On-line training neural network system for process control

Details On-line training neural network system for process control On-line training neural network system for process control

1990-08-03

1993-05-18

MacDonald, Allen R.

Boots, shoes, and leggings

364151, 395 22, 395906, 395 68, 395 23, G06F 1518

Patent

active

052127656

ABSTRACT:
An on-line training neural network for process control system and method trains by retrieving training sets from the stream of process data. The neural network detects the availability of new training data, and constructs a training set by retrieving the corresponding input data. The neural network is trained using the training set. Over time, many training sets are presented to the neural network. When multiple presentations are needed to effectively train, a buffer of training sets is filled and updated as new training data becomes available. The size of the buffer is selected in accordance with the training needs of the neural network. Once the buffer is full, a new training set bumps the oldest training set off the top of the buffer stack. The training sets in the buffer stack can be presented one or more times each time a new training set is constructed. An historical database of timestamped data can be used to construct training sets when training input data has a time delay from sample time to availability for the neural network. The timestamps of the training input data are used to select the appropriate timestamp at which input data is retrieved for use in the training set. Using the historical database, the neural network can be trained retrospectively by searching the historical database and constructing training sets based on past data.

REFERENCES:
Kuperstein et al., "Implementation of An Adaptive Neural Controller for Sensory-Motor Coordination", IEEE Control System Magazine, Apr. 1989, pp. 25-30.
Kuperstein et al., "Neural Controller for Adaptive Movements with Unforseen Payloads", IEEE Trans on Neural Networks, vol. 1, No. 1, Mar. 1990, pp. 137-142.
Kung et al., "Neural Network Architectures for Robotic Applications", IEEE Trans. on Robotics and Automation, vol. 5, No. 5, Oct. 1989, pp. 641-657.
McClelland, Explorations in Parallel Distributed Processing, MIT Press, 588, pp. 121-159.
Sanner et al., "Neuromorphic Pitch Attitude Regulation of an Underwater Telerobot", IEEE Control Systems Magazine, Apr. 1990, pp. 62-67.
Lippman, "An Introduction to Computing with Neural Nets", IEEE ASSP Magazine, Apr. 1987, pp. 4-21.
Givez et al., "Neuromorphic Controller with a Human Teacher", IEEE Internat. Conf. on Neural Networks, 1988, vol. II, pp. 595-602.
Liu, "Building a Generic Architecture for Robot Hand Control", IEEE Internat. Conf. on Neural Networks, 1988, vol. II, pp. 567-574.
Narendra et al., "Identification and Control of Dynamical Systems Using Neural Networks", IEEE Trans. on Neural Networks, vol. 1, No. 1, Mar. 1990, pp. 4-27.
Guez et al., "Neural Network Architecture for Control", IEEE Control Systems Magazine, Apr. 1988, pp. 22-25.
Chen, "Back-Propagation Neural Networks for Nonlinear Self Tuning Adaptive Control", IEEE Control Systems Mag., Apr. 1990, pp. 44-48.
Elsley, "A Learning Architecture for Control Based on Back-Propagation Neural Networks", Proc. IEEE Int'l Conf. on Neural Networks, pp. II 587-594.
Bhai et al., "Use of Neural Nets for Dynamic Modeling and Control of Chemical Process Systems", 1989 American Control Conf., pp. 1342-1347.
Hoskins et al., "Fault Diagnosis in Complex Chemical Plants Using Artificial Neural Networks", AICHE Journal, Jan. 1991, vol. 37, No. 1, pp. 137-141.
.ANG.strom, "Toward Intelligent Control", IEEE Control Systems Magazine, Apr. 1989, pp. 60-64.
Bavarian, "Introduction to Neural Networks for Intelligent Control", IEEE Control Systems Magazine, Apr. 1988, pp. 3-7.
Psaltis et al., "A Multilayered Neural Network Controller", IEEE Control Systems Magazine, Apr. 1988, pp. 17-21.
Kraft et al., "A Comparison Between CMAC Neural Network Control and Two Adaptive Control Systems", IEEE Control Systems Magazine, Apr. 1990, pp. 36-43.
Josin et al., "Robot Control Using Neural Networks", IEEE Internat. Conf. on Neural Networks, 1988, vol. I, pp. 625-631.
Liu et al., "Neural Network Architecture for Robot Hand Control", IEEE Control Systems Magazine, Apr. 1989, pp. 38-43.
Rumelhart et al., Parallel Distributed Processing, Explorations in the Microstructure of Cognition, 1986.
Bhaget, A Introduction to Neural Nets, Aug. 1990.
Ballou, Technological Mix to Fuel Neural Network Growth, Aug. 13, 1990.
Samdani, Neural Nets They Learn from Examples, Aug., 1990.
Venkatasubramanian et al., Process Fault Detection and Diagnosis Using Neural Networks--I. Steady-State Processes, Feb. 15, 1990.
Ungar et al., Adaptive Networks For Fault Diagnosis And Process Control, Jan. 15, 1990.
Ydstie, Forecasting And Control Using Adaptive Connectionist Networks, 1990.
Venkatasubramanian et al., A Neural Network Methodology for Process Fault Diagnosis, Dec., 1989.
Watanabe et al., Incipient Fault Diagnosis of Chemical Processes via Artificial Neural Networks, 1989.
Hoskins et al., Artificial Neural Network Models of Knowledge Representation in Chemical Engineering, 1988.
Graf et al., A Neural Controller for Collision-Free Movement of General Robot Manipulations, Apr., 1988.
Sobajic et al., Robust Control of Nonlinear Systems Using Pattern Recognition, IEEE International Conference on Systems, Man, and Cybernetics, vol. 1, pp. 315-320, (1989).
Lant et al., A Comparison of Adaptive Estimation with Neural Based Techniques for Bioprocess Application, Proceedings of the 1990 American Control Conference, vol. 3, pp. 2173-2178, (1990).
Guez et al., Neuromorphic Architectures for Fast Adaptive Robot Control, pp. 145-149, 1988 IEEE Int'l Conference (Apr. 24-29, 1988).
Shepanski et al., Teaching Artificial Neural Systems to Drive: Manual Training Techniques, pp. 231-238 Annual Workshop of SOA and Robotics (Aug. 5-7, 1987).
Sobajic et al., Intelligent Control of the Intelledex 605T Robot Manipulator, pp. 633-640, IEEE International Conference, San Diego (Jul. 24-27, 1988).

Affiliated with

Also associated with

Rating

On-line training neural network system for process control does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with On-line training neural network system for process control, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and On-line training neural network system for process control will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-809666