Skip to Main Content
Modelling of physical phenomena often involves the use of complex systems of equations whose computational solution has demanding requirements in terms of memory and computing power. Among the different techniques proposed to alleviate this problem, the discrete-time cellular neural network (DT-CNN) has been proved to be a powerful tool as it has the advantage of a feasible hardware implementation that can significantly speed up the computations. In this paper a thermal model of the soil based on the solution of the heat equation has been adapted to a multilayer DT-CNN architecture. Thus, we emulate the dynamic of a multilayer DT-CNN on an FPGA platform using Handel-C and VHDL. An speedup factor of 34 over a PC is achieved, which demonstrates the utility of such an implementation.