Scholars' Mine
Missouri S&T
Research Repository
Curtis Laws Wilson Library
400 W. 14th Street
Rolla, MO 65409-0060
scholarsmine@mst.edu
| Title: | Adaptive critic based neural networks for control (low order system applications) | |
| Author (s): | Balakrishnan, S. N. Biega, V. | |
| Department/Lab Affiliations: | Mechanical & Aerospace Engineering | |
| Keywords: | control system synthesis dynamic programming neurocontrollers nonlinear control systems suboptimal control 1D infinite horizon problem 2D linear problem adaptive critic based neural networks adaptive neural networks control synthesis corrective capabilities cost functions discretized system dynamic programming final state constraints low-order system near-optimal control laws nonlinear systems one dimensional infinite horizon problem two dimensional linear problem | |
| Issue Date: | 1995 | |
| Publisher: | Institute of Electrical and Electronics Engineers | |
| Citation: | *Adaptive critic based neural networks for control (low order system a pp.ications)* Balakrishnan, S. N.; Biega, V. American Control Conference, 1995. Proceedings of the, Vol.1, Iss., 21-23 Jun 1995 Pages:335-339 vol.1 | |
| Abstract: | Dynamic programming is an exact method of determining optimal control for a discretized system. Unfortunately, for nonlinear systems the computations necessary with this method become prohibitive. This study investigates the use of adaptive neural networks that utilize dynamic programming methodology to develop near optimal control laws. First, a one dimensional infinite horizon problem is examined. Problems involving cost functions with final state constraints are considered for one dimensional linear and nonlinear systems. A two dimensional linear problem is also investigated. In addition to these examples, an example of the corrective capabilities of critics is shown. Synthesis of the networks in this study needs no external training; they do not need any apriori knowledge of the functional form of control. Comparison with specific optimal control techniques show that the networks yield optimal control over the entire range of training | |
| Type: | Article - Journal text | |
| Copyright Notice: | This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. FULL COPYRIGHT INFORMATION: | |
| Publisher URL: | ||
| Link to this page: | ||
| Full Text: |
|
| title | Adaptive critic based neural networks for control (low order system applications) | |
| contributor.author | Balakrishnan, S. N. | |
| contributor.author | Biega, V. | |
| contributor.deptlab | Mechanical & Aerospace Engineering | |
| subject | control system synthesis | |
| subject | dynamic programming | |
| subject | neurocontrollers | |
| subject | nonlinear control systems | |
| subject | suboptimal control | |
| subject | 1D infinite horizon problem | |
| subject | 2D linear problem | |
| subject | adaptive critic based neural networks | |
| subject | adaptive neural networks | |
| subject | control synthesis | |
| subject | corrective capabilities | |
| subject | cost functions | |
| subject | discretized system | |
| subject | dynamic programming | |
| subject | final state constraints | |
| subject | low-order system | |
| subject | near-optimal control laws | |
| subject | nonlinear systems | |
| subject | one dimensional infinite horizon problem | |
| subject | two dimensional linear problem | |
| date.issued | 1995 | |
| date.submitted | 2007 | |
| publisher | Institute of Electrical and Electronics Engineers | |
| identifier.citation | *Adaptive critic based neural networks for control (low order system a pp.ications)* Balakrishnan, S. N.; Biega, V. American Control Conference, 1995. Proceedings of the, Vol.1, Iss., 21-23 Jun 1995 Pages:335-339 vol.1 | |
| identifier.pub.URI | ||
| description.abstract | Dynamic programming is an exact method of determining optimal control for a discretized system. Unfortunately, for nonlinear systems the computations necessary with this method become prohibitive. This study investigates the use of adaptive neural networks that utilize dynamic programming methodology to develop near optimal control laws. First, a one dimensional infinite horizon problem is examined. Problems involving cost functions with final state constraints are considered for one dimensional linear and nonlinear systems. A two dimensional linear problem is also investigated. In addition to these examples, an example of the corrective capabilities of critics is shown. Synthesis of the networks in this study needs no external training; they do not need any apriori knowledge of the functional form of control. Comparison with specific optimal control techniques show that the networks yield optimal control over the entire range of training | |
| type | Article - Journal | |
| type.DCMIType | text | |
| type.status | Final version | |
| rights | This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. | |
| rights.URI | ||
| date.accessioned | 2007-04-05T14:01:00Z | |
| date.available | 2007-04-05T14:00:59Z | |
| identifier.persist.URI | ||
| Full Text |
|