Multicomponent batch distillation is an operation difficult to control not only for its nonlinear and transient behaviour, but because the product quality cannot be measured rapidly and with reliability. In the present work, a computational system for direct digital control is developed for a pilot plant batch distillation column. The development of a self tuning regulator and a soft sensor of composition based on a neural network is described. Top and reboiler temperature measurements are the basis for the on-line composition inference. The computational system was experimentally tested in a computer operated pilot column. It could be seen that the neural network soft sensor is a feasible and a reliable tool to solve on-line operational problems of the control engineering systems. The developed control system permits to operate the batch distillation column efficiently and is easy to be implemented and operated. © 1999 Elsevier Science Ltd.23SUPPL. 1S261S264Frattini Fileti, A.M., Pereira, J.A.F.R., The development and experimental testing of two adaptive control strategies for batch distillation (1997) IChemE Symposium Series no, 142 (1), pp. 249-257Quintero-Marmol, E., Luyben, W., Inferential Model-Based Control of Multlcomponent Batch Distillation (1992) Chem. Engng Sci, 47 (4), pp. 887-898Sorensen, E., Skogestad, S., Comparison of inverted and regular batch distillation (1996) Chem: Engng Sci, 51 (22), pp. 4949-4962Tham, M.T., Morris, A.J., Montague, G.A., Landt, P.A., Soft sensors for process estimation and inferential control (1991) J. Process Cantrall, pp. 3-14Willis, M.J., Montague, G.A., Di Massimo, C., Tham, M.T., (1992) Artificial Neural Networks in Process Estimation and Control. Automatica 28(6), pp. 1181-1187Zhang, E.B.M., Morris, A.J., Kiparissides, C., Inferential Estimation of Polymer QUality using Stacked Neural Networks (1997) Camp. Chern. Engng, 21 (S), pp. SI025-S1030