Reducing Environmental Swings with a Recurrent Neural Network Control System

S. Skrivan, J. Zhang, and D. Jusak (USA)


Intelligent Control Systems, Artificial Intelligence, Recurrent Neural Networks, Programmable Logic Controller, CORBA, and Aquarium Control System


Maintaining environmental stability in a dynamic system is often a very important task for a control system. Swings in environmental conditions can be harmful to equipment and cause inefficiencies in the system. These swings are present throughout our lives, in your living room for example, when you set the thermostat to 68 degrees the actual temperature cycles above and below 68 degrees. This project uses a Recurrent Neural Network (RNN) in an Aquarium Control System to reduce the swings in temperature, ph level, and conductivity. The results of testing the online system and simulations show that the RNN does reduce these swings.

Important Links:

Go Back