Models of equipment and technological processes based on neural networks with a commutator structure are developed. The article proposes to use neural network models in automated control systems (ACS). Neural network models make it possible to implement automated control systems with a flexible programmable switching structure, quickly connect and disconnect new technological equipment, change the operation order in technological processes, and adapt the system to changing conditions and the external environment. The object of study is ACS. The method is modelling. The aim is to reduce the cost of developing and using automated control systems.