Active Control of Complex Systems via Dynamic (Recurrent) Neural Networks
In this work the synthesis of artificial neural networks is examined from the perspective of statistical estimation of functions, and development of synthesis algorithms is centered on new tools for building dynamic (recurrent) neural networks that incorporate internal feedbacks and time delays. The...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Report |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Ward, David G Parker, B E , Jr Barron, Roger L |
| description | In this work the synthesis of artificial neural networks is examined from the perspective of statistical estimation of functions, and development of synthesis algorithms is centered on new tools for building dynamic (recurrent) neural networks that incorporate internal feedbacks and time delays. The DynNet algorithm is described; it learns the feedforward and feedback structure of a nonlinear dynamic neural network and optimizes the coefficients therein. Applications of the algorithm are presented for the following areas: time-series predictions related to an advanced turbopropulsion combustion process rapid predictions of the responses of a synchronous generator to changes in its input and load conditions predictions of the behavior of a deterministic chaotic process on-line, real-time, optimal two-point boundary-value guidance of an air-to-air missile. The report outlines the advantages of dynamic neural networks and probes the issues related to their synthesis and use. |
| format | Report |
| fullrecord | <record><control><sourceid>dtic_1RU</sourceid><recordid>TN_cdi_dtic_stinet_ADA254878</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>ADA254878</sourcerecordid><originalsourceid>FETCH-dtic_stinet_ADA2548783</originalsourceid><addsrcrecordid>eNrjZPB0TC7JLEtVcM7PKynKz1HITwMycwtyUisUgiuLS1JzixXKMhMVXCrzEnMzkxU0glKTS4uKUvNKNBX8UkuLEnOAVEl5flF2MQ8Da1piTnEqL5TmZpBxcw1x9tBNKclMji8uycxLLYl3dHE0MjWxMLcwJiANAIqdMUY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>report</recordtype></control><display><type>report</type><title>Active Control of Complex Systems via Dynamic (Recurrent) Neural Networks</title><source>DTIC Technical Reports</source><creator>Ward, David G ; Parker, B E , Jr ; Barron, Roger L</creator><creatorcontrib>Ward, David G ; Parker, B E , Jr ; Barron, Roger L ; BARRON ASSOCIATES INC STANARDSVILLE VA</creatorcontrib><description>In this work the synthesis of artificial neural networks is examined from the perspective of statistical estimation of functions, and development of synthesis algorithms is centered on new tools for building dynamic (recurrent) neural networks that incorporate internal feedbacks and time delays. The DynNet algorithm is described; it learns the feedforward and feedback structure of a nonlinear dynamic neural network and optimizes the coefficients therein. Applications of the algorithm are presented for the following areas: time-series predictions related to an advanced turbopropulsion combustion process rapid predictions of the responses of a synchronous generator to changes in its input and load conditions predictions of the behavior of a deterministic chaotic process on-line, real-time, optimal two-point boundary-value guidance of an air-to-air missile. The report outlines the advantages of dynamic neural networks and probes the issues related to their synthesis and use.</description><language>eng</language><subject>ACTIVE CONTROL ; AIR ; Air Navigation and Guidance ; AIR TO AIR ; AIR TO AIR MISSILES ; Air- and Space-launched Guided Missiles ; ALGORITHMS ; ARTIFICIAL NEURAL NETWORKS ; BEHAVIOR ; BOUNDARIES ; BUILDINGS ; CHAOTIC SYSTEMS ; CLASSIFICATION ; COEFFICIENTS ; COMBUSTION ; COMBUSTION CONTROL ; COMMAND GUIDANCE ; CONTROL ; DELAY ; DYNAMIC NEURAL NETWORKS ; DYNAMICS ; ESTIMATION ; FEEDBACK ; FUNCTIONS ; GENERATORS ; GUIDANCE ; INPUT ; INTERNAL ; LEARNING ALGORITHMS ; MISSILE GUIDANCE ; MODELING ; NETWORKS ; NEURAL NETS ; PREDICTION ; PREDICTIONS ; PROBES ; REAL TIME ; RECURRENT NEURAL NETWORKS ; RESPONSE ; STATISTICAL ESTIMATION OF FUNCTIONS ; STRUCTURES ; SYNCHRONOUS MACHINES ; SYNTHESIS ; SYSTEMS ANALYSIS ; TIME ; VALUE ; WORK</subject><creationdate>1992</creationdate><rights>Approved for public release; distribution is unlimited.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,776,881,27544,27545</link.rule.ids><linktorsrc>$$Uhttps://apps.dtic.mil/sti/citations/ADA254878$$EView_record_in_DTIC$$FView_record_in_$$GDTIC$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Ward, David G</creatorcontrib><creatorcontrib>Parker, B E , Jr</creatorcontrib><creatorcontrib>Barron, Roger L</creatorcontrib><creatorcontrib>BARRON ASSOCIATES INC STANARDSVILLE VA</creatorcontrib><title>Active Control of Complex Systems via Dynamic (Recurrent) Neural Networks</title><description>In this work the synthesis of artificial neural networks is examined from the perspective of statistical estimation of functions, and development of synthesis algorithms is centered on new tools for building dynamic (recurrent) neural networks that incorporate internal feedbacks and time delays. The DynNet algorithm is described; it learns the feedforward and feedback structure of a nonlinear dynamic neural network and optimizes the coefficients therein. Applications of the algorithm are presented for the following areas: time-series predictions related to an advanced turbopropulsion combustion process rapid predictions of the responses of a synchronous generator to changes in its input and load conditions predictions of the behavior of a deterministic chaotic process on-line, real-time, optimal two-point boundary-value guidance of an air-to-air missile. The report outlines the advantages of dynamic neural networks and probes the issues related to their synthesis and use.</description><subject>ACTIVE CONTROL</subject><subject>AIR</subject><subject>Air Navigation and Guidance</subject><subject>AIR TO AIR</subject><subject>AIR TO AIR MISSILES</subject><subject>Air- and Space-launched Guided Missiles</subject><subject>ALGORITHMS</subject><subject>ARTIFICIAL NEURAL NETWORKS</subject><subject>BEHAVIOR</subject><subject>BOUNDARIES</subject><subject>BUILDINGS</subject><subject>CHAOTIC SYSTEMS</subject><subject>CLASSIFICATION</subject><subject>COEFFICIENTS</subject><subject>COMBUSTION</subject><subject>COMBUSTION CONTROL</subject><subject>COMMAND GUIDANCE</subject><subject>CONTROL</subject><subject>DELAY</subject><subject>DYNAMIC NEURAL NETWORKS</subject><subject>DYNAMICS</subject><subject>ESTIMATION</subject><subject>FEEDBACK</subject><subject>FUNCTIONS</subject><subject>GENERATORS</subject><subject>GUIDANCE</subject><subject>INPUT</subject><subject>INTERNAL</subject><subject>LEARNING ALGORITHMS</subject><subject>MISSILE GUIDANCE</subject><subject>MODELING</subject><subject>NETWORKS</subject><subject>NEURAL NETS</subject><subject>PREDICTION</subject><subject>PREDICTIONS</subject><subject>PROBES</subject><subject>REAL TIME</subject><subject>RECURRENT NEURAL NETWORKS</subject><subject>RESPONSE</subject><subject>STATISTICAL ESTIMATION OF FUNCTIONS</subject><subject>STRUCTURES</subject><subject>SYNCHRONOUS MACHINES</subject><subject>SYNTHESIS</subject><subject>SYSTEMS ANALYSIS</subject><subject>TIME</subject><subject>VALUE</subject><subject>WORK</subject><fulltext>true</fulltext><rsrctype>report</rsrctype><creationdate>1992</creationdate><recordtype>report</recordtype><sourceid>1RU</sourceid><recordid>eNrjZPB0TC7JLEtVcM7PKynKz1HITwMycwtyUisUgiuLS1JzixXKMhMVXCrzEnMzkxU0glKTS4uKUvNKNBX8UkuLEnOAVEl5flF2MQ8Da1piTnEqL5TmZpBxcw1x9tBNKclMji8uycxLLYl3dHE0MjWxMLcwJiANAIqdMUY</recordid><startdate>19920530</startdate><enddate>19920530</enddate><creator>Ward, David G</creator><creator>Parker, B E , Jr</creator><creator>Barron, Roger L</creator><scope>1RU</scope><scope>BHM</scope></search><sort><creationdate>19920530</creationdate><title>Active Control of Complex Systems via Dynamic (Recurrent) Neural Networks</title><author>Ward, David G ; Parker, B E , Jr ; Barron, Roger L</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-dtic_stinet_ADA2548783</frbrgroupid><rsrctype>reports</rsrctype><prefilter>reports</prefilter><language>eng</language><creationdate>1992</creationdate><topic>ACTIVE CONTROL</topic><topic>AIR</topic><topic>Air Navigation and Guidance</topic><topic>AIR TO AIR</topic><topic>AIR TO AIR MISSILES</topic><topic>Air- and Space-launched Guided Missiles</topic><topic>ALGORITHMS</topic><topic>ARTIFICIAL NEURAL NETWORKS</topic><topic>BEHAVIOR</topic><topic>BOUNDARIES</topic><topic>BUILDINGS</topic><topic>CHAOTIC SYSTEMS</topic><topic>CLASSIFICATION</topic><topic>COEFFICIENTS</topic><topic>COMBUSTION</topic><topic>COMBUSTION CONTROL</topic><topic>COMMAND GUIDANCE</topic><topic>CONTROL</topic><topic>DELAY</topic><topic>DYNAMIC NEURAL NETWORKS</topic><topic>DYNAMICS</topic><topic>ESTIMATION</topic><topic>FEEDBACK</topic><topic>FUNCTIONS</topic><topic>GENERATORS</topic><topic>GUIDANCE</topic><topic>INPUT</topic><topic>INTERNAL</topic><topic>LEARNING ALGORITHMS</topic><topic>MISSILE GUIDANCE</topic><topic>MODELING</topic><topic>NETWORKS</topic><topic>NEURAL NETS</topic><topic>PREDICTION</topic><topic>PREDICTIONS</topic><topic>PROBES</topic><topic>REAL TIME</topic><topic>RECURRENT NEURAL NETWORKS</topic><topic>RESPONSE</topic><topic>STATISTICAL ESTIMATION OF FUNCTIONS</topic><topic>STRUCTURES</topic><topic>SYNCHRONOUS MACHINES</topic><topic>SYNTHESIS</topic><topic>SYSTEMS ANALYSIS</topic><topic>TIME</topic><topic>VALUE</topic><topic>WORK</topic><toplevel>online_resources</toplevel><creatorcontrib>Ward, David G</creatorcontrib><creatorcontrib>Parker, B E , Jr</creatorcontrib><creatorcontrib>Barron, Roger L</creatorcontrib><creatorcontrib>BARRON ASSOCIATES INC STANARDSVILLE VA</creatorcontrib><collection>DTIC Technical Reports</collection><collection>DTIC STINET</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ward, David G</au><au>Parker, B E , Jr</au><au>Barron, Roger L</au><aucorp>BARRON ASSOCIATES INC STANARDSVILLE VA</aucorp><format>book</format><genre>unknown</genre><ristype>RPRT</ristype><btitle>Active Control of Complex Systems via Dynamic (Recurrent) Neural Networks</btitle><date>1992-05-30</date><risdate>1992</risdate><abstract>In this work the synthesis of artificial neural networks is examined from the perspective of statistical estimation of functions, and development of synthesis algorithms is centered on new tools for building dynamic (recurrent) neural networks that incorporate internal feedbacks and time delays. The DynNet algorithm is described; it learns the feedforward and feedback structure of a nonlinear dynamic neural network and optimizes the coefficients therein. Applications of the algorithm are presented for the following areas: time-series predictions related to an advanced turbopropulsion combustion process rapid predictions of the responses of a synchronous generator to changes in its input and load conditions predictions of the behavior of a deterministic chaotic process on-line, real-time, optimal two-point boundary-value guidance of an air-to-air missile. The report outlines the advantages of dynamic neural networks and probes the issues related to their synthesis and use.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_dtic_stinet_ADA254878 |
| source | DTIC Technical Reports |
| subjects | ACTIVE CONTROL AIR Air Navigation and Guidance AIR TO AIR AIR TO AIR MISSILES Air- and Space-launched Guided Missiles ALGORITHMS ARTIFICIAL NEURAL NETWORKS BEHAVIOR BOUNDARIES BUILDINGS CHAOTIC SYSTEMS CLASSIFICATION COEFFICIENTS COMBUSTION COMBUSTION CONTROL COMMAND GUIDANCE CONTROL DELAY DYNAMIC NEURAL NETWORKS DYNAMICS ESTIMATION FEEDBACK FUNCTIONS GENERATORS GUIDANCE INPUT INTERNAL LEARNING ALGORITHMS MISSILE GUIDANCE MODELING NETWORKS NEURAL NETS PREDICTION PREDICTIONS PROBES REAL TIME RECURRENT NEURAL NETWORKS RESPONSE STATISTICAL ESTIMATION OF FUNCTIONS STRUCTURES SYNCHRONOUS MACHINES SYNTHESIS SYSTEMS ANALYSIS TIME VALUE WORK |
| title | Active Control of Complex Systems via Dynamic (Recurrent) Neural Networks |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T12%3A56%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-dtic_1RU&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=unknown&rft.btitle=Active%20Control%20of%20Complex%20Systems%20via%20Dynamic%20(Recurrent)%20Neural%20Networks&rft.au=Ward,%20David%20G&rft.aucorp=BARRON%20ASSOCIATES%20INC%20STANARDSVILLE%20VA&rft.date=1992-05-30&rft_id=info:doi/&rft_dat=%3Cdtic_1RU%3EADA254878%3C/dtic_1RU%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |