An Improved LightGBM Algorithm for Online Fault Detection of Wind Turbine Gearboxes
It is widely accepted that conventional boost algorithms are of low efficiency and accuracy in dealing with big data collected from wind turbine operations. To address this issue, this paper is devoted to the application of an adaptive LightGBM method for wind turbine fault detections. To this end,...
Uložené v:
| Vydané v: | Energies (Basel) Ročník 13; číslo 4; s. 807 |
|---|---|
| Hlavní autori: | , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
MDPI AG
01.02.2020
|
| Predmet: | |
| ISSN: | 1996-1073, 1996-1073 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | It is widely accepted that conventional boost algorithms are of low efficiency and accuracy in dealing with big data collected from wind turbine operations. To address this issue, this paper is devoted to the application of an adaptive LightGBM method for wind turbine fault detections. To this end, the realization of feature selection for fault detection is firstly achieved by utilizing the maximum information coefficient to analyze the correlation among features in supervisory control and data acquisition (SCADA) of wind turbines. After that, a performance evaluation criterion is proposed for the improved LightGBM model to support fault detections. In this scheme, by embedding the confusion matrix as a performance indicator, an improved LightGBM fault detection approach is then developed. Based on the adaptive LightGBM fault detection model, a fault detection strategy for wind turbine gearboxes is investigated. To demonstrate the applications of the proposed algorithms and methods, a case study with a three-year SCADA dataset obtained from a wind farm sited in Southern China is conducted. Results indicate that the proposed approaches established a fault detection framework of wind turbine systems with either lower false alarm rate or lower missing detection rate. |
|---|---|
| AbstractList | It is widely accepted that conventional boost algorithms are of low efficiency and accuracy in dealing with big data collected from wind turbine operations. To address this issue, this paper is devoted to the application of an adaptive LightGBM method for wind turbine fault detections. To this end, the realization of feature selection for fault detection is firstly achieved by utilizing the maximum information coefficient to analyze the correlation among features in supervisory control and data acquisition (SCADA) of wind turbines. After that, a performance evaluation criterion is proposed for the improved LightGBM model to support fault detections. In this scheme, by embedding the confusion matrix as a performance indicator, an improved LightGBM fault detection approach is then developed. Based on the adaptive LightGBM fault detection model, a fault detection strategy for wind turbine gearboxes is investigated. To demonstrate the applications of the proposed algorithms and methods, a case study with a three-year SCADA dataset obtained from a wind farm sited in Southern China is conducted. Results indicate that the proposed approaches established a fault detection framework of wind turbine systems with either lower false alarm rate or lower missing detection rate. |
| Author | Zhao, Qi Li, Linlin Ding, Steven X. Huang, Bin Tang, Mingzhu Wu, Huawei Long, Wen |
| Author_xml | – sequence: 1 givenname: Mingzhu orcidid: 0000-0002-9371-3207 surname: Tang fullname: Tang, Mingzhu – sequence: 2 givenname: Qi surname: Zhao fullname: Zhao, Qi – sequence: 3 givenname: Steven X. surname: Ding fullname: Ding, Steven X. – sequence: 4 givenname: Huawei surname: Wu fullname: Wu, Huawei – sequence: 5 givenname: Linlin surname: Li fullname: Li, Linlin – sequence: 6 givenname: Wen surname: Long fullname: Long, Wen – sequence: 7 givenname: Bin orcidid: 0000-0003-4292-0860 surname: Huang fullname: Huang, Bin |
| BookMark | eNptUE1PAjEQbQwmInLxF_Rsstpuu9v2iChIguEgxmPTr4WSZUu6xei_dxGNxjiXeZmZ92benINeExoHwCVG14QIdOMaTBBFHLET0MdClBlGjPR-4TMwbNsN6oIQTAjpg6dRA2fbXQyvzsK5X63T9PYRjupViD6tt7AKES6a2jcOTtS-TvDOJWeSDw0MFXzxjYXLfdSH_tSpqMObay_AaaXq1g2_8gA8T-6X44dsvpjOxqN5ZrrVKSMlyzUymJaYCiqsNtgyQgpcVJbzyjAhGM7zMqe4ENRqynmpC6wcYryDigzA7Khrg9rIXfRbFd9lUF5-FkJcSRWTN7WTlnTuK6MZF4QywZVQ2BY2N5YKrVDZaaGjlomhbaOrpPFJHXymqHwtMZKHH8ufH3eUqz-U7xP-Gf4Acid7qw |
| CitedBy_id | crossref_primary_10_1177_0309524X221113013 crossref_primary_10_1016_j_psep_2024_06_038 crossref_primary_10_1109_ACCESS_2022_3185259 crossref_primary_10_1007_s11053_023_10240_1 crossref_primary_10_3390_app14135849 crossref_primary_10_1016_j_petlm_2021_04_006 crossref_primary_10_1109_JSEN_2024_3396881 crossref_primary_10_3389_fenrg_2021_701574 crossref_primary_10_1007_s10836_024_06134_6 crossref_primary_10_3390_pr12050975 crossref_primary_10_3390_en15165780 crossref_primary_10_1080_23335777_2022_2135610 crossref_primary_10_3390_en17051215 crossref_primary_10_1016_j_segan_2023_101126 crossref_primary_10_3390_math12101514 crossref_primary_10_1177_14759217231178652 crossref_primary_10_1007_s10462_022_10233_1 crossref_primary_10_1088_1361_6501_ad366a crossref_primary_10_3389_fenrg_2021_751066 crossref_primary_10_3390_e22040478 crossref_primary_10_3390_s22186826 crossref_primary_10_1016_j_resourpol_2024_105014 crossref_primary_10_1177_14759217211009780 crossref_primary_10_3390_en14196127 crossref_primary_10_12677_sa_2024_135180 crossref_primary_10_1109_JSEN_2023_3303223 crossref_primary_10_1002_rvr2_71 crossref_primary_10_1080_01431161_2024_2307945 crossref_primary_10_3390_en15197423 crossref_primary_10_1016_j_measurement_2022_110722 crossref_primary_10_3390_mi14020265 crossref_primary_10_1007_s12204_022_2495_5 crossref_primary_10_3390_w13070920 crossref_primary_10_2478_fiqf_2025_0004 crossref_primary_10_3390_pr11010068 crossref_primary_10_3390_s21062228 crossref_primary_10_1007_s40722_024_00335_z crossref_primary_10_1016_j_jclepro_2022_134011 crossref_primary_10_3389_fenrg_2021_686616 crossref_primary_10_1088_1742_6596_2184_1_012020 crossref_primary_10_1155_2020_2091382 crossref_primary_10_1049_cim2_12055 crossref_primary_10_3389_fenrg_2021_750983 crossref_primary_10_1016_j_engstruct_2025_120350 crossref_primary_10_3390_s21186215 crossref_primary_10_5004_dwt_2022_29110 crossref_primary_10_1016_j_enbuild_2021_111423 crossref_primary_10_3390_en14123572 crossref_primary_10_3390_jmse13071337 crossref_primary_10_3390_en16155793 crossref_primary_10_1080_15435075_2023_2217901 crossref_primary_10_3390_rs13101952 crossref_primary_10_3390_s22186763 crossref_primary_10_7717_peerj_cs_2016 crossref_primary_10_1007_s13563_024_00437_y crossref_primary_10_1007_s42417_024_01440_x crossref_primary_10_1016_j_advengsoft_2024_103635 crossref_primary_10_3390_en14196283 crossref_primary_10_1016_j_asoc_2021_107146 |
| Cites_doi | 10.1126/science.1205438 10.1214/18-BA1110 10.1016/j.chemolab.2019.06.003 10.1109/ACCESS.2019.2940470 10.1016/j.enbuild.2018.12.032 10.3390/ijgi8020097 10.1145/2939672.2939785 10.1016/j.neucom.2015.12.061 10.1007/s10845-019-01522-8 10.1016/j.renene.2018.09.027 10.1109/TNNLS.2018.2881143 10.1016/j.jprocont.2017.08.010 10.1109/TSTE.2018.2801625 10.1016/j.procir.2018.12.021 10.1214/aos/1013203451 10.1016/j.apenergy.2012.04.037 10.3390/en9060379 10.1016/j.asoc.2016.01.039 10.1016/j.ifacsc.2019.100071 10.1109/TIE.2016.2538745 10.1007/s10586-018-1854-3 10.1016/j.comnet.2019.01.026 10.1016/j.renene.2018.10.031 10.1016/j.automatica.2018.10.047 10.1006/jcss.1997.1504 10.1109/TNNLS.2017.2754319 10.3390/s19143092 10.3390/en12173396 10.1016/j.ymssp.2018.02.016 10.1016/j.jtbi.2016.12.010 |
| ContentType | Journal Article |
| DBID | AAYXX CITATION DOA |
| DOI | 10.3390/en13040807 |
| DatabaseName | CrossRef DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1996-1073 |
| ExternalDocumentID | oai_doaj_org_article_d3073fcb78934798a9a1d5d2cd49ba06 10_3390_en13040807 |
| GroupedDBID | 29G 2WC 5GY 5VS 7XC 8FE 8FG 8FH AADQD AAHBH AAYXX ABDBF ACUHS ADBBV ADMLS AENEX AFFHD AFKRA AFZYC ALMA_UNASSIGNED_HOLDINGS BCNDV BENPR CCPQU CITATION CS3 DU5 EBS ESX FRP GROUPED_DOAJ GX1 I-F IAO KQ8 L6V L8X MODMG M~E OK1 OVT P2P PHGZM PHGZT PIMPY PROAC TR2 TUS |
| ID | FETCH-LOGICAL-c333t-3672b0c14614949dbc1d733515fd88fc79971226241594db4886b51ae078886a3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 70 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000522492700035&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1996-1073 |
| IngestDate | Fri Oct 03 12:45:27 EDT 2025 Tue Nov 18 22:17:49 EST 2025 Sat Nov 29 07:17:40 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c333t-3672b0c14614949dbc1d733515fd88fc79971226241594db4886b51ae078886a3 |
| ORCID | 0000-0002-9371-3207 0000-0003-4292-0860 |
| OpenAccessLink | https://doaj.org/article/d3073fcb78934798a9a1d5d2cd49ba06 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_d3073fcb78934798a9a1d5d2cd49ba06 crossref_citationtrail_10_3390_en13040807 crossref_primary_10_3390_en13040807 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-02-01 |
| PublicationDateYYYYMMDD | 2020-02-01 |
| PublicationDate_xml | – month: 02 year: 2020 text: 2020-02-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Energies (Basel) |
| PublicationYear | 2020 |
| Publisher | MDPI AG |
| Publisher_xml | – name: MDPI AG |
| References | Ge (ref_3) 2018; 65 Weber (ref_27) 2019; 80 Zheng (ref_32) 2019; 7 Friedman (ref_16) 2001; 29 ref_36 ref_12 Kong (ref_4) 2019; 132 ref_11 Bjurgert (ref_20) 2017; 29 ref_33 Lei (ref_6) 2019; 133 Pontes (ref_29) 2016; 186 Jenifer (ref_19) 2016; 42 Freund (ref_15) 1997; 55 Wang (ref_1) 2018; 9 ref_18 ref_17 Basha (ref_14) 2018; 11 Chakraborty (ref_35) 2019; 185 Marvuglia (ref_13) 2012; 98 Tang (ref_8) 2019; 22 Reshef (ref_24) 2011; 334 Bischl (ref_26) 2016; 17 Chen (ref_7) 2018; 27 Nemzer (ref_25) 2017; 415 Sun (ref_23) 2018; 30 Guo (ref_31) 2019; 151 Letham (ref_30) 2019; 14 Chen (ref_28) 2019; 191 Liu (ref_34) 2019; 10 Yin (ref_2) 2016; 63 Chen (ref_21) 2019; 7 ref_5 Gomes (ref_22) 2017; 50 Liu (ref_9) 2018; 108 Li (ref_10) 2019; 99 |
| References_xml | – volume: 334 start-page: 1518 year: 2011 ident: ref_24 article-title: Detecting novel associations in large data sets publication-title: Science doi: 10.1126/science.1205438 – volume: 14 start-page: 495 year: 2019 ident: ref_30 article-title: Constrained bayesian optimization with noisy experiments publication-title: Bayesian Anal. doi: 10.1214/18-BA1110 – volume: 27 start-page: 2773 year: 2018 ident: ref_7 article-title: Probability-relevant incipient fault detection and diagnosis methodology with applications to electric drive systems publication-title: IEEE Trans. Control Syst. Technol. – volume: 191 start-page: 54 year: 2019 ident: ref_28 article-title: Lightgbm-ppi: Predicting protein-protein interactions through lightgbm with multi-information fusion publication-title: Chemom. Intell. Lab. Syst. doi: 10.1016/j.chemolab.2019.06.003 – volume: 7 start-page: 133314 year: 2019 ident: ref_32 article-title: CGMDA: An Approach to Predict and Validate MicroRNA-Disease Associations by Utilizing Chaos Game Representation and LightGBM publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2940470 – volume: 185 start-page: 326 year: 2019 ident: ref_35 article-title: Early detection of faults in HVAC systems using an XGBoost model with a dynamic threshold publication-title: Energy Build. doi: 10.1016/j.enbuild.2018.12.032 – ident: ref_36 doi: 10.3390/ijgi8020097 – ident: ref_17 doi: 10.1145/2939672.2939785 – volume: 186 start-page: 22 year: 2016 ident: ref_29 article-title: Design of experiments and focused grid search for neural network parameter optimization publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.12.061 – ident: ref_33 doi: 10.1007/s10845-019-01522-8 – volume: 132 start-page: 1373 year: 2019 ident: ref_4 article-title: Meshing frequency modulation assisted empirical wavelet transform for fault diagnosis of wind turbine planetary ring gear publication-title: Renew. Energy doi: 10.1016/j.renene.2018.09.027 – ident: ref_18 – volume: 30 start-page: 2295 year: 2018 ident: ref_23 article-title: A particle swarm optimization-based flexible convolutional autoencoder for image classification publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2018.2881143 – volume: 65 start-page: 107 year: 2018 ident: ref_3 article-title: Distributed predictive modeling framework for prediction and diagnosis of key performance index in plant-wide processes publication-title: J. Process Control doi: 10.1016/j.jprocont.2017.08.010 – volume: 17 start-page: 5938 year: 2016 ident: ref_26 article-title: Mlr: Machine learning in r publication-title: J. Mach. Learn. Res. – volume: 9 start-page: 1627 year: 2018 ident: ref_1 article-title: Wind turbine fault detection and identification through PCA-based optimal variable selection publication-title: IEEE Trans. Sustain. Energy doi: 10.1109/TSTE.2018.2801625 – volume: 80 start-page: 683 year: 2019 ident: ref_27 article-title: Machine learning based system identification tool for data-based energy and resource modeling and simulation publication-title: Procedia CIRP doi: 10.1016/j.procir.2018.12.021 – volume: 29 start-page: 1189 year: 2001 ident: ref_16 article-title: Greedy function approximation: A gradient boosting machine publication-title: Ann. Stat. doi: 10.1214/aos/1013203451 – volume: 98 start-page: 574 year: 2012 ident: ref_13 article-title: Monitoring of wind farms’ power curves using machine learning techniques publication-title: Appl. Energy doi: 10.1016/j.apenergy.2012.04.037 – ident: ref_12 doi: 10.3390/en9060379 – volume: 42 start-page: 167 year: 2016 ident: ref_19 article-title: Contrast enhancement and brightness preserving of digital mammograms using fuzzy clipped contrast-limited adaptive histogram equalization algorithm publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2016.01.039 – volume: 50 start-page: 23 year: 2017 ident: ref_22 article-title: A survey on ensemble learning for data stream classification publication-title: ACM Comput. Surv. (CSUR) – volume: 10 start-page: 100071 year: 2019 ident: ref_34 article-title: Deep ensemble forests for industrial fault classification publication-title: IFAC J. Syst. Control doi: 10.1016/j.ifacsc.2019.100071 – volume: 63 start-page: 3201 year: 2016 ident: ref_2 article-title: Diagnosis and prognosis for complicated industrial systems—Part II publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2016.2538745 – volume: 22 start-page: 7525 year: 2019 ident: ref_8 article-title: Cost-sensitive large margin distribution machine for fault detection of wind turbines publication-title: Cluster. Comput. doi: 10.1007/s10586-018-1854-3 – volume: 11 start-page: 41 year: 2018 ident: ref_14 article-title: Impact of gradient ascent and boosting algorithm in classification publication-title: Int. J. Intell. Eng. Syst. – volume: 151 start-page: 166 year: 2019 ident: ref_31 article-title: An xgboost-based physical fitness evaluation model using advanced feature selection and bayesian hyper-parameter optimization for wearable running monitoring publication-title: Comput. Netw. doi: 10.1016/j.comnet.2019.01.026 – volume: 133 start-page: 422 year: 2019 ident: ref_6 article-title: Fault diagnosis of wind turbine based on Long Short-term memory networks publication-title: Renew. Energy doi: 10.1016/j.renene.2018.10.031 – volume: 99 start-page: 308 year: 2019 ident: ref_10 article-title: Performance-based fault detection and fault-tolerant control for automatic control systems publication-title: Automatica doi: 10.1016/j.automatica.2018.10.047 – volume: 7 start-page: 1 year: 2019 ident: ref_21 article-title: Real-world Image Denoising with Deep Boosting publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 55 start-page: 119 year: 1997 ident: ref_15 article-title: A decision-theoretic generalization of on-line learning and an application to boosting publication-title: J. Comput. Syst. Sci. doi: 10.1006/jcss.1997.1504 – volume: 29 start-page: 4510 year: 2017 ident: ref_20 article-title: On Adaptive Boosting for System Identification publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2017.2754319 – ident: ref_11 doi: 10.3390/s19143092 – ident: ref_5 doi: 10.3390/en12173396 – volume: 108 start-page: 33 year: 2018 ident: ref_9 article-title: Artificial intelligence for fault diagnosis of rotating machinery: A review publication-title: Mech. Syst. Signal Process. doi: 10.1016/j.ymssp.2018.02.016 – volume: 415 start-page: 158 year: 2017 ident: ref_25 article-title: Shannon information entropy in the canonical genetic code publication-title: J. Theor. Biol. doi: 10.1016/j.jtbi.2016.12.010 |
| SSID | ssj0000331333 |
| Score | 2.5014465 |
| Snippet | It is widely accepted that conventional boost algorithms are of low efficiency and accuracy in dealing with big data collected from wind turbine operations. To... |
| SourceID | doaj crossref |
| SourceType | Open Website Enrichment Source Index Database |
| StartPage | 807 |
| SubjectTerms | bayesian hyper-parameter optimization fault diagnosis gradient boosting algorithm lightgbm maximum information coefficient |
| Title | An Improved LightGBM Algorithm for Online Fault Detection of Wind Turbine Gearboxes |
| URI | https://doaj.org/article/d3073fcb78934798a9a1d5d2cd49ba06 |
| Volume | 13 |
| WOSCitedRecordID | wos000522492700035&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1996-1073 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000331333 issn: 1996-1073 databaseCode: DOA dateStart: 20080101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1996-1073 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000331333 issn: 1996-1073 databaseCode: M~E dateStart: 20080101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1996-1073 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000331333 issn: 1996-1073 databaseCode: BENPR dateStart: 20080301 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 1996-1073 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000331333 issn: 1996-1073 databaseCode: PIMPY dateStart: 20080301 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8NAEF5EPOhBfGJ9saAXD6FpdpPNHltt66EtglV7C_uKCjWRNhVP_nZns7FGELx4ySEZwu7M7M73wfANQucsDjUPA-lFUUg8alLpcS2JFxqqtAi49ssu3_sBG43iyYTf1EZ92Z4wJw_sHNfUNglTJRkUVsp4LLho6VAHSlMuhRPb9hmvkanyDiYEyBdxeqQEeH3TZHBbU8BH7EcFqgn1lxWlt4U2KyiI224J22jFZDtooyYQuItu2xl2tN9oPLA8ut8Z4vb0MQdO__SCAXFiJxaKe2IxLfCVKcreqgznKX4Avo3Hi5m03_uQ0jJ_N_M9dNfrji-vvWoMgqdgC4VHIhZIX9kB3FZKRkvV0owQACKpjuNUMc5ZC1CUrcWcaglHMpJhSxjf0ttIkH20muWZOUCYahX5XFHBiIBCZCSnTBkq0ljrKOWygS6-XJOoSiPcjqqYJsAVrBuTbzc20NnS9tUpY_xq1bEeXlpYNevyBcQ4qWKc_BXjw__4yRFaDyxXLjuuj9FqMVuYE7Sm3orn-ey0TB94Dj-6n22tybY |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=An+Improved+LightGBM+Algorithm+for+Online+Fault+Detection+of+Wind+Turbine+Gearboxes&rft.jtitle=Energies+%28Basel%29&rft.au=Tang%2C+Mingzhu&rft.au=Zhao%2C+Qi&rft.au=Ding%2C+Steven+X.&rft.au=Wu%2C+Huawei&rft.date=2020-02-01&rft.issn=1996-1073&rft.eissn=1996-1073&rft.volume=13&rft.issue=4&rft.spage=807&rft_id=info:doi/10.3390%2Fen13040807&rft.externalDBID=n%2Fa&rft.externalDocID=10_3390_en13040807 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1996-1073&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1996-1073&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1996-1073&client=summon |