초록 ▼

A data estimation capability using a FNN to estimate engine state data for an engine control system is described. The data estimation capability provides for making data relating to the engine state available as control parameters in a simple, inexpensive manner. The data estimation includes using d

A data estimation capability using a FNN to estimate engine state data for an engine control system is described. The data estimation capability provides for making data relating to the engine state available as control parameters in a simple, inexpensive manner. The data estimation includes using data from one or more sensors as inputs to a FNN to estimate unmeasured engine operating states. The data estimates are provided as control parameters to an engine control system. The FNN can be used to provide data estimates for engine state values (e.g. the exhaust air fuel ratio, the exhaust NOx. value, the combustion chamber temperature, etc.) that are too difficult or too expensive to measure directly. Each FNN can be configured using a genetic optimizer to select the input data used by the FNN and the coupling weights in the FNN. For example, the air/fuel ratio in the engine exhaust is estimated from the crank-angle acceleration, the crank angle, the engine speed, the air intake volume, the intake air vacuum, the ignition timing, the valve timing angle, and/or the EGR valve control; thereby eliminating the need for an O2 sensor in the exhaust.

대표청구항 ▼

1. An engine controller comprising: a control parameter output; a plurality of inputs configured to receive input information; and a fuzzy neural network configured to estimate said control parameter output from said input information to produce an estimated control parameter, said fuzzy neural netw

1. An engine controller comprising: a control parameter output; a plurality of inputs configured to receive input information; and a fuzzy neural network configured to estimate said control parameter output from said input information to produce an estimated control parameter, said fuzzy neural network comprising a neural network and a fuzzy inference system, said fuzzy neural network trained by comparing said estimated control parameter with said control parameter to produce an error signal and training said fuzzy neural network to produce said estimated control signal in a manner that reduces said error signal.