purposely collected. Afterwards, the NN model has been used for the analysis of the process performance under various operating conditions, namely distillate production versus feed flow rate, solar radiation and cold feed temperature. On this basis, a control system that optimizes the distillate production under variable operating conditions has been developed, implemented and tested.