Optimization of the Synthesis of Superconducting YBCO Samples Using the Random Forest Algorithm and the Taguchi Method

Джураев, Д.Р., Тураев, А.А., Тураев, О.Г.

O‘zbekiston fizika jurnali · 2026-yil

Annotatsiya

This paper presents the results of a study on modeling and predicting the critical superconductingtemperature (Tc) of YBa2Cu3O7δ (YBCO) samples synthesized via the solid-state reactionmethod, using a multiparameter machine approach. The influence of synthesis parameters suchas calcination temperature and duration (Tcal, τ1, τ2), sintering temperature (Tsin), pressing pressure(P), and cooling time (τ3) was investigated. To model the complex, uncertain, and multifactorrelationships between synthesis conditions and Tc values, a Random Forest regressionmodel was employed. The Random Forest model achieved high accuracy: R2 = 0.993, MAE =0.0106 K, and RMSE = 0.0125 K, indicating excellent agreement between predicted and experimentalTc values. Feature importance analysis revealed that τ2 (sintering time) and Tsin (sinteringtemperature), τ3 (cooling time), and τ1 (calcination time) have the greatest impact on Tc.This hierarchy of importance was further confirmed using SHAP analysis (Shapley values).This study demonstrates the potential for effective development of high-performance superconductingmaterials through the integration of regression modeling and experimental design.

Maqola ma’lumotlari
MualliflarДжураев, Д.Р., Тураев, А.А., Тураев, О.Г.
JurnalO‘zbekiston fizika jurnali
Nashr sanasi2026-02-18
Jild27
Son4
TilRus
DOI10.52304/.v27i4.611

Kalit so‘zlar

YBCO, критическая температура, метод Тагучи, случайный лес, регрессионная модель, YBCO, critical temperature, Taguchi method, Random Forest regression model

Ilmiy soha

O‘zbekiston fizika jurnali jurnalidan boshqa maqolalar

O‘zbekiston fizika jurnali — barcha maqolalar