Since many parameters effect on the floor heating System designs, so system Simulation and design by using of dominant equation through numerical methods and achieving desirable results needs much time and expense. In this Study, the neural network used as the floor heating system which we can use it as a new method to design a quicker and Simpler floor heating system. For this purpose, first, the model of System which was a 3 dimensional room with different boundary Conditions Stimulated by Gambit & Fluent Soft wares. Considering, the inner air of the room incompressibility, boussinesq model, reformed model of k −ε, radioactive model DO and simple algorithm, the stimulation of fluid flow and temperature distribution performed. After change of effective various parameters on the floor heating system in the model (room) such as pipe depth, water temperature, internal emissivity, air absorption Coefficient, window sizes, object size(object was in room) , distance between object and floor are used as educational data for neural network. The neural network produced by two layers: hidden layer, with 20 neural neurons and arbitrary function, outer layer, with 1 neural neuron and liner Function, in the Matlab software with 6 inputs and 1 output. Comparing the achieved results with the Corresponding results by numerical methods which done by the new data showed that The difference between the results was very insignificant So the neural network Can be used as a Simpler and quicker design for floor heating system of rooms.

Keywords