Nanomaterials play a vital role in healthcare, electronics, manufacturing industries, biotechnology, and security systems. One such material is graphene and its oxides are specifically used for recycling industrial waste water. Graphene, a single layer in honeycomb cross section, provides excellent attention because of its significant optical, mechanical, and physical properties. GO was utilized to decrease the acidic or essential centralization of the mechanical wastewater into reusable water for the modern reason utilizing graphene channels. In this paper, sample solution (waste water) is taken from paper industry. Graphene channels can be created from the pencil graphite. Graphene has the high goals of separating capacity, and graphene is considered as “a definitive RO film” in light of its stronger, thinner, and more chemically safe nature than the polymer layers. Graphene oxide layers are likewise to be used in the desalination plant in place of the RO membrane.

The paper presents a Meta-cognitive Fully Complexvalued Fast Learning Predictor (Mc-FCFLP) for solving realvalued prediction problems. Mc-FCFLP has two components namely, a cognitive component and a meta-cognitive one. The meta-cognitive component of Mc-FCFLP consist of a selfregulatory learning mechanism which fixes what-to-learn, whento-learn and how -to-learn. As the training samples are provided to the network one by one, the meta-cognitive component chooses appropriate learning strategies for the sample. The training sample is either gets deleted, utilised to add a new neuron or it is hold back for the future use. Hence, the architecture of Mc-FCFLP is build throughout the training process. The performance of the proposed predictor is evaluated compared to the other complex-valued and a some best performing realvalued networks with a set of benchmark Prediction problems. Performance outcomes show that the Mc-FCFLP has better prediction ability compared to the other networks shown in the literature.