Scholarlink

<p>The thermal performance of nanofluids in combination with coolants as working fluid is investigated in this research. The thermohydraulic parameters of the working fluids under research are analyzed using the collected data by the residual attention convolutional neural network (RACNN) module. The consequences of nanoparticles at a concentration of 0.01 mass% in the base fluid enhance the thermal energy of the heat exchangers are reflected in the results. The nanoparticles upgraded the thermal conductivity and convective heat transfer coefficients, thereby increasing overall thermal energy movement effectiveness in the heat exchanger, even at higher superficial velocities. The practical application of the fluids is conveyed by the performance index value of the fluids which is greater than 1. The validations of the module are relatively assessed against the primary network to highlight the prediction accuracy of the attention module. The research introduced an advanced particle swarm optimization combined with a support vector processor (PSO-SVP), to enhance the accuracy of the module in identifying the flow pattern of the heat exchanger. The outputs for annular, bubbly, churn, and slug flows in the heat exchanger are identified and explored. Moreover, the controlled formation of pores, throats, and the uniform distribution of nanoparticles are also examined. Overall, the findings suggest that incorporating nanoparticles significantly enhances the thermal efficiency of the exchangers, making them a viable choice for utilization in industrial settings.</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

Optimizing small-sized heat exchangers using Mahindra first choice-based nanofluids and deep learning-driven thermal prediction with multi-objective optimization

  • 期刊论文

  • 发表日期：

    2025年12月17日

查看全文
  • S. Bhaskar,
  • B. Nageswara Rao

摘要

The thermal performance of nanofluids in combination with coolants as working fluid is investigated in this research. The thermohydraulic parameters of the working fluids under research are analyzed using the collected data by the residual attention convolutional neural network (RACNN) module. The consequences of nanoparticles at a concentration of 0.01 mass% in the base fluid enhance the thermal energy of the heat exchangers are reflected in the results. The nanoparticles upgraded the thermal conductivity and convective heat transfer coefficients, thereby increasing overall thermal energy movement effectiveness in the heat exchanger, even at higher superficial velocities. The practical application of the fluids is conveyed by the performance index value of the fluids which is greater than 1. The validations of the module are relatively assessed against the primary network to highlight the prediction accuracy of the attention module. The research introduced an advanced particle swarm optimization combined with a support vector processor (PSO-SVP), to enhance the accuracy of the module in identifying the flow pattern of the heat exchanger. The outputs for annular, bubbly, churn, and slug flows in the heat exchanger are identified and explored. Moreover, the controlled formation of pores, throats, and the uniform distribution of nanoparticles are also examined. Overall, the findings suggest that incorporating nanoparticles significantly enhances the thermal efficiency of the exchangers, making them a viable choice for utilization in industrial settings.