Intelligent estimation of critical current degradation in HTS tapes under repetitive overcurrent cycling for cryo-electric transportation applications

Sadeghi, Alireza; Alipour Bonab, Shahin; Song, Wenjuan; Yazdani-Asrami, Mohammad

doi:10.1016/j.mtphys.2024.101365

Cited by 7 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Decision Tree (DT) is a type of supervised learning model that can be used for both classification and regression tasks. This approach is based on a binary tree structure where nodes are split to form the decision tree [32]. The algorithm of the decision tree involves dividing the dataset into smaller segments or classes and presenting the outcome in a leaf node [33].…”

Section: Decision Tree Regression (Dtr)mentioning

confidence: 99%

A comprehensive machine learning-based investigation for the index-value prediction of 2G HTS coated conductor tapes

Bonab,

Russo,

Morandi

et al. 2024

Mach. Learn.: Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Index-value, or so-called n-value prediction is of paramount importance for understanding the superconductors’ behaviour specially when modelling of superconductors is needed. This parameter is dependent on several physical quantities including temperature, the magnetic field’s density and orientation, and affects the behaviour of HTS devices made out of coated conductors in terms of losses and quench propagation. In this paper, a comprehensive analysis of many machine learning methods for estimating the n-value has been carried out. The results demonstrated that Cascade Forward Neural Network (CFNN) excels in this scope. Despite needing considerably higher training time when compared to the other attempted models, it performs at the highest accuracy, with 0.48 Root Mean Squared Error (RMSE) and 99.72% Pearson coefficient for goodness of fit (R-squared). On the other hand, the Rigid Regression method had the worst predictions with 4.92 RMSE and 37.29% R-squared. Also, Random Forest, boosting methods, and simple Feed Forward Neural Network can be considered as a middle accuracy model with faster training time than CFNN. The findings of this study not only advance modelling of superconductors but also pave the way for applications and further research on machine learning plug-and-play codes for superconducting studies including modelling of superconducting devices.

show abstract

Section: Decision Tree Regression (Dtr)mentioning

confidence: 99%

A comprehensive machine learning-based investigation for the index-value prediction of 2G HTS coated conductor tapes

Bonab,

Russo,

Morandi

et al. 2024

Mach. Learn.: Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In equation (1), i ∈ N and from 1 to P, term ||w|| 2 2 is known as the regularization factor, C is a constant for controlling the smoothness of model, v is a coefficient from 0 to 1 that controls the number of support vectors, ϵ is loss function, P is the total number of datapoints of the dataset that was used for training of the model, ζ i , ζ * i are non-negative slack parameters, and f (x i ) and s i are predicted and actual value of x i , respectively [37].…”

Section: Svrmentioning

confidence: 99%

Estimation of magnetic levitation and lateral forces in MgB₂ superconducting bulks with various dimensional sizes using artificial intelligence techniques

Alipour Bonab,

Xing,

Russo

et al. 2024

Supercond. Sci. Technol.

View full text Add to dashboard Cite

The advent of superconducting bulks, because of their compactness and performance, offers new perspectives and opportunities in many applications and sectors, such as magnetic field shielding, motors/generators, NMR/MRI, magnetic bearings, flywheel energy storage, Maglev trains, among others. The investigation and characterization of bulks typically relies on time-consuming and expensive experimental campaigns; hence the development of effective surrogate models would considerably speed up the research progress around them. In this study, we have first produced an experimental dataset with the levitation and lateral forces between different MgB2 bulks and one permanent magnet under different operating conditions. Next, we have exploited the dataset to develop surrogate models based on Artificial Intelligence (AI) techniques, namely Extremely Gradient Boosting (XGBoost), Support Vector Machine Regressor (SVR), and Kernel Ridge Regression (KRR). After the tuning of the hyperparameters of the AI models, the results demonstrated that SVR is the superior technique and can predict levitation and lateral forces with a worst-case accuracy scenario 99.86% in terms of goodness of fit to experimental data. Moreover, the response time of these models for prediction of new datapoints is ultra-fast.

show abstract

Artificial intelligence-based model to predict the heat transfer coefficient in flow boiling of liquid hydrogen as fuel and cryogenic coolant in future hydrogen-powered cryo-electric aviation

Alipour Bonab,

Yazdani-Asrami

2025

Fuel

View full text Add to dashboard Cite

Intelligent estimation of critical current degradation in HTS tapes under repetitive overcurrent cycling for cryo-electric transportation applications

Cited by 7 publications

References 42 publications

A comprehensive machine learning-based investigation for the index-value prediction of 2G HTS coated conductor tapes

A comprehensive machine learning-based investigation for the index-value prediction of 2G HTS coated conductor tapes

Estimation of magnetic levitation and lateral forces in MgB₂ superconducting bulks with various dimensional sizes using artificial intelligence techniques

Artificial intelligence-based model to predict the heat transfer coefficient in flow boiling of liquid hydrogen as fuel and cryogenic coolant in future hydrogen-powered cryo-electric aviation

Contact Info

Product

Resources

About

Intelligent estimation of critical current degradation in HTS tapes under repetitive overcurrent cycling for cryo-electric transportation applications

Cited by 7 publications

References 42 publications

A comprehensive machine learning-based investigation for the index-value prediction of 2G HTS coated conductor tapes

A comprehensive machine learning-based investigation for the index-value prediction of 2G HTS coated conductor tapes

Estimation of magnetic levitation and lateral forces in MgB2 superconducting bulks with various dimensional sizes using artificial intelligence techniques

Artificial intelligence-based model to predict the heat transfer coefficient in flow boiling of liquid hydrogen as fuel and cryogenic coolant in future hydrogen-powered cryo-electric aviation

Contact Info

Product

Resources

About

Estimation of magnetic levitation and lateral forces in MgB₂ superconducting bulks with various dimensional sizes using artificial intelligence techniques