Neural network-based virtual sensor for automatic transmission slip
AssigneeGeneral Motors Corporation
InventorThomas L. Ting
Life of this patent
Estimating the term…
Abstract
A method is disclosed for computer-based control of the timing and level of gear shifts in a multi-speed automatic transmission operated in combination with an internal combustion engine and interposed fluid torque converter. The computer containing power control module signals gear shifts in response to its repeated cyclic processing of engine and transmission operation parameters including torque converter slippage. Here, such slippage is estimated using a neural network with suitable such parameters as input data. In preferred modes of operation, different neural networks are available for selection and use by the computer in different modes of engine-transmission operation.
Claims8
A method for estimating torque converter slip speed during computer-based control of shift events of a multi-speed automatic transmission in a vehicle comprising said transmission;
- an engine;
- a torque converter having input means driven by said engine, output means for providing torque input to said transmission and a clutch for engaging said input and output means, said torque converter being operable in a slip mode in which there is a difference between the speed of said input and output means sufficient to affect said shift events and a low-slip lockup mode in which said clutch is engaged;
- a powertrain control module with a programmed micro-processor;
- and engine and transmission operating parameter sensors, said method being conducted using said control module and comprising
- reading selected engine and transmission operating parameters during processing cycles of said module for managing gear shifts of said transmission and
- estimating torque converter slip speed using a neural network during at least one mode of engine and transmission operation producing a slip mode of operation of said torque converter.
Dependencies are inferred from the claim text.