摘要 |
<P>PROBLEM TO BE SOLVED: To provide a learning device and fuel injection system for reducing computational complexity. Ž<P>SOLUTION: This learning device learns values of multiple parameters included in a model formula to improve an approximation degree of a model waveform expressed with the model formula with respect to the waveform detected by a fuel pressure sensor. The learning device changes each of multiple parameters to an increased side and to a decreased side with respect to a reference value set for each of the multiple parameters (S52). The learning device calculates an approximation degree for each combination of the changes of the multiple parameters (S53). The learning device performs update when the update end condition that the approximation degree ΣM at the reference values is higher than any of the approximation degrees Σq, Σr, Σs, Σt is not satisfied by using the combination of the changes providing the highest approximation degree among the approximation degrees as the combination of the updated reference values (S56). The learning device decides the reference values as learning values of the parameters when the update end condition is satisfied (S55). Ž<P>COPYRIGHT: (C)2010,JPO&INPIT Ž
|