Deep learning for electrolysis process anode effect prediction based on long short-term memory network and stacked denoising autoencoder
The anode effect is a common failure in the aluminium electrolysis industry. If the anode effect cannot be accurately predicted, it will cause increased energy consumption, harmful gas generation and even equipment damage in the aluminium electrolysis. In this paper, an anode effect prediction frame...
Uložené v:
| Vydané v: | Rare metals Ročník 43; číslo 12; s. 6730 - 6741 |
|---|---|
| Hlavní autori: | , , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Beijing
Nonferrous Metals Society of China
01.12.2024
|
| Predmet: | |
| ISSN: | 1001-0521, 1867-7185 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | The anode effect is a common failure in the aluminium electrolysis industry. If the anode effect cannot be accurately predicted, it will cause increased energy consumption, harmful gas generation and even equipment damage in the aluminium electrolysis. In this paper, an anode effect prediction framework using multi-model merging based on deep learning technology is proposed. Different models are used to process aluminium electrolysis cell condition parameters with high dimensions and different characteristics, and hidden key fault information is deeply mined. A stacked denoising autoencoder is utilized to denoise and extract features from a large number of long-period parameter data. A long short-term memory network is implemented to identify the intrinsic links between the real-time voltage and current time series and the anode effect. By setting the model time step, the anode effect can be predicted precisely in advance, and the proposed method has good robustness and generalization. Moreover, the traditional Adam algorithm is improved, which enhances the performance and convergence speed of the model. The experimental results show that the classification accuracy and F1 score of the model are 97.14% and 0.9579%, respectively. The prediction time can reach 15 min.
Graphical abstract |
|---|---|
| AbstractList | The anode effect is a common failure in the aluminium electrolysis industry. If the anode effect cannot be accurately predicted, it will cause increased energy consumption, harmful gas generation and even equipment damage in the aluminium electrolysis. In this paper, an anode effect prediction framework using multi-model merging based on deep learning technology is proposed. Different models are used to process aluminium electrolysis cell condition parameters with high dimensions and different characteristics, and hidden key fault information is deeply mined. A stacked denoising autoencoder is utilized to denoise and extract features from a large number of long-period parameter data. A long short-term memory network is implemented to identify the intrinsic links between the real-time voltage and current time series and the anode effect. By setting the model time step, the anode effect can be predicted precisely in advance, and the proposed method has good robustness and generalization. Moreover, the traditional Adam algorithm is improved, which enhances the performance and convergence speed of the model. The experimental results show that the classification accuracy and F1 score of the model are 97.14% and 0.9579%, respectively. The prediction time can reach 15 min.
Graphical abstract The anode effect is a common failure in the aluminium electrolysis industry. If the anode effect cannot be accurately predicted, it will cause increased energy consumption, harmful gas generation and even equipment damage in the aluminium electrolysis. In this paper, an anode effect prediction framework using multi‐model merging based on deep learning technology is proposed. Different models are used to process aluminium electrolysis cell condition parameters with high dimensions and different characteristics, and hidden key fault information is deeply mined. A stacked denoising autoencoder is utilized to denoise and extract features from a large number of long‐period parameter data. A long short‐term memory network is implemented to identify the intrinsic links between the real‐time voltage and current time series and the anode effect. By setting the model time step, the anode effect can be predicted precisely in advance, and the proposed method has good robustness and generalization. Moreover, the traditional Adam algorithm is improved, which enhances the performance and convergence speed of the model. The experimental results show that the classification accuracy and F1 score of the model are 97.14% and 0.9579%, respectively. The prediction time can reach 15 min. Graphical 摘要 阳极效应是铝电解生产过程中最为常见的故障，阳极效应会增加能耗，产生有害气体，造成设备损坏。本文结合铝电解生产数据特点提出了一种基于深度学习的多模型融合阳极效应预测框架，采用不同的算法处理高维、不同特征的铝电解槽运行参数，充分挖掘隐藏的关键故障信息，具有很好的鲁棒性和泛化性。利用堆叠降噪自动编码器(SDAE)对大量日采集参数去噪并提取特征，采用长短期记忆网络(LSTM)识别实时电压和电流的时间序列与阳极效应的内在联系，通过设定模型时间步长对阳极效应进行预测。同时采用改进的Adam算法对模型进行优化，提高了模型的性能和收敛速度。实验结果表明，该模型的分类准确率为97.14%，F1分数为0.9579，预测时间可达15 min。 The anode effect is a common failure in the aluminium electrolysis industry. If the anode effect cannot be accurately predicted, it will cause increased energy consumption, harmful gas generation and even equipment damage in the aluminium electrolysis. In this paper, an anode effect prediction framework using multi‐model merging based on deep learning technology is proposed. Different models are used to process aluminium electrolysis cell condition parameters with high dimensions and different characteristics, and hidden key fault information is deeply mined. A stacked denoising autoencoder is utilized to denoise and extract features from a large number of long‐period parameter data. A long short‐term memory network is implemented to identify the intrinsic links between the real‐time voltage and current time series and the anode effect. By setting the model time step, the anode effect can be predicted precisely in advance, and the proposed method has good robustness and generalization. Moreover, the traditional Adam algorithm is improved, which enhances the performance and convergence speed of the model. The experimental results show that the classification accuracy and F1 score of the model are 97.14% and 0.9579%, respectively. The prediction time can reach 15 min. 阳极效应是铝电解生产过程中最为常见的故障，阳极效应会增加能耗，产生有害气体，造成设备损坏。本文结合铝电解生产数据特点提出了一种基于深度学习的多模型融合阳极效应预测框架，采用不同的算法处理高维、不同特征的铝电解槽运行参数，充分挖掘隐藏的关键故障信息，具有很好的鲁棒性和泛化性。利用堆叠降噪自动编码器(SDAE)对大量日采集参数去噪并提取特征，采用长短期记忆网络(LSTM)识别实时电压和电流的时间序列与阳极效应的内在联系，通过设定模型时间步长对阳极效应进行预测。同时采用改进的Adam算法对模型进行优化，提高了模型的性能和收敛速度。实验结果表明，该模型的分类准确率为97.14%，F1分数为0.9579，预测时间可达15 min。 |
| Author | Lu, Jian Li, Yi-Hui Cao, Wen-Qi Yin, Gang Xu, Heng-Quan He, Wen Quan, Peng-Cheng Wang, Min Yan, Fei-Ya |
| Author_xml | – sequence: 1 givenname: Gang surname: Yin fullname: Yin, Gang email: yk115@cqu.edu.cn organization: School of Resource and Safety Engineering, and State Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University – sequence: 2 givenname: Yi-Hui orcidid: 0000-0002-6563-8772 surname: Li fullname: Li, Yi-Hui organization: School of Resource and Safety Engineering, and State Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University – sequence: 3 givenname: Fei-Ya surname: Yan fullname: Yan, Fei-Ya organization: Guiyang Aluminium Magnesium Design and Research Institute Co., Ltd – sequence: 4 givenname: Peng-Cheng surname: Quan fullname: Quan, Peng-Cheng organization: Aba Aluminium Factory – sequence: 5 givenname: Min surname: Wang fullname: Wang, Min organization: Chongqing Qineng Electric Aluminium Co., Ltd – sequence: 6 givenname: Wen-Qi surname: Cao fullname: Cao, Wen-Qi organization: Bomei Qimingxing Aluminium Co., Ltd – sequence: 7 givenname: Heng-Quan surname: Xu fullname: Xu, Heng-Quan organization: Aba Aluminium Factory – sequence: 8 givenname: Jian surname: Lu fullname: Lu, Jian organization: Guiyang Aluminium Magnesium Design and Research Institute Co., Ltd – sequence: 9 givenname: Wen surname: He fullname: He, Wen organization: Bomei Qimingxing Aluminium Co., Ltd |
| BookMark | eNqNkMtOAyEUQInRxPr4AVf8wOiFmYFpXNVH1aSJidE1oXBHsVNoAKP9Az9bal25MC7IfcC5N5wDsuuDR0JOGJwyAHmWGG_HXQW8KUcKUX3skBHrhKwk69rdkgOwClrO9slBSq8ATSMEjMjnFeKKDqijd_6Z9iFSHNDkGIZ1comuYjCYEtU-WKTY9-WuNNE6k13wdK4TWlqSIRQ8vYSYq4xxSZe4DHFNPeb3EBeFtzRlbRbltUUfXNqs0285oDdldDwie70eEh7_xEPyNL1-vLytZvc3d5eTWWXqpmZVO5edRJyPTYfC9lpLkIKJ3gB2UrYcONixER1wNC1Y0EJrK4WseduYMYr6kHTbuSaGlCL2yrisN3_JUbtBMVAbo2prVBWj6tuo-igo_4WuolvquP4bOt9C727A9T8I9TB54BfTUjFW6HpLpwL6Z4zqNbxFXwT9tfMLQUahTg |
| CitedBy_id | crossref_primary_10_1016_j_ultras_2025_107778 crossref_primary_10_1016_j_neucom_2025_131485 crossref_primary_10_1109_JSEN_2025_3547369 |
| Cites_doi | 10.1016/j.jmst.2023.05.010 10.1109/access.2020.3041834 10.1093/bioinformatics/btz682 10.1177/1475921719893594 10.1016/j.jmst.2022.05.051 10.1016/j.jclepro.2017.06.199 10.1007/s12598-021-01911-0 10.1007/bf03338607 10.1109/tii.2017.2780884 10.1109/tnnls.2016.2551940 10.1088/1361-6501/aaee5e 10.3390/rs10010016 10.5545/sv-jme.2018.5249 10.3934/jimo.2016066 10.1007/s40820-023-01192-5 10.1016/j.patrec.2014.01.008 10.1007/s12598-023-02282-4 10.1109/access.2019.2907000 10.1016/j.ress.2022.108445 10.1109/tim.2022.3225044 10.1016/j.apacoust.2020.107391 10.1016/j.sigpro.2016.07.028 10.3934/jimo.2018060 10.1007/s11837-016-2043-6 10.1098/rspa.2017.0844 10.1088/1361-6501/ab2b89 10.1109/tie.2015.2510977 10.1007/s12598-022-02238-0 10.1088/1361‐6501/ab2b89 10.1007/s12598‐022‐02238‐0 10.1007/s12598‐021‐01911‐0 10.5545/sv‐jme.2018.5249 10.1007/s12598‐023‐02282‐4 10.1007/s40820‐023‐01192‐5 10.1088/1361‐6501/aaee5e 10.1109/CAC.2017.8242789 10.1007/s11837‐016‐2043‐6 |
| ContentType | Journal Article |
| Copyright | Youke Publishing Co.,Ltd 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. 2024 Youke Publishing Co., Ltd. |
| Copyright_xml | – notice: Youke Publishing Co.,Ltd 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. – notice: 2024 Youke Publishing Co., Ltd. |
| DBID | AAYXX CITATION |
| DOI | 10.1007/s12598-024-02766-x |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1867-7185 |
| EndPage | 6741 |
| ExternalDocumentID | 10_1007_s12598_024_02766_x RAR2BF02711 |
| Genre | article |
| GrantInformation_xml | – fundername: the General Program of National Natural Science Foundation of China grantid: 51374268 – fundername: the Chongqing Talent Innovation and Entrepreneurship Demonstration Team Project grantid: CQYC202203091061 – fundername: the Major Projects for Technological Transformation grantid: H20201555 – fundername: Major Projects for Technological Transformation funderid: H20201555 – fundername: General Program of National Natural Science Foundation of China funderid: 51374268 – fundername: Chongqing Talent Innovation and Entrepreneurship Demonstration Team Project funderid: CQYC202203091061 |
| GroupedDBID | --K -EM -SB -S~ 06D 0R~ 0VY 188 1B1 29P 2B. 2C0 2KG 2VQ 30V 4.4 406 408 40D 5VR 5VS 5XA 5XC 8FE 8FG 8RM 8TC 92H 92I 92R 93N 96X AAAVM AACDK AAEDT AAHNG AAIAL AAJBT AAJKR AALRI AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAXDM AAXUO AAYIU AAYQN AAYTO AAYZH AAZMS ABAKF ABDZT ABECU ABFTD ABFTV ABJCF ABJNI ABJOX ABKCH ABMQK ABQBU ABSXP ABTEG ABTHY ABTKH ABTMW ABWVN ABXPI ACAOD ACBXY ACDTI ACGFS ACHSB ACIWK ACKNC ACMDZ ACMLO ACOKC ACPIV ACRPL ACZOJ ADHHG ADHIR ADINQ ADKNI ADMLS ADMUD ADNMO ADRFC ADURQ ADYFF ADZKW AEBTG AEFQL AEGNC AEJHL AEJRE AEMSY AENEX AEOHA AEPYU AESKC AETCA AEVLU AEXYK AFBBN AFGCZ AFKRA AFLOW AFQWF AFUIB AFWTZ AFZKB AGAYW AGDGC AGJBK AGMZJ AGQEE AGQMX AGRTI AGWZB AGYKE AHAVH AHBYD AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALFXC ALMA_UNASSIGNED_HOLDINGS AMKLP AMXSW AMYLF AMYQR ANMIH AOCGG AXYYD BA0 BENPR BGLVJ BGNMA CAG CAJEB CCEZO CCPQU CDRFL CHBEP COF CW9 D1I DDRTE DNIVK DPUIP DU5 EBLON EBS EIOEI EJD EO9 ESBYG FA0 FDB FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FYJPI GGCAI GGRSB GJIRD GQ6 GQ7 H13 HCIFZ HF~ HG6 HLICF HMJXF HRMNR HZ~ I0C IKXTQ IWAJR I~X J-C JBSCW JZLTJ KB. KOV LLZTM M41 M4Y MA- NPVJJ NQJWS NU0 O9- O9J P9N PDBOC PT4 Q-- Q2X R9I RIG RLLFE ROL RSV S1Z S27 S3B SCL SCM SDC SDG SDH SHX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE T13 TCJ TGT TSG U1G U2A U5L UG4 UGNYK UOJIU UTJUX UY8 UZ4 UZXMN VC2 VFIZW W48 WK8 Z7R Z7V Z7X Z7Y Z7Z Z85 Z88 ZMTXR ~A9 AAPKM ABBRH ABDBE ABFSG ABRTQ ACSTC AEUYN AEZWR AFDZB AFHIU AFOHR AHPBZ AHWEU AIGII AIXLP ATHPR AYFIA M7S PHGZM PHGZT PQGLB PTHSS AAYXX AFFHD CITATION |
| ID | FETCH-LOGICAL-c3431-5b787eeb9c8e6dfaa707616fc0e87752020d9c6802ec50d0a6aad7673254c9e63 |
| IEDL.DBID | RSV |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001266533300004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1001-0521 |
| IngestDate | Tue Nov 18 21:38:53 EST 2025 Sat Nov 29 06:51:50 EST 2025 Thu Oct 09 10:00:25 EDT 2025 Fri Feb 21 02:38:10 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 12 |
| Keywords | Deep learning Improved Adam algorithm Aluminium electrolysis Merging model Anode effect prediction |
| Language | English |
| License | http://onlinelibrary.wiley.com/termsAndConditions#vor |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3431-5b787eeb9c8e6dfaa707616fc0e87752020d9c6802ec50d0a6aad7673254c9e63 |
| Notes | Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self‐archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Copyright comment |
| ORCID | 0000-0002-6563-8772 |
| PageCount | 12 |
| ParticipantIDs | crossref_citationtrail_10_1007_s12598_024_02766_x crossref_primary_10_1007_s12598_024_02766_x wiley_primary_10_1007_s12598_024_02766_x_RAR2BF02711 springer_journals_10_1007_s12598_024_02766_x |
| PublicationCentury | 2000 |
| PublicationDate | 20241200 December 2024 2024-12-00 |
| PublicationDateYYYYMMDD | 2024-12-01 |
| PublicationDate_xml | – month: 12 year: 2024 text: 20241200 |
| PublicationDecade | 2020 |
| PublicationPlace | Beijing |
| PublicationPlace_xml | – name: Beijing |
| PublicationTitle | Rare metals |
| PublicationTitleAbbrev | Rare Met |
| PublicationYear | 2024 |
| Publisher | Nonferrous Metals Society of China |
| Publisher_xml | – name: Nonferrous Metals Society of China |
| References | Lu, Wang, Qin, Ma (CR20) 2017; 130 Pan, Kong, Chen, Zhou, Liu, Xu (CR18) 2019; 30 Yin, Xiang, Wang, Xiang, He, Cao (CR22) 2023; 47 Yi, Bai, Zhou, He, Yao (CR5) 2018; 14 Wang, Wu, Dong, Pan, Zhou, Wang, Guo, Wu, Gao, Dai, Mao (CR11) 2023; 165 Chen, Jiang, Fang, Zhu, Ye, Liu (CR9) 2022; 41 Lee, Yoon, Kim, Kim, Kim, So, Kang (CR34) 2020; 36 Zhu, Pan, Wu, Zhou, Li, Ren, Shi, Yu, Wei, Wu, Yang (CR14) 2023; 42 CR15 Dion, Marks, Kiss, Poncsak, Lagace (CR2) 2017; 164 Liu, Yang, Cai, Wang, Lai, Hao, Wang (CR8) 2023; 42 CR33 Langkvist, Karlsson, Loutfi (CR19) 2014; 42 Liang, Shi, Zhang (CR27) 2018; 10 Vlachas, Byeon, Wan, Sapsis, Koumoutsakos (CR30) 2018; 474 Kong, Yu, Teo, Yang (CR4) 2017; 13 Wang, Zhao, Teng, Sun (CR25) 2020; 167 Yi, Huang, Fu, He, Li (CR6) 2016; 63 Zhou, Zhang, Liu, Hu, Duan, Xu (CR16) 2019; 30 Yin, Li, He, Cao, Wang, Yan, Xiang, Lu, Luo, Lu (CR10) 2023; 74 Chen, Li, Chen, Yang, Gui (CR17) 2019; 15 CR3 Li, Wu, Zhang, Wu, Pan, Wang, Liu, Liu, Yao, Zhang (CR13) 2023; 15 Dion, Kiss, Poncsak, Lagace (CR1) 2016; 68 De Bruin, Verbert, Babuska (CR29) 2017; 28 Chen, Wang, Xiong, Wu, Gao, Wu, Ma, Wu, Mao (CR12) 2023; 132 Zhou, Shi, Yin, He, Yi (CR24) 2020; 8 Farrow (CR7) 1984; 36 Yan, Liu, Jia (CR26) 2020; 19 Dai, Li, Li (CR21) 2019; 7 Zhou, Zheng, Yin, Pang, Yi (CR23) 2023; 72 Zhang, Hu, Yang (CR32) 2022; 222 Pan, He, Tang, Meng (CR31) 2018; 64 Yin, Chen, He, He, Luo, Tang (CR28) 2021; 45 2019; 7 2023; 74 2021; 45 2019; 30 2023; 15 2017; 28 2019; 15 2023; 165 2020; 36 2022; 41 2017; 130 2020; 167 2002 2018; 64 2020; 19 2014; 42 2023; 42 2020; 8 2022; 222 2018; 474 2023; 47 1984; 36 2017; 13 2023; 132 2016; 63 2017 2017; 164 2018; 10 2016; 68 2023; 72 2018; 14 e_1_2_9_30_1 e_1_2_9_31_1 e_1_2_9_34_1 e_1_2_9_10_1 e_1_2_9_35_1 e_1_2_9_13_1 e_1_2_9_32_1 e_1_2_9_12_1 e_1_2_9_33_1 Yin G (e_1_2_9_23_1) 2023; 47 Yin G (e_1_2_9_29_1) 2021; 45 e_1_2_9_15_1 e_1_2_9_14_1 e_1_2_9_17_1 e_1_2_9_16_1 e_1_2_9_19_1 e_1_2_9_18_1 e_1_2_9_20_1 e_1_2_9_22_1 e_1_2_9_21_1 e_1_2_9_24_1 e_1_2_9_8_1 e_1_2_9_7_1 e_1_2_9_6_1 e_1_2_9_5_1 e_1_2_9_4_1 e_1_2_9_3_1 e_1_2_9_2_1 e_1_2_9_9_1 e_1_2_9_26_1 e_1_2_9_25_1 e_1_2_9_28_1 e_1_2_9_27_1 Yin G (e_1_2_9_11_1) 2023; 74 |
| References_xml | – volume: 165 start-page: 49 year: 2023 ident: CR11 article-title: Atomic-scale simulations in multi-component alloys and compounds: a review on advances in interatomic potential publication-title: J Mater Sci Technol doi: 10.1016/j.jmst.2023.05.010 – volume: 8 start-page: 220374 year: 2020 ident: CR24 article-title: Optimal control for aluminum electrolysis process using adaptive dynamic programming publication-title: IEEE Access doi: 10.1109/access.2020.3041834 – volume: 36 start-page: 1234 issue: 4 year: 2020 ident: CR34 article-title: BioBERT: a pre-trained biomedical language representation model for biomedical text mining publication-title: Bioinformatics doi: 10.1093/bioinformatics/btz682 – volume: 19 start-page: 1602 issue: 5 year: 2020 ident: CR26 article-title: Health condition identification for rolling bearing using a multi-domain indicator-based optimized stacked denoising autoencoder publication-title: Struct Health Monit-Int J doi: 10.1177/1475921719893594 – volume: 132 start-page: 213 year: 2023 ident: CR12 article-title: Identifying facile material descriptors for Charpy impact toughness in low-alloy steel via machine learning publication-title: J Mater Sci Technol doi: 10.1016/j.jmst.2022.05.051 – volume: 164 start-page: 357 year: 2017 ident: CR2 article-title: Quantification of perfluorocarbons emissions during high voltage anode effects using non-linear approach publication-title: J Clean Prod doi: 10.1016/j.jclepro.2017.06.199 – volume: 41 start-page: 1543 issue: 5 year: 2022 ident: CR9 article-title: Machine learning assisted discovering of new M2X3-type thermoelectric materials publication-title: Rare Met doi: 10.1007/s12598-021-01911-0 – volume: 36 start-page: 33 issue: 11 year: 1984 ident: CR7 article-title: Prediction of anode effects in aluminum reduction cells publication-title: J Metals doi: 10.1007/bf03338607 – ident: CR33 – volume: 14 start-page: 3405 issue: 8 year: 2018 ident: CR5 article-title: Operating parameters optimization for the aluminum electrolysis process using an improved quantum-behaved particle swarm algorithm publication-title: IEEE Trans Ind Inf doi: 10.1109/tii.2017.2780884 – volume: 28 start-page: 523 issue: 3 year: 2017 ident: CR29 article-title: Railway track circuit fault diagnosis using recurrent neural networks publication-title: IEEE Trans Neural Netw Learn Syst doi: 10.1109/tnnls.2016.2551940 – volume: 30 start-page: 1 issue: 1 year: 2019 ident: CR16 article-title: Anode effect prediction based on a singular value thresholding and extreme gradient boosting approach publication-title: Meas Sci Technol doi: 10.1088/1361-6501/aaee5e – volume: 10 start-page: 1 issue: 1 year: 2018 ident: CR27 article-title: Remote sensing image classification based on stacked denoising autoencoder publication-title: Remote Sens doi: 10.3390/rs10010016 – volume: 47 start-page: 273 issue: 2 year: 2023 ident: CR22 article-title: Prediction method of remaining life of aluminum reduction cell based on data drive publication-title: Chin J Rare Met – volume: 74 start-page: 3419 issue: 8 year: 2023 ident: CR10 article-title: Early warning method of aluminum reduction cell leakage accident based on KPCA and SVM publication-title: CIESC J – volume: 64 start-page: 443 issue: 7 year: 2018 ident: CR31 article-title: An improved bearing fault diagnosis method using one-dimensional CNN and LSTM publication-title: Stroj Vestn-J Mech E doi: 10.5545/sv-jme.2018.5249 – volume: 13 start-page: 1149 issue: 3 year: 2017 ident: CR4 article-title: Robust real-time optimization for blending operation of alumina production publication-title: J Ind Manag Optim doi: 10.3934/jimo.2016066 – volume: 15 start-page: 1 issue: 1 year: 2023 ident: CR13 article-title: Machine learning-assisted low-dimensional electrocatalysts design for hydrogen evolution reaction publication-title: Nano-Micro Lett doi: 10.1007/s40820-023-01192-5 – volume: 42 start-page: 11 year: 2014 ident: CR19 article-title: A review of unsupervised feature learning and deep learning for time-series modeling publication-title: Pattern Recogn Lett doi: 10.1016/j.patrec.2014.01.008 – volume: 42 start-page: 2396 issue: 7 year: 2023 ident: CR14 article-title: Improved material descriptors for bulk modulus in intermetallic compounds via machine learning publication-title: Rare Met doi: 10.1007/s12598-023-02282-4 – volume: 7 start-page: 38287 year: 2019 ident: CR21 article-title: Modeling vehicle interactions via modified LSTM models for trajectory prediction publication-title: IEEE Access doi: 10.1109/access.2019.2907000 – volume: 222 start-page: 1 year: 2022 ident: CR32 article-title: Anomaly detection and diagnosis for wind turbines using long short-term memory-based stacked denoising autoencoders and XGBoost publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2022.108445 – volume: 72 start-page: 1 year: 2023 ident: CR23 article-title: YOLOTrashCan: a deep learning marine debris detection network publication-title: IEEE Trans Instrum Meas doi: 10.1109/tim.2022.3225044 – volume: 167 start-page: 1 year: 2020 ident: CR25 article-title: A stacked convolutional sparse denoising autoencoder model for underwater heterogeneous information data publication-title: Appl Acoust doi: 10.1016/j.apacoust.2020.107391 – ident: CR3 – ident: CR15 – volume: 130 start-page: 377 year: 2017 ident: CR20 article-title: Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification publication-title: Signal Process doi: 10.1016/j.sigpro.2016.07.028 – volume: 45 start-page: 428 issue: 4 year: 2021 ident: CR28 article-title: A method for anode effect prediction of aluminium electrolysis cell based on SDAE and random forest publication-title: Chin J Rare Met – volume: 15 start-page: 595 issue: 2 year: 2019 ident: CR17 article-title: Anode effect prediction based on collaborative two-dimensional forecast model in aluminum electrolysis production publication-title: J Ind Manag Optim doi: 10.3934/jimo.2018060 – volume: 68 start-page: 2472 issue: 9 year: 2016 ident: CR1 article-title: Prediction of low-voltage tetrafluoromethane emissions based on the operating conditions of an aluminium electrolysis cell publication-title: JOM doi: 10.1007/s11837-016-2043-6 – volume: 474 start-page: 1 issue: 2213 year: 2018 ident: CR30 article-title: Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks publication-title: Proc Royal Soc Math Phys Eng Sci doi: 10.1098/rspa.2017.0844 – volume: 30 start-page: 1 issue: 11 year: 2019 ident: CR18 article-title: A modified neighborhood mutual information and light gradient boosting machine-based long-term prediction approach for anode effect publication-title: Meas Sci Technol doi: 10.1088/1361-6501/ab2b89 – volume: 63 start-page: 2488 issue: 4 year: 2016 ident: CR6 article-title: Multi-objective bacterial foraging optimization algorithm based on parallel cell entropy for aluminum electrolysis production process publication-title: IEEE Trans Ind Electron doi: 10.1109/tie.2015.2510977 – volume: 42 start-page: 2713 issue: 8 year: 2023 ident: CR8 article-title: Prediction of sintered density of binary W(Mo) alloys using machine learning publication-title: Rare Met doi: 10.1007/s12598-022-02238-0 – start-page: 1 year: 2017 – volume: 132 start-page: 213 year: 2023 article-title: Identifying facile material descriptors for Charpy impact toughness in low‐alloy steel via machine learning publication-title: J Mater Sci Technol – volume: 30 start-page: 1 issue: 11 year: 2019 article-title: A modified neighborhood mutual information and light gradient boosting machine‐based long‐term prediction approach for anode effect publication-title: Meas Sci Technol – volume: 68 start-page: 2472 issue: 9 year: 2016 article-title: Prediction of low‐voltage tetrafluoromethane emissions based on the operating conditions of an aluminium electrolysis cell publication-title: JOM – volume: 13 start-page: 1149 issue: 3 year: 2017 article-title: Robust real‐time optimization for blending operation of alumina production publication-title: J Ind Manag Optim – volume: 15 start-page: 1 issue: 1 year: 2023 article-title: Machine learning‐assisted low‐dimensional electrocatalysts design for hydrogen evolution reaction publication-title: Nano‐Micro Lett – volume: 42 start-page: 2396 issue: 7 year: 2023 article-title: Improved material descriptors for bulk modulus in intermetallic compounds via machine learning publication-title: Rare Met – volume: 42 start-page: 11 year: 2014 article-title: A review of unsupervised feature learning and deep learning for time‐series modeling publication-title: Pattern Recogn Lett – volume: 63 start-page: 2488 issue: 4 year: 2016 article-title: Multi‐objective bacterial foraging optimization algorithm based on parallel cell entropy for aluminum electrolysis production process publication-title: IEEE Trans Ind Electron – volume: 41 start-page: 1543 issue: 5 year: 2022 article-title: Machine learning assisted discovering of new M2X3‐type thermoelectric materials publication-title: Rare Met – volume: 42 start-page: 2713 issue: 8 year: 2023 article-title: Prediction of sintered density of binary W(Mo) alloys using machine learning publication-title: Rare Met – volume: 28 start-page: 523 issue: 3 year: 2017 article-title: Railway track circuit fault diagnosis using recurrent neural networks publication-title: IEEE Trans Neural Netw Learn Syst – volume: 474 start-page: 1 issue: 2213 year: 2018 article-title: Data‐driven forecasting of high‐dimensional chaotic systems with long short‐term memory networks publication-title: Proc Royal Soc Math Phys Eng Sci – volume: 36 start-page: 33 issue: 11 year: 1984 article-title: Prediction of anode effects in aluminum reduction cells publication-title: J Metals – volume: 15 start-page: 595 issue: 2 year: 2019 article-title: Anode effect prediction based on collaborative two‐dimensional forecast model in aluminum electrolysis production publication-title: J Ind Manag Optim – volume: 167 start-page: 1 year: 2020 article-title: A stacked convolutional sparse denoising autoencoder model for underwater heterogeneous information data publication-title: Appl Acoust – volume: 14 start-page: 3405 issue: 8 year: 2018 article-title: Operating parameters optimization for the aluminum electrolysis process using an improved quantum‐behaved particle swarm algorithm publication-title: IEEE Trans Ind Inf – volume: 164 start-page: 357 year: 2017 article-title: Quantification of perfluorocarbons emissions during high voltage anode effects using non‐linear approach publication-title: J Clean Prod – volume: 47 start-page: 273 issue: 2 year: 2023 article-title: Prediction method of remaining life of aluminum reduction cell based on data drive publication-title: Chin J Rare Met – volume: 10 start-page: 1 issue: 1 year: 2018 article-title: Remote sensing image classification based on stacked denoising autoencoder publication-title: Remote Sens – volume: 8 start-page: 220374 year: 2020 article-title: Optimal control for aluminum electrolysis process using adaptive dynamic programming publication-title: IEEE Access – volume: 45 start-page: 428 issue: 4 year: 2021 article-title: A method for anode effect prediction of aluminium electrolysis cell based on SDAE and random forest publication-title: Chin J Rare Met – start-page: 341 year: 2017 – volume: 7 start-page: 38287 year: 2019 article-title: Modeling vehicle interactions via modified LSTM models for trajectory prediction publication-title: IEEE Access – volume: 36 start-page: 1234 issue: 4 year: 2020 article-title: BioBERT: a pre‐trained biomedical language representation model for biomedical text mining publication-title: Bioinformatics – volume: 19 start-page: 1602 issue: 5 year: 2020 article-title: Health condition identification for rolling bearing using a multi‐domain indicator‐based optimized stacked denoising autoencoder publication-title: Struct Health Monit‐Int J – volume: 130 start-page: 377 year: 2017 article-title: Fault diagnosis of rotary machinery components using a stacked denoising autoencoder‐based health state identification publication-title: Signal Process – volume: 64 start-page: 443 issue: 7 year: 2018 article-title: An improved bearing fault diagnosis method using one‐dimensional CNN and LSTM publication-title: Stroj Vestn‐J Mech E – volume: 222 start-page: 1 year: 2022 article-title: Anomaly detection and diagnosis for wind turbines using long short‐term memory‐based stacked denoising autoencoders and XGBoost publication-title: Reliab Eng Syst Saf – volume: 74 start-page: 3419 issue: 8 year: 2023 article-title: Early warning method of aluminum reduction cell leakage accident based on KPCA and SVM publication-title: CIESC J – volume: 30 start-page: 1 issue: 1 year: 2019 article-title: Anode effect prediction based on a singular value thresholding and extreme gradient boosting approach publication-title: Meas Sci Technol – volume: 72 start-page: 1 year: 2023 article-title: YOLOTrashCan: a deep learning marine debris detection network publication-title: IEEE Trans Instrum Meas – start-page: 503 year: 2002 – volume: 165 start-page: 49 year: 2023 article-title: Atomic‐scale simulations in multi‐component alloys and compounds: a review on advances in interatomic potential publication-title: J Mater Sci Technol – ident: e_1_2_9_19_1 doi: 10.1088/1361‐6501/ab2b89 – volume: 47 start-page: 273 issue: 2 year: 2023 ident: e_1_2_9_23_1 article-title: Prediction method of remaining life of aluminum reduction cell based on data drive publication-title: Chin J Rare Met – ident: e_1_2_9_9_1 doi: 10.1007/s12598‐022‐02238‐0 – ident: e_1_2_9_26_1 doi: 10.1016/j.apacoust.2020.107391 – ident: e_1_2_9_21_1 doi: 10.1016/j.sigpro.2016.07.028 – ident: e_1_2_9_10_1 doi: 10.1007/s12598‐021‐01911‐0 – ident: e_1_2_9_31_1 doi: 10.1098/rspa.2017.0844 – ident: e_1_2_9_35_1 doi: 10.1093/bioinformatics/btz682 – ident: e_1_2_9_32_1 doi: 10.5545/sv‐jme.2018.5249 – ident: e_1_2_9_15_1 doi: 10.1007/s12598‐023‐02282‐4 – volume: 45 start-page: 428 issue: 4 year: 2021 ident: e_1_2_9_29_1 article-title: A method for anode effect prediction of aluminium electrolysis cell based on SDAE and random forest publication-title: Chin J Rare Met – ident: e_1_2_9_12_1 doi: 10.1016/j.jmst.2023.05.010 – ident: e_1_2_9_22_1 doi: 10.1109/access.2019.2907000 – ident: e_1_2_9_14_1 doi: 10.1007/s40820‐023‐01192‐5 – ident: e_1_2_9_3_1 doi: 10.1016/j.jclepro.2017.06.199 – ident: e_1_2_9_7_1 doi: 10.1109/tie.2015.2510977 – ident: e_1_2_9_30_1 doi: 10.1109/tnnls.2016.2551940 – ident: e_1_2_9_20_1 doi: 10.1016/j.patrec.2014.01.008 – ident: e_1_2_9_27_1 doi: 10.1177/1475921719893594 – ident: e_1_2_9_6_1 doi: 10.1109/tii.2017.2780884 – ident: e_1_2_9_17_1 doi: 10.1088/1361‐6501/aaee5e – ident: e_1_2_9_25_1 doi: 10.1109/access.2020.3041834 – ident: e_1_2_9_4_1 – ident: e_1_2_9_5_1 doi: 10.3934/jimo.2016066 – ident: e_1_2_9_33_1 doi: 10.1016/j.ress.2022.108445 – ident: e_1_2_9_24_1 doi: 10.1109/tim.2022.3225044 – ident: e_1_2_9_28_1 doi: 10.3390/rs10010016 – ident: e_1_2_9_8_1 doi: 10.1007/bf03338607 – ident: e_1_2_9_13_1 doi: 10.1016/j.jmst.2022.05.051 – ident: e_1_2_9_18_1 doi: 10.3934/jimo.2018060 – ident: e_1_2_9_16_1 doi: 10.1109/CAC.2017.8242789 – ident: e_1_2_9_34_1 – ident: e_1_2_9_2_1 doi: 10.1007/s11837‐016‐2043‐6 – volume: 74 start-page: 3419 issue: 8 year: 2023 ident: e_1_2_9_11_1 article-title: Early warning method of aluminum reduction cell leakage accident based on KPCA and SVM publication-title: CIESC J |
| SSID | ssj0044660 |
| Score | 2.3707716 |
| Snippet | The anode effect is a common failure in the aluminium electrolysis industry. If the anode effect cannot be accurately predicted, it will cause increased energy... |
| SourceID | crossref wiley springer |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 6730 |
| SubjectTerms | Aluminium electrolysis Anode effect prediction Biomaterials Chemistry and Materials Science Deep learning Energy Improved Adam algorithm Materials Engineering Materials Science Merging model Metallic Materials Nanoscale Science and Technology Original Article Physical Chemistry |
| Title | Deep learning for electrolysis process anode effect prediction based on long short-term memory network and stacked denoising autoencoder |
| URI | https://link.springer.com/article/10.1007/s12598-024-02766-x https://onlinelibrary.wiley.com/doi/abs/10.1007%2Fs12598-024-02766-x |
| Volume | 43 |
| WOSCitedRecordID | wos001266533300004&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: PRVAVX databaseName: SpringerLink Journals customDbUrl: eissn: 1867-7185 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0044660 issn: 1001-0521 databaseCode: RSV dateStart: 20090201 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3JTsMwELVQ4QAHdkTZ5AM3sJSlsZNjWSoOCKGyqLfIsR2oVJKqaRH8AZ_NTOJQKqEKuCWRl8gez3te5pmQY-FHiQRoZUqEmoFReCzxTQoj3hgBCAMYUarrX4ubm7DXi25tUFhRn3avtyRLTz0NdgOmHjLAFNx35JwBc1wEuAtxOHbvHmv_ixuUlQYBTpQBnWyozM9lzMJRXfEsUy2hprP2v59cJ6uWWtJ2ZQsbZMFkm2Tlm-DgFvm4MGZI7U0RTxQIK7X34JTKJHRYhQ1QmeXa0OqsB3zEzRzsQIqYpyk8DHLIXjwDd2fo2-kLHth9p1l1qBzyawq0EzyEpuDY8j6uSFA5Geeom6nNaJs8dC7vz6-YvYuBKR84BgsSGNnGJJEKDdeplAIXQHiqHBMKEXjAOnWkeOh4RgWOdiSXUgsufJiAqshwf4c0sjwzu4QGMtGBDFwhorSFeoc89VtQvIRivUDzJnHrLomVFSrH-zIG8VRiGVs5hlaOy1aO35rk5CvPsJLpmJv6tO692A7ZYm7yVmkNvyg57ra73lkH3lx372-17JNlD-3G9ZjnHpDGeDQxh2RJvY77xeioNPFPVzn1_A |
| linkProvider | Springer Nature |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1bS8MwFA4yBfXBuzivefBNA10vSfs4L2PiHDKn7K2kSaqD2Y51E_0H_mxP0tY5EFHf2pJLSU7O9yU5-YLQMXOCiAO0EsF8ScAobBI5KoYRrxQDhAGMMOr6LdZu-71ecFscCsvKaPdyS9J46ulhN2DqPgFM0fuOlBJgjvMuIJYO5OvcPZT-V29Q5hoEeqIM6FQclfm-jFk4KiueZaoGahqr__vJNbRSUEtcz21hHc2pZAMtfxEc3ETvF0oNcXFTxCMGwoqLe3CMMgke5scGME9SqXAe6wEf9WaO7kCsMU9ieBikkD17Au5OtG_Hzzpg9w0neVA55JcYaCd4CInBsaV9vSKB-WScat1MqUZb6L5x2T1vkuIuBiIc4BjEi2BkKxUFwldUxpwzvQBCY2EpnzHPBtYpA0F9y1bCs6TFKeeSUebABFQEijrbqJKkidpB2OOR9LhXYyyIXa13SGPHheI5FGt7klZRreySUBRC5fq-jEE4lVjWrRxCK4emlcPXKjr5zDPMZTp-TH1a9l5YDNnsx-SusYZflBx26h37rAFvtdru32o5QovN7k0rbF21r_fQkq1tyITN7KPKeDRRB2hBvIz72ejQmPsH5fn43g |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwFA4yRfTBuzivefBNw7Z2TdrH6RyKY4x5YW8lTVIdzHbsIvoP_Nme04vbQETxrS1JGpKTnC8553yHkFNhe4EE1cqUcDUDobBYYJsQVrwxAjQM6IiEXb8pWi232_XaM1H8ibd7bpJMYxqQpSkalwY6LE0D3wC1uwz0C9ogOWeAIhermDQIz-t3j_lejMbKlI8AD82gqbKwme_bmFdNeSfmUWuidhrr_-_wBlnLICetpTKySRZMtEVWZ4gIt8lH3ZgBzTJIPFEAsjTLj5MwltBBGk5AZRRrQ1MfEPiIRh6cWIq6UFN46MdQffQMmJ7hnk9f0JH3nUapsznU1xTgKOwcmsKGF_fwpoLKyThGPk1thjvkoXF1f3nNshwNTNmAPZgTwIo3JvCUa7gOpRR4McJDVTauEI4FaFR7irtlyyinrMuSS6kFFzYcTJVnuL1LClEcmT1CHRloRzoVIbywijyIPLSr0LyEZi1H8yKp5NPjq4zAHPNo9P0p9TKOsg-j7Cej7L8VydlXnUFK3_Fj6fN8Jv1sKY9-LF5NJOMXLfudWse6aMBbpbL_t7-ckOV2veE3b1q3B2TFQhFKvGkOSWE8nJgjsqRex73R8DiR_E_IQAHR |
| 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=Deep+learning+for+electrolysis+process+anode+effect+prediction+based+on+long+short%E2%80%90term+memory+network+and+stacked+denoising+autoencoder&rft.jtitle=Rare+metals&rft.au=Yin%2C+Gang&rft.au=Li%2C+Yi%E2%80%90Hui&rft.au=Yan%2C+Fei%E2%80%90Ya&rft.au=Quan%2C+Peng%E2%80%90Cheng&rft.date=2024-12-01&rft.issn=1001-0521&rft.eissn=1867-7185&rft.volume=43&rft.issue=12&rft.spage=6730&rft.epage=6741&rft_id=info:doi/10.1007%2Fs12598-024-02766-x&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s12598_024_02766_x |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1001-0521&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1001-0521&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1001-0521&client=summon |