neural network and/or fuzzy logic

[clay]

Good response Phil, I've thought of the "learning ECU" myself more than a couple
times. Entirely possible, and should be able to do a good job, with the excellent
feedback of the wideband O2's available.

The torque sensor is essential, but I don't believe it needs to be rotating. Take
my favorite American V8, for example... The motor mount is approximately
orthogonal to the mount/crankshaft radius, making a perfect location for the
torque sensor.

Just one more part, tho. I don't think I'll be using one tomorrow, either. but it
is both reasonable, and possible.

- Clay

>
>
> Date: Thu, 30 Dec 1999 01:12:33 +1100
> From: Phil Lamovie <phil at injec.com>
> Subject: neural network and/or fuzzy logic
>
> Hi All,
>
> Jens wrote "my major interest is to use a neural network
>                       and/or fuzzy logic "
>
> You made reference to fuzzy logic allowing you to dispense
> with the dyno so I'll assume you mean for closed loop fuel & spark
> control.

> My first question is do you plan to measure engine torque

> with a rotating and transmitting load sensor ?

> If not then fuzzy is not the way to go. the only algorithm that
> comes to mind is based on torque peak i.e. MBT per cylinder.