The exploitation of neural networks in automotive engine management systems

The use of electronic engine control systems on spark ignition engines has enabled a high degree of performance optimisation to be achieved. The range of functions performed by these systems, and the level of performance dema nded, is rising and thus so are development times and costs. Neural network s have attracted attention as having the potential to simplify software dev elopment and improve the performance of this software. The scope and nature of possible applications is described. In particular. the pattern recognit ion and classification abilities of networks are applied to crankshaft spee d fluctuation data for engine-fault diagnosis, and multidimensional mapping capabilities are investigated as an alternative to large 'lookup' tables a nd calibration functions. (C) 2000 Elsevier Science Ltd. All rights reserve d.