Patent
1996-02-05
1998-07-14
Davis, George B.
395 22, 395 23, 395905, G06F 1500, G06F 1518
Patent
active
057817006
ABSTRACT:
An electronic engine control (EEC) module executes both open loop and closed loop neural network processes to control the air/fuel mixture ratio of a vehicle engine to hold the fuel mixture at stoichiometry. The open loop neural network provides transient air/fuel control to provide a base stoichiometric air/fuel mixture ratio signal in response to throttle position under current engine speed and load conditions. The base air/fuel mixture ratio signal from the open loop network is additively combined with a closed loop trimming signal which varies the air/fuel mixture ratio in response to variations in the sensed exhaust gas oxygen level. Each neural network function is defined by a unitary data structure which defines the network architecture, including the number of node layers, the number of nodes per layer, and the interconnections between nodes. In addition, the data structure holds weight values which determine the manner in which network signals are combined. The network definition data structures are created by a network training system which utilizes an external training processor which employs gradient methods to derive network weight values in accordance with a cost function which quantitatively defines system objectives and an identification network which is pretrained to provide gradient signals representative of the behavior of the physical plant. The training processor executes training cycles asynchronously with the operation of the EEC module in a representative test vehicle.
REFERENCES:
patent: 4506639 (1985-03-01), Murakami et al.
patent: 4625697 (1986-12-01), Hosaka
patent: 4899280 (1990-02-01), Onari et al.
patent: 5041976 (1991-08-01), Marko et al.
patent: 5048495 (1991-09-01), Onari et al.
patent: 5050562 (1991-09-01), Ishii et al.
patent: 5099429 (1992-03-01), Onari et al.
patent: 5200898 (1993-04-01), Yuhara et al.
patent: 5247445 (1993-09-01), Miyano et al.
patent: 5361213 (1994-11-01), Fujieda et al.
patent: 5410477 (1995-04-01), Ishii et al.
patent: 5434783 (1995-07-01), Pal et al.
patent: 5479573 (1995-12-01), Keeler et al.
patent: 5598509 (1997-01-01), Takahashi et al.
patent: 5625750 (1997-04-01), Puskorius et al.
"Automotive Engine Idle Speed Control with Recurrent Neural Networks" by G. V. Puskorius and L. A. Feldkamp, Research Laboratory, Ford Motor Company; In Proceedings of the 1993 American Control Conference; pp. 311 to 316.
Puskorius et al, "Truncated Backpropogation Through Time and Kalman Filter", Proceedings of the 1994 IEEE Inter. Conf. on Neural Networks, vol. IV, pp. 2488-2493.
Puskorius et al, "Recurrent Network Training with the Decoupled Extended Kalman Filter Algorithm", Proceedings of the 1992 SPIE Conference on the Science of Artificial Neural Networks, Orlando 1992.
Feldkamp et al, "Neural Control Systems Trained by Dynamics Gradient Methods for Automotive Applications," IEEE ICNN, 1992.
Puskorius et al, "Neuro Control of Nonlinear Dynamical Systems with Kalman Filter Trained Recurrent Networks", IEEE Transactions on Neural Networks, 1994.
Narendara et al, "Gradient Methods for the Optimization of Dynamical Systems Containing Neural Networks", IEEE Transactions on Neural Networks, 1991.
Narendara et al, "Identification and Control of Dynamical Systems Using Neural Networks", IEEE Transactions on Neural Networks, 1990.
Davis Leighton Ira
Feldkamp Lee Albert
Puskorius Gintaras Vincent
Davis George B.
Ford Global Technologies Inc.
Lippa Allan J.
LandOfFree
Trained Neural network air/fuel control system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Trained Neural network air/fuel control system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Trained Neural network air/fuel control system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1891761