Nipeng Wang, Wenhai Zhou, Rui Liang, Rongli Jia, Bingxu Su, Tingliang Chen, Leiwen Yue, Jiafeng Cao
{"title":"Prediction and Application of Critical Current in 2G HTS Conductors Based on GA-BP Algorithm","authors":"Nipeng Wang, Wenhai Zhou, Rui Liang, Rongli Jia, Bingxu Su, Tingliang Chen, Leiwen Yue, Jiafeng Cao","doi":"10.1007/s10948-025-06975-y","DOIUrl":null,"url":null,"abstract":"<div><p>Critical current, as a key parameter distinguishing superconductors from ordinary conductors, determines the stability of superconducting devices and systems during operation. To accurately assess the critical performance of superconductors, a genetic algorithm (GA)–optimized back-propagation (BP) neural network model is introduced and used in this paper to predict the critical currents of second-generation high-temperature superconductors (2G HTS). Firstly, a staged optimization is carried out for the neural network structure and hyper-parameters, and the GA-BP model is established by constructing different fitness functions. Next, the prediction accuracy and generalization ability of the GA-BP model are validated by comparing the relative errors between the predicted values from two models in the 180° to 240° anti-angle region. Eventually, the critical current at a specific temperature is predicted by the GA-BP model, and the corresponding <i>J</i><sub><i>c</i>0</sub> is calculated for the finite element calculation of superconducting strips. The calculation results show that the relative error between the maximum current density obtained based on the predicted <i>J</i><sub><i>c</i>0</sub> and the experimental <i>J</i><sub><i>c</i>0</sub> is only 0.907%, indicating that the model can be used to accurately determine the operating state of the superconducting equipment.</p></div>","PeriodicalId":669,"journal":{"name":"Journal of Superconductivity and Novel Magnetism","volume":"38 3","pages":""},"PeriodicalIF":1.6000,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Superconductivity and Novel Magnetism","FirstCategoryId":"101","ListUrlMain":"https://link.springer.com/article/10.1007/s10948-025-06975-y","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"PHYSICS, APPLIED","Score":null,"Total":0}
引用次数: 0
Abstract
Critical current, as a key parameter distinguishing superconductors from ordinary conductors, determines the stability of superconducting devices and systems during operation. To accurately assess the critical performance of superconductors, a genetic algorithm (GA)–optimized back-propagation (BP) neural network model is introduced and used in this paper to predict the critical currents of second-generation high-temperature superconductors (2G HTS). Firstly, a staged optimization is carried out for the neural network structure and hyper-parameters, and the GA-BP model is established by constructing different fitness functions. Next, the prediction accuracy and generalization ability of the GA-BP model are validated by comparing the relative errors between the predicted values from two models in the 180° to 240° anti-angle region. Eventually, the critical current at a specific temperature is predicted by the GA-BP model, and the corresponding Jc0 is calculated for the finite element calculation of superconducting strips. The calculation results show that the relative error between the maximum current density obtained based on the predicted Jc0 and the experimental Jc0 is only 0.907%, indicating that the model can be used to accurately determine the operating state of the superconducting equipment.
期刊介绍:
The Journal of Superconductivity and Novel Magnetism serves as the international forum for the most current research and ideas in these fields. This highly acclaimed journal publishes peer-reviewed original papers, conference proceedings and invited review articles that examine all aspects of the science and technology of superconductivity, including new materials, new mechanisms, basic and technological properties, new phenomena, and small- and large-scale applications. Novel magnetism, which is expanding rapidly, is also featured in the journal. The journal focuses on such areas as spintronics, magnetic semiconductors, properties of magnetic multilayers, magnetoresistive materials and structures, magnetic oxides, etc. Novel superconducting and magnetic materials are complex compounds, and the journal publishes articles related to all aspects their study, such as sample preparation, spectroscopy and transport properties as well as various applications.