AUTOMOTIVE ENGINE MISFIRE DETECTION SYSTEM INCLUDING BIT-SERIAL BASED RECURRENT NEUROPROCESSOR

摘要

PURPOSE: An automotive engine misfire detection system including a bit-serial based recurrent neuroprocessor is provided to improve a detecting engine misfires on board the vehicle in real time and in a cost effective manner by using a crankshaft based engine diagnostic system including a neuroprocessor for performing a required computations. CONSTITUTION: A crankshaft based engine diagnostic system includes a neuroprocessor for performing the required computations for detecting engine misfires on board the vehicle in real time and in a cost effective manner. The neuroprocessor achieves cost effectiveness and design compactness by employing a combination of bit-serial and bit-parallel techniques for the implementation of the neurons of the neuroprocessor. The number of neurons required to perform the task is significantly reduced by time multiplexing groups of neurons from a fixed pool of neurons to implement the successive hidden layers of a recurrent neural network topology.