Active engine mounting controller using extended minimal resource allocating networks
The application of the Extended Minimal Resource Allocation Network (EMRAN) in the field of active vibration isolation for an automotive engine system is presented. As the source of disturbance the engine is mounted on a two passive mounts in parallel with an active force actuator. EMRAN is implemented to control the force actuator and to isolate this disturbance. The characteristic of EMRAN and the criteria for growing and pruning of hidden layers are presented. EMRAN's capability is compared with a PID controller and NARMA-L2 neural controller and shows superior performance in rejecting sinusoidal disturbances and achieving the chassis's vibration isolation.
Keywords: engine mounting, active vibration isolation, engine modelling, neural networks, control systems, dynamics, extended minimal resource allocation network, automotive engines, vehicle vibration, force actuators, sinusoidal disturbances