Deep learning-based cooling system temperature prediction apparatus according to physical causality and method therefor

A deep learning-based cooling system temperature prediction method according to a physical causality, the method using an artificial neural network modeled by connecting a plurality of artificial neural network submodels each including an input layer, a hidden layer, and an output layer, and the method comprising:

• determining a control mode as one of a divisional control and an integral control;
• selecting at least one of a control variable, an environment variable, or a time variable set in advance in the plurality of artificial neural network submodels, depending on the divisional control and the integral control, in accordance with the physical causality, for a number of the artificial neural network submodels, wherein the control variable and the environment variable are sequentially input to each of the plurality of artificial neural network submodels in accordance with the determined control mode;
• predicting a pump flow speed, a cooling water flow rate, a battery inlet cooling water temperature, a motor inlet cooling water temperature, a radiator outlet cooling water temperature, a battery temperature, and a motor temperature by inputting the selected variable to the plurality of artificial neural network submodels;
• and
• learning the plurality of artificial neural network submodels by using the variables predicted in the submodels as feedback variables.