Scholarlink

<p>Optimizing heat convection&#xa0;in water heaters is crucial due to their industrial use. This research combines experiments and machine learning to enhance convection heat transfer using ultrasonic waves in a spiral heater within a cylindrical tank. Various parameters affect ultrasonic enhancement, including ultrasonic power (U.P.), transducers’ geometric configuration, heat source height (H.h.), and heater power (H.P.). Based on our experimental data, we obtained a correlation using ordinary least squares (OLS) and developed an averaging ensemble (AE) of classic machine learning (CML) models and a convolutional neural network (CNN) model. We aim to predict the temperature difference between the&#xa0;heater and the&#xa0;water bulk. The CNN model (<i>R</i><sup>2</sup> = 0.91) performed similarly to the AE of CML models (<i>R</i><sup>2</sup> = 0.90) and outperformed OLS (<i>R</i><sup>2</sup> = 0.8). Further, the applicability and sensitivity analyses revealed data validity (&gt; 97%) and the&#xa0;most important parameters, respectively. Finally, we employ machine learning-based optimization. The optimal configuration, determined by the&#xa0;simplicial homology global optimizer, is 4 transducers at the corners of a square (configuration ID 1) with U.P. = 210 W, H.P. = 1000 W, and H.h. = 60&#xa0;mm, resulting in Q/∆T = 36.9 with a 1.11% error compared to experimental results.</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

Experimental and machine learning optimization of ultrasonic-enhanced heat convection in a spiral heater

  • 期刊论文

  • 发表日期：

    2025年4月28日

查看全文
  • Farzad Azizi Zade,
  • Razieh Abedini,
  • Amir Abdullah,
  • Mohammad Passandideh-Fard

摘要

Optimizing heat convection in water heaters is crucial due to their industrial use. This research combines experiments and machine learning to enhance convection heat transfer using ultrasonic waves in a spiral heater within a cylindrical tank. Various parameters affect ultrasonic enhancement, including ultrasonic power (U.P.), transducers’ geometric configuration, heat source height (H.h.), and heater power (H.P.). Based on our experimental data, we obtained a correlation using ordinary least squares (OLS) and developed an averaging ensemble (AE) of classic machine learning (CML) models and a convolutional neural network (CNN) model. We aim to predict the temperature difference between the heater and the water bulk. The CNN model (R2 = 0.91) performed similarly to the AE of CML models (R2 = 0.90) and outperformed OLS (R2 = 0.8). Further, the applicability and sensitivity analyses revealed data validity (> 97%) and the most important parameters, respectively. Finally, we employ machine learning-based optimization. The optimal configuration, determined by the simplicial homology global optimizer, is 4 transducers at the corners of a square (configuration ID 1) with U.P. = 210 W, H.P. = 1000 W, and H.h. = 60 mm, resulting in Q/∆T = 36.9 with a 1.11% error compared to experimental results.