Scholarlink

<p>Radiators play an important role in automobiles as they directly affect the energy utilization and operational dependability. This paper presents an integrated experimental, response surface, and Machine Learning (ML) based techniques to investigate and predict the performance of a typical automobile radiator. Experimental data is collected by varying hot water flow rate (0.5–2.5&#xa0;l/min), cold air velocity (1–5&#xa0;m/s), and feeding temperature (50–60&#xa0;°C). The operating conditions were optimized using Response Surface Methodology (RSM), and the optimal radiator effectiveness was determined to be 73.2%. Furthermore, two ML modeling approaches, namely Gradient Boosting (GB) and Extreme Learning Machine (ELM), were employed to predict the radiator's performance. Among the three developed models by RSM and ML techniques, the GB model performed better than the RSM and ELM models, as indicated by its highest coefficient of determination (R<sup>2</sup>) of 0.967, Mean Absolute Error of 1.41, Mean Square Error of 7.526, and Mean Absolute Percentage Error of 3.32. The findings of this research highlight that hybrid optimization-modeling approaches are beneficial for heat exchanger applications and have significant implications for the design and operation of automobile radiators.</p> Graphical abstract <p></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 optimization and performance modeling of an automobile radiator via response surface methodology and machine learning frameworks

  • 期刊论文

  • 发表日期：

    2026年6月22日

查看全文
  • Faizan Ahmed,
  • Nayeemuddin Mohammed,
  • Hiren Mewada

摘要

Radiators play an important role in automobiles as they directly affect the energy utilization and operational dependability. This paper presents an integrated experimental, response surface, and Machine Learning (ML) based techniques to investigate and predict the performance of a typical automobile radiator. Experimental data is collected by varying hot water flow rate (0.5–2.5 l/min), cold air velocity (1–5 m/s), and feeding temperature (50–60 °C). The operating conditions were optimized using Response Surface Methodology (RSM), and the optimal radiator effectiveness was determined to be 73.2%. Furthermore, two ML modeling approaches, namely Gradient Boosting (GB) and Extreme Learning Machine (ELM), were employed to predict the radiator's performance. Among the three developed models by RSM and ML techniques, the GB model performed better than the RSM and ELM models, as indicated by its highest coefficient of determination (R2) of 0.967, Mean Absolute Error of 1.41, Mean Square Error of 7.526, and Mean Absolute Percentage Error of 3.32. The findings of this research highlight that hybrid optimization-modeling approaches are beneficial for heat exchanger applications and have significant implications for the design and operation of automobile radiators.

Graphical abstract