Control of left ventricular assist device using artificial neural network

Presents the neural network identification and control of a highly complicated nonlinear Left Ventricular Assist Device (LVAD) system with a pneumatically driven mock circulation system. Generally an LVAD system needs to compensate for nonlinearities. Hence, it is necessary to apply high performance control techniques. Fortunately, a neural network can be applied to the control of a nonlinear dynamic system by utilizing its learning capability. Here, the authors identify an LVAD system with Neural Network Identification (NNI). Once the NNI has learned the dynamic model of the LVAD system, another network, called Neural Network Controller (NNC), is designed for control of the LVAD system. The ability and effectiveness of identifying and controlling an LVAD system using the proposed algorithm is demonstrated by computer simulation.