Research on running state recognition method of hydro-turbine based on FOA-PNN
•HHT is used to analyze the effect of pressure fluctuation signal.•The mutual information theory is used to obtain the characteristic parameter.•PNN is applied to turbine fault monitoring for the first time.•FOA is used to optimize the PNN model. To effectively monitor the operating state of hydro-t...
Gespeichert in:
| Veröffentlicht in: | Measurement : journal of the International Measurement Confederation 2021-02, Vol.169, p.108498, Article 108498 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | 108498 |
| container_title | Measurement : journal of the International Measurement Confederation |
| container_volume | 169 |
| creator | Lan, Chaofeng Li, Shuijing Chen, Huan Zhang, Wu Li, Hui |
| description | •HHT is used to analyze the effect of pressure fluctuation signal.•The mutual information theory is used to obtain the characteristic parameter.•PNN is applied to turbine fault monitoring for the first time.•FOA is used to optimize the PNN model.
To effectively monitor the operating state of hydro-turbine, a diagnosis strategy based on the operating conditions and pressure pulsation of the turbine is proposed. The improved Hilbert-Huang Transform (HHT) method is used to study the characteristics of pressure pulsation under different operating conditions. The physical parameters of pressure pulsation are extracted through the mutual information theory. Procedures include optimizing the smoothing factor σ of the Probabilistic neural network (PNN) network through the Fruit fly optimization algorithm (FOA), constructing the FOA-PNN network model, classifying the unit operating status. The result shows that when σ = 0.23, the prediction accuracy of the FOA-PNN network is 100%, and the training time is 0.336372 s. It is proven that the FOA-PNN can predict the running state of the turbine in a short time and monitor the running malfunction in real time. |
| doi_str_mv | 10.1016/j.measurement.2020.108498 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2476553842</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0263224120310265</els_id><sourcerecordid>2476553842</sourcerecordid><originalsourceid>FETCH-LOGICAL-c349t-6078be472d44da7ec97db18e467d9cf8d4c0a4a8e235af5973968d63d890720e3</originalsourceid><addsrcrecordid>eNqNkNFLwzAQxoMoOKf_Q8XnzjRNm_RxDKfC2EQUfAtpct1SbDKTVNh_b0t98NGng7vv--7uh9BthhcZzsr7dtGBDL2HDmxcEEzGPqcVP0OzjLM8pRn5OEczTMo8JYRml-gqhBZjXOZVOUPbVwggvTokzia-t9bYfRKijJB4UG5vTTTDpIN4cDpxTXI4ae_S2PvaWEhqGUCP1vVumb5st9foopGfAW5-6xy9rx_eVk_pZvf4vFpuUpXTKqYlZrwGyoimVEsGqmK6zjjQkulKNVxThSWVHEheyKao2HAr12WueYUZwZDP0d2Ue_Tuq4cQRet6b4eVglBWFkXOKRlU1aRS3oXgoRFHbzrpTyLDYsQnWvEHnxjxiQnf4F1NXhje-DbgRVAGrAJtBjBRaGf-kfIDC3V-jQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2476553842</pqid></control><display><type>article</type><title>Research on running state recognition method of hydro-turbine based on FOA-PNN</title><source>Elsevier ScienceDirect Journals</source><creator>Lan, Chaofeng ; Li, Shuijing ; Chen, Huan ; Zhang, Wu ; Li, Hui</creator><creatorcontrib>Lan, Chaofeng ; Li, Shuijing ; Chen, Huan ; Zhang, Wu ; Li, Hui</creatorcontrib><description>•HHT is used to analyze the effect of pressure fluctuation signal.•The mutual information theory is used to obtain the characteristic parameter.•PNN is applied to turbine fault monitoring for the first time.•FOA is used to optimize the PNN model.
To effectively monitor the operating state of hydro-turbine, a diagnosis strategy based on the operating conditions and pressure pulsation of the turbine is proposed. The improved Hilbert-Huang Transform (HHT) method is used to study the characteristics of pressure pulsation under different operating conditions. The physical parameters of pressure pulsation are extracted through the mutual information theory. Procedures include optimizing the smoothing factor σ of the Probabilistic neural network (PNN) network through the Fruit fly optimization algorithm (FOA), constructing the FOA-PNN network model, classifying the unit operating status. The result shows that when σ = 0.23, the prediction accuracy of the FOA-PNN network is 100%, and the training time is 0.336372 s. It is proven that the FOA-PNN can predict the running state of the turbine in a short time and monitor the running malfunction in real time.</description><identifier>ISSN: 0263-2241</identifier><identifier>EISSN: 1873-412X</identifier><identifier>DOI: 10.1016/j.measurement.2020.108498</identifier><language>eng</language><publisher>London: Elsevier Ltd</publisher><subject>Algorithms ; Fault diagnosis ; Fruit fly optimization algorithm ; Hilbert transformation ; Hydraulic turbines ; Hydro-turbine ; Information theory ; Neural networks ; Optimization ; Physical properties ; Pressure ; Pressure fluctuations ; Probabilistic neural network ; Pulsation ; Turbines</subject><ispartof>Measurement : journal of the International Measurement Confederation, 2021-02, Vol.169, p.108498, Article 108498</ispartof><rights>2020 Elsevier Ltd</rights><rights>Copyright Elsevier Science Ltd. Feb 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c349t-6078be472d44da7ec97db18e467d9cf8d4c0a4a8e235af5973968d63d890720e3</citedby><cites>FETCH-LOGICAL-c349t-6078be472d44da7ec97db18e467d9cf8d4c0a4a8e235af5973968d63d890720e3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.measurement.2020.108498$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3536,27903,27904,45974</link.rule.ids></links><search><creatorcontrib>Lan, Chaofeng</creatorcontrib><creatorcontrib>Li, Shuijing</creatorcontrib><creatorcontrib>Chen, Huan</creatorcontrib><creatorcontrib>Zhang, Wu</creatorcontrib><creatorcontrib>Li, Hui</creatorcontrib><title>Research on running state recognition method of hydro-turbine based on FOA-PNN</title><title>Measurement : journal of the International Measurement Confederation</title><description>•HHT is used to analyze the effect of pressure fluctuation signal.•The mutual information theory is used to obtain the characteristic parameter.•PNN is applied to turbine fault monitoring for the first time.•FOA is used to optimize the PNN model.
To effectively monitor the operating state of hydro-turbine, a diagnosis strategy based on the operating conditions and pressure pulsation of the turbine is proposed. The improved Hilbert-Huang Transform (HHT) method is used to study the characteristics of pressure pulsation under different operating conditions. The physical parameters of pressure pulsation are extracted through the mutual information theory. Procedures include optimizing the smoothing factor σ of the Probabilistic neural network (PNN) network through the Fruit fly optimization algorithm (FOA), constructing the FOA-PNN network model, classifying the unit operating status. The result shows that when σ = 0.23, the prediction accuracy of the FOA-PNN network is 100%, and the training time is 0.336372 s. It is proven that the FOA-PNN can predict the running state of the turbine in a short time and monitor the running malfunction in real time.</description><subject>Algorithms</subject><subject>Fault diagnosis</subject><subject>Fruit fly optimization algorithm</subject><subject>Hilbert transformation</subject><subject>Hydraulic turbines</subject><subject>Hydro-turbine</subject><subject>Information theory</subject><subject>Neural networks</subject><subject>Optimization</subject><subject>Physical properties</subject><subject>Pressure</subject><subject>Pressure fluctuations</subject><subject>Probabilistic neural network</subject><subject>Pulsation</subject><subject>Turbines</subject><issn>0263-2241</issn><issn>1873-412X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNqNkNFLwzAQxoMoOKf_Q8XnzjRNm_RxDKfC2EQUfAtpct1SbDKTVNh_b0t98NGng7vv--7uh9BthhcZzsr7dtGBDL2HDmxcEEzGPqcVP0OzjLM8pRn5OEczTMo8JYRml-gqhBZjXOZVOUPbVwggvTokzia-t9bYfRKijJB4UG5vTTTDpIN4cDpxTXI4ae_S2PvaWEhqGUCP1vVumb5st9foopGfAW5-6xy9rx_eVk_pZvf4vFpuUpXTKqYlZrwGyoimVEsGqmK6zjjQkulKNVxThSWVHEheyKao2HAr12WueYUZwZDP0d2Ue_Tuq4cQRet6b4eVglBWFkXOKRlU1aRS3oXgoRFHbzrpTyLDYsQnWvEHnxjxiQnf4F1NXhje-DbgRVAGrAJtBjBRaGf-kfIDC3V-jQ</recordid><startdate>202102</startdate><enddate>202102</enddate><creator>Lan, Chaofeng</creator><creator>Li, Shuijing</creator><creator>Chen, Huan</creator><creator>Zhang, Wu</creator><creator>Li, Hui</creator><general>Elsevier Ltd</general><general>Elsevier Science Ltd</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>202102</creationdate><title>Research on running state recognition method of hydro-turbine based on FOA-PNN</title><author>Lan, Chaofeng ; Li, Shuijing ; Chen, Huan ; Zhang, Wu ; Li, Hui</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c349t-6078be472d44da7ec97db18e467d9cf8d4c0a4a8e235af5973968d63d890720e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Fault diagnosis</topic><topic>Fruit fly optimization algorithm</topic><topic>Hilbert transformation</topic><topic>Hydraulic turbines</topic><topic>Hydro-turbine</topic><topic>Information theory</topic><topic>Neural networks</topic><topic>Optimization</topic><topic>Physical properties</topic><topic>Pressure</topic><topic>Pressure fluctuations</topic><topic>Probabilistic neural network</topic><topic>Pulsation</topic><topic>Turbines</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lan, Chaofeng</creatorcontrib><creatorcontrib>Li, Shuijing</creatorcontrib><creatorcontrib>Chen, Huan</creatorcontrib><creatorcontrib>Zhang, Wu</creatorcontrib><creatorcontrib>Li, Hui</creatorcontrib><collection>CrossRef</collection><jtitle>Measurement : journal of the International Measurement Confederation</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lan, Chaofeng</au><au>Li, Shuijing</au><au>Chen, Huan</au><au>Zhang, Wu</au><au>Li, Hui</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Research on running state recognition method of hydro-turbine based on FOA-PNN</atitle><jtitle>Measurement : journal of the International Measurement Confederation</jtitle><date>2021-02</date><risdate>2021</risdate><volume>169</volume><spage>108498</spage><pages>108498-</pages><artnum>108498</artnum><issn>0263-2241</issn><eissn>1873-412X</eissn><abstract>•HHT is used to analyze the effect of pressure fluctuation signal.•The mutual information theory is used to obtain the characteristic parameter.•PNN is applied to turbine fault monitoring for the first time.•FOA is used to optimize the PNN model.
To effectively monitor the operating state of hydro-turbine, a diagnosis strategy based on the operating conditions and pressure pulsation of the turbine is proposed. The improved Hilbert-Huang Transform (HHT) method is used to study the characteristics of pressure pulsation under different operating conditions. The physical parameters of pressure pulsation are extracted through the mutual information theory. Procedures include optimizing the smoothing factor σ of the Probabilistic neural network (PNN) network through the Fruit fly optimization algorithm (FOA), constructing the FOA-PNN network model, classifying the unit operating status. The result shows that when σ = 0.23, the prediction accuracy of the FOA-PNN network is 100%, and the training time is 0.336372 s. It is proven that the FOA-PNN can predict the running state of the turbine in a short time and monitor the running malfunction in real time.</abstract><cop>London</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.measurement.2020.108498</doi></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0263-2241 |
| ispartof | Measurement : journal of the International Measurement Confederation, 2021-02, Vol.169, p.108498, Article 108498 |
| issn | 0263-2241 1873-412X |
| language | eng |
| recordid | cdi_proquest_journals_2476553842 |
| source | Elsevier ScienceDirect Journals |
| subjects | Algorithms Fault diagnosis Fruit fly optimization algorithm Hilbert transformation Hydraulic turbines Hydro-turbine Information theory Neural networks Optimization Physical properties Pressure Pressure fluctuations Probabilistic neural network Pulsation Turbines |
| title | Research on running state recognition method of hydro-turbine based on FOA-PNN |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T12%3A38%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Research%20on%20running%20state%20recognition%20method%20of%20hydro-turbine%20based%20on%20FOA-PNN&rft.jtitle=Measurement%20:%20journal%20of%20the%20International%20Measurement%20Confederation&rft.au=Lan,%20Chaofeng&rft.date=2021-02&rft.volume=169&rft.spage=108498&rft.pages=108498-&rft.artnum=108498&rft.issn=0263-2241&rft.eissn=1873-412X&rft_id=info:doi/10.1016/j.measurement.2020.108498&rft_dat=%3Cproquest_cross%3E2476553842%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2476553842&rft_id=info:pmid/&rft_els_id=S0263224120310265&rfr_iscdi=true |