Skip to Main Content
This paper presents a neural network implementation of the delay compensator to reduce the variable sampling to actuation delay effects in networked control systems. The compensator action is based on the knowledge of the sampling to actuation delay affecting the system and the control signal. It can be easily added to an existing control system that does not account for the sampling to actuation delay effect. The compensator can be applied to distributed systems using online or off-line scheduling policies provided that the sampling to actuation delay can be evaluated for each control cycle. The effectiveness of the neural network delay compensator is evaluated using a networked control system with a pole-placement controller and the results are compared with the ones obtained previously using a fuzzy implementation of the compensator.