{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T23:11:04Z","timestamp":1769037064676,"version":"3.49.0"},"reference-count":48,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T00:00:00Z","timestamp":1768953600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Electric arc furnaces (EAF) represent a class of nonlinear loads distinguished by high energy consumption during metal melting processes. Voltage collapses in these systems adversely affect power quality, reduce energy efficiency, and cause significant disruptions in production processes. Consequently, this study investigates the feasibility of deep learning-based approaches for forecasting voltage collapse events induced by the dynamic and nonlinear loads generated by electric arc furnaces. The analysis employs methods developed using the Tabular Network (TabNet) and Neural Oblivious Decision Ensembles (NODE) models to assess the characteristic variations of arc furnaces and their impacts on power systems through both experimental and simulation data. The characteristic behavior of the electric arc was modeled using an exponential-hyperbolic function validated by real-time data, while the simulation model was established in the MATLAB\/Simulink environment to identify voltage collapse events. Critical features such as I1 (current) and V1 (voltage) were found to play a decisive role in predicting voltage collapse, and the decision mechanisms of the models were elucidated in detail using Explainable Artificial Intelligence (XAI) techniques such as SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME). The obtained results indicate that both models achieve an accuracy rate of approximately 95% with balanced classification performance, thereby offering a reliable approach for the early diagnosis of voltage fluctuations and collapse events in power systems. Furthermore, the findings contribute to strategic decision support systems aimed at enhancing safety and energy efficiency in industrial applications and offer a novel perspective on the potential of deep learning models in complex systems.<\/jats:p>","DOI":"10.7717\/peerj-cs.3505","type":"journal-article","created":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T08:43:18Z","timestamp":1768984998000},"page":"e3505","source":"Crossref","is-referenced-by-count":0,"title":["The analysis of voltage collapse induced by nonlinear loads in an arc furnace utilising deep learning-driven TabNet and NODE models"],"prefix":"10.7717","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3729-8170","authenticated-orcid":true,"given":"Bur\u00e7ak","family":"Asal","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Adana Alparslan T\u00fcrke\u015f Science and Technology University, Adana, Turkey"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3880-3039","authenticated-orcid":true,"given":"Saadin","family":"Oyucu","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering\/Faculty of Technology, Gazi University Ankara, Ankara, Turkey"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2563-1218","authenticated-orcid":true,"given":"Ahmet","family":"Aksoz","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Kayseri University, Kayseri, Turkey"}]},{"given":"Mustafa","family":"\u015eeker","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Sivas Cumhuriyet University, Sivas, Turkey"}]}],"member":"4443","published-online":{"date-parts":[[2026,1,21]]},"reference":[{"key":"10.7717\/peerj-cs.3505\/ref-1","first-page":"8","article-title":"STATCOM modeling for mitigation of voltage fluctuations caused by electric arc furnaces","author":"Aguero","year":"2006"},{"key":"10.7717\/peerj-cs.3505\/ref-2","doi-asserted-by":"publisher","first-page":"113512\u2013113531","DOI":"10.1109\/ACCESS.2020.3003568","article-title":"A review of machine learning approaches to power system security and stability","volume":"8","author":"Alimi","year":"2020","journal-title":"IEEE Access"},{"issue":"8","key":"10.7717\/peerj-cs.3505\/ref-3","doi-asserted-by":"publisher","first-page":"6679","DOI":"10.1609\/aaai.v35i8.16826","article-title":"TabNet: attentive interpretable tabular learning","volume":"8A","author":"Arik","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.7717\/peerj-cs.3505\/ref-4","doi-asserted-by":"crossref","DOI":"10.1002\/0470871229","volume-title":"Power system harmonics","author":"Arrillaga","year":"2003","edition":"2"},{"key":"10.7717\/peerj-cs.3505\/ref-5","article-title":"Neutral currents in three phase wye systems","volume-title":"Power Systems Engineering Data","author":"Arthur","year":"1996"},{"key":"10.7717\/peerj-cs.3505\/ref-6","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1016\/j.energy.2016.09.043","article-title":"Analyzing power quality issues in electric arc furnace by modeling","volume":"115","author":"Bhonsle","year":"2016","journal-title":"Energy"},{"key":"10.7717\/peerj-cs.3505\/ref-7","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/0378-7796(85)90054-9","article-title":"A generalized approach to analysis of voltage stability in electric power systems","volume":"9","author":"Brucoli","year":"1985","journal-title":"Electric Power Systems Research"},{"key":"10.7717\/peerj-cs.3505\/ref-8","first-page":"671","article-title":"Voltage collapse proximity indicators computed from an optimal power flow","author":"Carpentier","year":"1984"},{"issue":"3","key":"10.7717\/peerj-cs.3505\/ref-9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5120\/12471-8864","article-title":"Neutral current and neutral voltage in a three phase four wire distribution system of a technical institution","volume":"72","author":"Chakraborty","year":"2013","journal-title":"International Journal of Computer Applications"},{"issue":"9","key":"10.7717\/peerj-cs.3505\/ref-10","doi-asserted-by":"publisher","first-page":"251","DOI":"10.15623\/IJRET.2013.0209037","article-title":"Voltage collapse mitigation by reactive power compensation at the load side","volume":"2","author":"Chayapathi","year":"2013","journal-title":"International Journal of Research in Engineering and Technology"},{"issue":"1","key":"10.7717\/peerj-cs.3505\/ref-11","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1109\/TPWRS.2023.3266956","article-title":"Learning power grid outages with higher-order topological neural networks","volume":"39","author":"Chen","year":"2023","journal-title":"IEEE Transactions on Power Systems"},{"issue":"6","key":"10.7717\/peerj-cs.3505\/ref-12","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/81.928149","article-title":"Anti-control of Hopf bifurcations","volume":"48","author":"Chen","year":"2001","journal-title":"IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications"},{"key":"10.7717\/peerj-cs.3505\/ref-13","article-title":"Prediction of voltage collapse in power system using voltage stability indices","author":"Choudekar","year":"2017"},{"key":"10.7717\/peerj-cs.3505\/ref-14","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-97-4053-6","volume-title":"Electric arc furnace: methods to decrease energy consumption","author":"Conejo","year":"2024"},{"key":"10.7717\/peerj-cs.3505\/ref-15","first-page":"1023","article-title":"Power system voltage stability and control","volume":"3","author":"Costi","year":"1986","journal-title":"Proceedings of the 1986 IEEE International Symposium on Circuits and Systems"},{"issue":"15","key":"10.7717\/peerj-cs.3505\/ref-16","doi-asserted-by":"publisher","first-page":"1676","DOI":"10.1080\/15325008.2012.716495","article-title":"Transmission line fault classification and location using wavelet entropy and neural network","volume":"40","author":"Dasgupta","year":"2012","journal-title":"Electric Power Components and Systems"},{"key":"10.7717\/peerj-cs.3505\/ref-17","volume-title":"Electric power systems quality","author":"Dugan","year":"2004"},{"key":"10.7717\/peerj-cs.3505\/ref-18","first-page":"485","article-title":"Load flow feasibility and the voltage collapse problem","author":"Galiana","year":"1984"},{"issue":"4","key":"10.7717\/peerj-cs.3505\/ref-19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.segan.2015.05.001","article-title":"A control strategy for enhancing the fault ride-through capability of a microgrid during balanced and unbalanced grid voltage sags","volume":"3","author":"Gkavanoudis","year":"2015","journal-title":"Sustainable Energy, Grids and Networks"},{"key":"10.7717\/peerj-cs.3505\/ref-20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.14338","article-title":"TabR: tabular deep learning meets nearest neighbors in 2023","author":"Gorishniy","year":"2023"},{"key":"10.7717\/peerj-cs.3505\/ref-21","first-page":"525","article-title":"Electric furnace steelmaking","volume-title":"The Making, Shaping and Treating of Steel","author":"Jones","year":"1998"},{"issue":"3","key":"10.7717\/peerj-cs.3505\/ref-22","doi-asserted-by":"publisher","first-page":"4978","DOI":"10.1109\/TIA.2024.3358761","article-title":"Application of the deterministic chaos in AC electric arc furnace modeling","volume":"60","author":"Klimas","year":"2024","journal-title":"IEEE Transactions on Industry Applications"},{"issue":"10","key":"10.7717\/peerj-cs.3505\/ref-23","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1109\/TCS.1986.1085856","article-title":"Static bifurcations in electric power networks: loss of steady-state stability and voltage collapse","volume":"33","author":"Kwatny","year":"1986","journal-title":"IEEE Transactions on Circuits and Systems"},{"key":"10.7717\/peerj-cs.3505\/ref-24","doi-asserted-by":"publisher","first-page":"113913","DOI":"10.1016\/j.rser.2023.113913","article-title":"Deep learning based on transformer architecture for power system short-term voltage stability assessment with class imbalance","volume":"189","author":"Li","year":"2024","journal-title":"Renewable and Sustainable Energy Reviews"},{"key":"10.7717\/peerj-cs.3505\/ref-25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3311065","article-title":"PMU measurements-based short-term voltage stability assessment of power systems via deep transfer learning","volume":"72","author":"Li","year":"2023","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.7717\/peerj-cs.3505\/ref-26","first-page":"177","article-title":"Voltage stability assessment in power grids using novel machine learning-based methods","author":"Mollaiee","year":"2021"},{"issue":"2","key":"10.7717\/peerj-cs.3505\/ref-27","doi-asserted-by":"publisher","DOI":"10.4314\/njt.v43i2.14","article-title":"Single topology neural network-based voltage collapse prediction of developing power systems","volume":"43","author":"Onah","year":"2024","journal-title":"Nigerian Journal of Technology"},{"issue":"19","key":"10.7717\/peerj-cs.3505\/ref-28","doi-asserted-by":"publisher","first-page":"3071","DOI":"10.3390\/math12193071","article-title":"Hybrid deep neural network approaches for power quality analysis in electric arc furnaces","volume":"12","author":"Panoiu","year":"2024","journal-title":"Mathematics"},{"key":"10.7717\/peerj-cs.3505\/ref-29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.06312","article-title":"Neural oblivious decision ensembles for deep learning on tabular data","author":"Popov","year":"2019"},{"key":"10.7717\/peerj-cs.3505\/ref-30","doi-asserted-by":"publisher","first-page":"109906","DOI":"10.1016\/j.epsr.2023.109906","article-title":"Quantizing branches\u2019 responsibility for voltage sags\/swells and flicker events","volume":"225","author":"Samet","year":"2023","journal-title":"Electric Power Systems Research"},{"key":"10.7717\/peerj-cs.3505\/ref-31","article-title":"Voltage stability and security assessment, EPRI Draft Final Report, PR-1999-8","author":"Schleuter","year":"1987"},{"issue":"11","key":"10.7717\/peerj-cs.3505\/ref-32","first-page":"274","article-title":"Investigation of voltage quality in electric arc furnace with Matlab\/Simulink","volume":"2","author":"\u015eeker","year":"2014","journal-title":"International Journal of Engineering & Technical Research"},{"issue":"7","key":"10.7717\/peerj-cs.3505\/ref-33","doi-asserted-by":"publisher","first-page":"4005","DOI":"10.3390\/app15074005","article-title":"A novel voltage\u2013current characteristic model for understanding of electric arc furnace behavior using experimental data and grey wolf optimization algorithm","volume":"15","author":"\u015eeker","year":"2025","journal-title":"Applied Sciences"},{"issue":"3","key":"10.7717\/peerj-cs.3505\/ref-34","doi-asserted-by":"publisher","first-page":"30","DOI":"10.5755\/j01.eie.23.3.18328","article-title":"An experimental approach for understanding v-i characteristic of electric arc furnace load","volume":"23","author":"Seker","year":"2017","journal-title":"Elektron ir Elektrotechnika"},{"key":"10.7717\/peerj-cs.3505\/ref-35","article-title":"Investigation of characteristics of electric arc furnace operation","volume-title":"2016 National Conference on Electrical, Electronics and Biomedical Engineering (ELECO)","author":"Seker","year":"2017"},{"issue":"6","key":"10.7717\/peerj-cs.3505\/ref-36","doi-asserted-by":"publisher","first-page":"25","DOI":"10.5755\/j01.eie.23.6.19691","article-title":"Power quality measurement and analysis in electric arc furnace for Turkish electricity transmission system","volume":"23","author":"Seker","year":"2017","journal-title":"Elektron. ir Elektrotechnika"},{"issue":"November","key":"10.7717\/peerj-cs.3505\/ref-37","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1109\/icpst.2004.1460084","article-title":"Voltage flicker analysis and mitigation-case study in ac electric arc furnace using PSCAD\/EMTDC","volume":"1","author":"Sharmeela","year":"2004","journal-title":"2004 International Conference on Power System Technology, 2004. PowerCon 2004"},{"key":"10.7717\/peerj-cs.3505\/ref-38","first-page":"1","article-title":"A synthetic test circuit for current switching tests of HVDC circuit breakers","author":"Sheng","year":"2008"},{"key":"10.7717\/peerj-cs.3505\/ref-39","first-page":"1","article-title":"Enhancement in power quality using dynamic voltage restorer (DVR) in distribution network","author":"Singh","year":"2017"},{"issue":"25","key":"10.7717\/peerj-cs.3505\/ref-40","doi-asserted-by":"publisher","first-page":"4610","DOI":"10.1080\/10916466.2023.2223623","article-title":"Tabnet efficiency for facies classification and feature embedding learning from well log data","volume":"42","author":"Ta","year":"2023","journal-title":"Petroleum Science and Technology"},{"issue":"8","key":"10.7717\/peerj-cs.3505\/ref-41","doi-asserted-by":"publisher","first-page":"54","DOI":"10.15587\/1729-4061.2020.219439","article-title":"Using the constant current\u2012constant voltage converters to effectively reduce voltage fluctuations in the power supply systems for electric arc furnaces","volume":"6","author":"Turkovskyi","year":"2020","journal-title":"Eastern-European Journal of Enterprise Technologies"},{"key":"10.7717\/peerj-cs.3505\/ref-42","doi-asserted-by":"publisher","DOI":"10.1080\/15325008.2023.2295357","article-title":"Deep learning based effective technique for smart grid contingency analysis using RNN with LSTM","author":"Udhaya Shankar","year":"2023","journal-title":"Electric Power Components and Systems"},{"issue":"10","key":"10.7717\/peerj-cs.3505\/ref-43","doi-asserted-by":"publisher","first-page":"1741","DOI":"10.1134\/S0005117918100016","article-title":"A suite of intelligent tools for early detection and prevention of blackouts in power interconnections","volume":"79","author":"Voropai","year":"2018","journal-title":"Automation and Remote Control"},{"key":"10.7717\/peerj-cs.3505\/ref-44","first-page":"309","article-title":"Power grid fault diagnosis and prediction based on deep learning","author":"Wu","year":"2023"},{"key":"10.7717\/peerj-cs.3505\/ref-45","first-page":"1","article-title":"Multi-channel convolutional neural network with long short-term memory for power grid safety monitoring","author":"Xu","year":"2024"},{"key":"10.7717\/peerj-cs.3505\/ref-46","doi-asserted-by":"crossref","DOI":"10.1109\/CIYCEE55749.2022.9958980","article-title":"Modeling of electric arc furnace for power quality analysis","author":"Xu","year":"2022"},{"key":"10.7717\/peerj-cs.3505\/ref-47","doi-asserted-by":"publisher","first-page":"116781","DOI":"10.1016\/j.measurement.2025.116781","article-title":"Explainable deep learning method for power system stability evaluation with incomplete voltage data based on transfer learning","volume":"247","author":"Yang","year":"2025","journal-title":"Measurement"},{"key":"10.7717\/peerj-cs.3505\/ref-48","first-page":"6","article-title":"A novel preventive control approach for mitigating voltage collapse","author":"Zhao","year":"2006"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3505.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3505.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3505.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3505.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T08:43:25Z","timestamp":1768985005000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,21]]},"references-count":48,"alternative-id":["10.7717\/peerj-cs.3505"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3505","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,21]]},"article-number":"e3505"}}