Adaptive filtering in complex process systems using recurrent neural networks /
The objective of this research study is to develop a method for adaptive state filtering in complex process systems using recurrent neural networks (NN). Nonlinear and "nonparametric'' adaptive state filtering methods, such as the one developed here, have many applications in industri...
| Main Author: | |
|---|---|
| Format: | Thesis Book |
| Language: | English |
| Published: |
[Place of publication not identified] :
[publisher not identified] ;
1999.
|
| Subjects: | |
| Online Access: | http://proxy.library.tamu.edu/login?url=http://proquest.umi.com/pqdweb?did=731677991&sid=1&Fmt=2&clientId=2945&RQT=309&VName=PQD |
| Summary: | The objective of this research study is to develop a method for adaptive state filtering in complex process systems using recurrent neural networks (NN). Nonlinear and "nonparametric'' adaptive state filtering methods, such as the one developed here, have many applications in industrial operations and maintenance. The proposed nonlinear and "nonparametric'' state filtering method is based on the fundamental principles of the Kalman Filter. However, in contrast to conventional state filtering methods which make use of linear process models, minimal assumptions are placed upon the process model used in the developed filtering method. The key process model assumptions stem from the limitations of the NNs to approximate arbitrary nonlinear functions. Further, no assumptions are placed on the process model noise. In fact, the developed method formulates a minimum variance filter, which is designed using least-squares algorithms. Specifically, nonadaptive and adaptive forms of the proposed state filtering method is developed, and its applicability investigated. Additionally, a hybrid form of the same method is developed, which uses both the nonadaptive and adaptive developments. The proposed method is applied to three simulated process systems, with increasing levels of complexity: an artificial problem, a DC Motor-pump system, and a U-Tube Steam Generator (UTSG) system. In addition to estimating dynamic states, the proposed filtering method is used to estimate critical parameters of a DC Motor-Pump and a UTSG system. It is found that the proposed filtering method performs well in all cases studied. As anticipated, the accuracy of the state estimates are directly dependent upon the fidelity of the process models used in the filter development. This research study demonstrates that certain NNs can be effectively used for adaptive nonlinear state filtering, when very little is known explicitly about the dynamics of the process under consideration. This conclusion complements the well-known capabilities of certain NNs in modeling the input-output behavior of complex systems, and it is, again, attributed to their superior function approximation capability. Experimental verification of these simulation results is warranted, and it should be pursued as the next step towards building confidence in these nonlinear computational tools. |
|---|---|
| Item Description: | Vita. "Major Subject: Nuclear Engineering". |
| Physical Description: | xxi, 318 leaves : illustrations ; 28 cm. Issued also on microfiche from University Microfilm Inc. |
| Bibliography: | Includes bibliographical references (leaves 305-312). |