This paper introduces an anaerobic digestion identification and control scheme, based on adaptive, on-line trained neural networks. Anaerobic digestion is a complex, nonlinear biochemical process, widely used for the treatment of organic sludge in municipal wastewater treatment plants. Conventional control schemes usually fail to overcome the typical difficulties encountered in systems with complex nonlinear dynamics and difficult-to-measure or time varying parameters. It is shown by simulation results that, under a predictive control approach, adaptive on-line trained neural networks are successful in tackling such problems. in the case of anaerobic digestion. The proposed control scheme features desired tracking, regulation and robustness properties in various anaerobic digestion control tasks, including set points or process inputs variations, even in the presence of measurement noise or in cases of process parameter changes. In addition, the performance of three training algorithms, the back-propagation and two different random optimisation techniques, is examined over the neural controller training task. In all cases the random optimisation techniques converge much faster than the back-propagation algorithm.