Scholarlink

<p>The impact of heat generation and Soret–Dufour effects on bioconvection stagnation point flow of MHD Boger nanofluid around a spinning sphere in the occurrence of gyrotactic microbes is examined. This paper presents a numerical solution of this impact using back-propagation intelligent Bayesian regularization with the neural network domain (BPIBR-NNs), which is novel with convergent stability. Using a dataset for the proposed (BPIBR-NNs) for many MHD-BNF-TRDS scenarios, the Bvp4c numerical technique. This model may be useful for a variety of systems, including bacterial-powered micromixers, chip-scale micro-devices like bio-microsystems, microbial fuel cells, enzyme-based biosensors, and micro-scale environments like microfluidic devices. Gyrotactic microbes added to nanoparticles increase their thermal efficiency. Reactors and spinning machines need to be built and adjusted for industrial processes to work because reliable mixing and effective heat transmission are essential. This model may be used by environmental engineers to forecast the distribution of nutrients and contaminants in water bodies. To assess the accuracy of the proposed model, the data are processed, correctly tabulated, and its validity is examined. The BPIBR-NNs training, testing, and validation methods were used to evaluate the estimate solutions for specific occurrences and compare the suggested model for verification.</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

Machine learning analysis based on Bayesian regularization algorithm for the thermal bioconvection flow of Boger nanofluid in the presence of gyrotactic microbes: enzyme-based biosensor applications

  • 期刊论文

  • 发表日期：

    2025年11月7日

查看全文
  • Shaaban M. Shaaban,
  • Ahmed Babeker Elhag,
  • Ines Hilali Jaghdam,
  • Mamurakhon Toshpulatova,
  • Munawar Abbas,
  • Ibrahim Mahariq,
  • Mustafa Bayram,
  • Mohammad Saqlain Sajjad

摘要

The impact of heat generation and Soret–Dufour effects on bioconvection stagnation point flow of MHD Boger nanofluid around a spinning sphere in the occurrence of gyrotactic microbes is examined. This paper presents a numerical solution of this impact using back-propagation intelligent Bayesian regularization with the neural network domain (BPIBR-NNs), which is novel with convergent stability. Using a dataset for the proposed (BPIBR-NNs) for many MHD-BNF-TRDS scenarios, the Bvp4c numerical technique. This model may be useful for a variety of systems, including bacterial-powered micromixers, chip-scale micro-devices like bio-microsystems, microbial fuel cells, enzyme-based biosensors, and micro-scale environments like microfluidic devices. Gyrotactic microbes added to nanoparticles increase their thermal efficiency. Reactors and spinning machines need to be built and adjusted for industrial processes to work because reliable mixing and effective heat transmission are essential. This model may be used by environmental engineers to forecast the distribution of nutrients and contaminants in water bodies. To assess the accuracy of the proposed model, the data are processed, correctly tabulated, and its validity is examined. The BPIBR-NNs training, testing, and validation methods were used to evaluate the estimate solutions for specific occurrences and compare the suggested model for verification.