Scholarlink

<p>An eXtreme Gradient Boosting (XGBoost) machine learning model was developed to predict the electrocaloric temperature change (Δ<i>T</i><sub>EC</sub>) of PMN-PT electroceramics based on processing parameters (PMN/PT ratio, sample type, calcination and sintering time/temperature) and measurement conditions (direct/indirect measurement, electric field, and measurement temperature). A dataset of 2863 data points was compiled from the experimental literature, and the model achieved a coefficient of determination (<i>R</i><sup>2</sup>) of 0.97 and a mean absolute error (MAE) of 0.04&#xa0;°C on the test set, demonstrating strong predictive performance. Feature importance analysis revealed that electric field and T-T<sub>C</sub> are the primary drivers of electrocaloric response, while processing conditions also significantly influence Δ<i>T</i><sub>EC</sub>. A Bayesian Optimization framework was employed to systematically identify the optimal processing parameters for maximizing Δ<i>T</i><sub>EC</sub>. Under experimentally realistic conditions (24&#xa0;°C measurement temperature, 40&#xa0;kV/cm electric field), the optimal PMN/PT composition (81.06%/18.94%) and processing parameters (calcination at 810&#xa0;°C for 3&#xa0;h, sintering at 1280&#xa0;°C for 7&#xa0;h) were identified, yielding a predicted Δ<i>T</i><sub>EC</sub> of 1.40&#xa0;°C, which exceeds most experimentally reported values under similar conditions. Additionally, a virtual dataset of 100.000 synthetic data points was generated and analyzed to explore high-performance regions within the electrocaloric design space. The results highlight the potential of machine learning in materials science, offering a scalable and data-driven approach to accelerate the discovery and optimization of advanced electrocaloric materials.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Electrocaloric property optimization of PMN-PT ceramics using predictive modeling

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月25日

查看全文
  • Mustafa Cagri Bayir,
  • Ebru Mensur

摘要

An eXtreme Gradient Boosting (XGBoost) machine learning model was developed to predict the electrocaloric temperature change (ΔTEC) of PMN-PT electroceramics based on processing parameters (PMN/PT ratio, sample type, calcination and sintering time/temperature) and measurement conditions (direct/indirect measurement, electric field, and measurement temperature). A dataset of 2863 data points was compiled from the experimental literature, and the model achieved a coefficient of determination (R2) of 0.97 and a mean absolute error (MAE) of 0.04 °C on the test set, demonstrating strong predictive performance. Feature importance analysis revealed that electric field and T-TC are the primary drivers of electrocaloric response, while processing conditions also significantly influence ΔTEC. A Bayesian Optimization framework was employed to systematically identify the optimal processing parameters for maximizing ΔTEC. Under experimentally realistic conditions (24 °C measurement temperature, 40 kV/cm electric field), the optimal PMN/PT composition (81.06%/18.94%) and processing parameters (calcination at 810 °C for 3 h, sintering at 1280 °C for 7 h) were identified, yielding a predicted ΔTEC of 1.40 °C, which exceeds most experimentally reported values under similar conditions. Additionally, a virtual dataset of 100.000 synthetic data points was generated and analyzed to explore high-performance regions within the electrocaloric design space. The results highlight the potential of machine learning in materials science, offering a scalable and data-driven approach to accelerate the discovery and optimization of advanced electrocaloric materials.