{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T22:40:46Z","timestamp":1776811246784,"version":"3.51.2"},"reference-count":23,"publisher":"European Society of Computational Methods in Sciences and Engineering","issue":"2","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computational Methods in Sciences and Engineering"],"published-print":{"date-parts":[[2024,3]]},"abstract":"<jats:p>Fault detection for photovoltaic power generation system is a challenging problem in condition monitoring and troubleshooting, which aims to maintain the safe operation of equipment and improve the benefit of photovoltaic industry. Aiming at the problems of frequent failures of photovoltaic power generation system, large amount of operating data and difficult to obtain fault samples, we propose an unsupervised fault detection approach for photovoltaic power generation system via bidirectional long\/short memory deep auto-encoder which combines the auto-encoder in deep learning with the Bi-directional Long Short-Term Memory (BiLSTM). Specifically, We first take the statistical feature enhanced as the input of an auto-encoder based on BiLSTM. Then, we build a simulation model of Grid-connected PV system. Finally, we use the operation results under normal conditions to train the fault detection model to obtain the reconstruction error and determine the fault detection threshold, so as to judge the anomalies of the photovoltaic power generation system. We simulate the shadow occlusion fault and verify the effectiveness of the proposed method, and the fault detection accuracy of 0.95 is achieved. Compare with other models, the results show that it could set up better dependence on multi-dimensional data in time sequences, effectively testing solar panel failures and solving insufficient data labels problems.<\/jats:p>","DOI":"10.3233\/jcm-237070","type":"journal-article","created":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T11:41:24Z","timestamp":1715341284000},"page":"849-861","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["Unsupervised fault detection approach based on depth auto-encoder for photovoltaic power generation system"],"prefix":"10.66113","volume":"24","author":[{"given":"Jun","family":"Zhang","sequence":"first","affiliation":[{"name":"Computer Engineering Technical College (Artificial Intelligence College), Guangdong Polytechnic of Science and Technology, Zhuhai, Guangdong, China"}]},{"given":"Zongren","family":"Chen","sequence":"additional","affiliation":[{"name":"Computer Engineering Technical College (Artificial Intelligence College), Guangdong Polytechnic of Science and Technology, Zhuhai, Guangdong, China"}]},{"given":"Weimei","family":"Wu","sequence":"additional","affiliation":[{"name":"Computer Engineering Technical College (Artificial Intelligence College), Guangdong Polytechnic of Science and Technology, Zhuhai, Guangdong, China"}]},{"given":"Liuyang","family":"Shao","sequence":"additional","affiliation":[{"name":"North China Electric Power University","place":["China"]}]},{"given":"Kaihuan","family":"Deng","sequence":"additional","affiliation":[{"name":"North China Electric Power University","place":["China"]}]},{"given":"Shixiong","family":"Gao","sequence":"additional","affiliation":[{"name":"North China Electric Power University","place":["China"]}]}],"member":"55691","published-online":{"date-parts":[[2024,5]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Caithness Windfarm Information Forum. Summary of Wind Turbine Accident data to 30 September 2020 [Internet]. 2020 [cited 2022 Dec 13]. Available from: http:\/\/www.caithnesswindfarms.co.uk."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","unstructured":"MengH YeX YangM SongX SuZ LiuW LuoL ZhaoH. Equivalent modeling and simulation for PV system on dynamic clustering equivalent strategy. In: IECON 2017 \u2013 43rd Annual Conference of the IEEE Industrial Electronics Society; Beijing China. 2017. pp. 5779-84. doi: 10.1109\/IECON.2017.8217002.","DOI":"10.1109\/IECON.2017.8217002"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","unstructured":"ChenR CaoJ ZhangD. Probabilistic Prediction of Photovoltaic Power Using Bayesian Neural Network \u2013 LSTM Model. In: 2021 IEEE 4th International Conference on Renewable Energy and Power Engineering (REPE); Beijing China. 2021. pp. 294-99. doi: 10.1109\/REPE52765.2021.9617071.","DOI":"10.1109\/REPE52765.2021.9617071"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","unstructured":"QinB. Study on Fault Detection and Location of Photovoltaic Array. YunNan Normal University. 2021. doi: 10.27459\/d.cnki.gynfc.2021.001132.","DOI":"10.27459\/d.cnki.gynfc.2021.001132"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2914731"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2020.01.014"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2968370"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","unstructured":"WenT KeyesR. Time Series Anomaly Detection Using Convolutional Neural Networks and Transfer mLearning. 2019. doi: 10.48550\/arXiv.1905.13628.","DOI":"10.48550\/arXiv.1905.13628"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/tie.2018.2844805"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2019.01.022"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2020.02.004"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2018.10.031"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2021.04.025"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.16182\/j.issn1004731x.joss.20-0369"},{"issue":"01","key":"e_1_3_2_17_2","first-page":"81","article-title":"Fault diagnosis of wind turbine generator using deep self coding network and XGBoost","volume":"43","author":"Zhao H","year":"2019","unstructured":"ZhaoH LiuH LiuH LinY. Fault diagnosis of wind turbine generator using deep self coding network and XGBoost. Automat Electric Power Syst. 2019; 43(01): 81-86. doi: CNKI:SUN:DLXT.0.2019-01-010.","journal-title":"Automat Electric Power Syst."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3011441"},{"issue":"11","key":"e_1_3_2_19_2","article-title":"Simulation Research on Improved Photovoltaic Battery MPPT Control Method Based on Conductance Increment Method","volume":"32","author":"Zhou F","year":"2019","unstructured":"ZhouF MiaoZ HanK. Simulation Research on Improved Photovoltaic Battery MPPT Control Method Based on Conductance Increment Method. Ind Control Comput. 2019; 32(11): 88-90, 120. doi: CNKI:SUN:GYKJ.0.2019-11-037.","journal-title":"Ind Control Comput."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.11857\/j.issn.1674-5124.2022040177"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","unstructured":"ChenB WangJ ZhaoM et al. Research on MPPT control of photovoltaic power generation system based on improved whale algorithm. Proc CSU-EPSA. 2023; 35(02): 19-26. doi: 10.19635\/j.cnki.csu-epsa.001057.","DOI":"10.19635\/j.cnki.csu-epsa.001057"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.19805\/j.cnki.jcspe.2022.06.004"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","unstructured":"ZhangX. Research on Wind Turbine Fault Diagnosis Methods Based on Auto-encoder. ZheJiang SCI-TECH University. 2022. doi: 10.27786\/d.cnki.gzjlg.2022.000194.","DOI":"10.27786\/d.cnki.gzjlg.2022.000194"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","unstructured":"WuP ZhangX HeJ LouS GaoJ. Locality Preserving Randomized Canonical Correlation Analysis for Real-time Nonlinear Process Monitoring. Process Safety Environ Prot. 2021. doi: 10.1016\/J.PSEP.2021.01.028.","DOI":"10.1016\/J.PSEP.2021.01.028"}],"container-title":["Journal of Computational Methods in Sciences and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JCM-237070","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JCM-237070","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JCM-237070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T22:05:53Z","timestamp":1776809153000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JCM-237070"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":23,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["10.3233\/JCM-237070"],"URL":"https:\/\/doi.org\/10.3233\/jcm-237070","relation":{},"ISSN":["1472-7978","1875-8983"],"issn-type":[{"value":"1472-7978","type":"print"},{"value":"1875-8983","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}