Scholarlink

<p>The ability of nanofluids to carry nutrients and promote cellular connections makes them valuable for tissue engineering, pharmacokinetics, and stability enhancement in biomedical engineering. Energy transfer devices, cooling systems, and medication administration systems all benefit from their use. Additionally, they accelerate heat transfer. They also speed up the transfer of heat in manufacturing, polymer processing, and drug delivery, among other operations. Using the Levenberg–Marquardt scheme (LMS) algorithm, the work offers an AI-based approach to understanding stretching sheet behavior. Appropriate conversions are used to convert governing flow PDEs into ODEs. Scenarios 1–7 are given an initial reference solution created with MATLAB function ‘bvp4c’. Eighty percent is used for training, ten percent is for validation, and ten percent is for testing. Responses are estimated using LMS-BPNN in each of these scenarios. The effectiveness and reliability of the method are evaluated using regression analysis, correlation index, and error-based fitness curves. The study also examines flow performance indicators using LMS-BPNN to gain insights. The reliability and consistency of the proposed AI-driven technique are shown through error analysis.</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

Gyrotactic microorganisms in the pharmacokinetics of electrically conducted nanofluid over a stretching sheet: complex algorithmic models

  • 期刊论文

  • 发表日期：

    2025年4月28日

查看全文
  • Arslan Bin Amjad,
  • Rahma Sellami,
  • Muhammad Imran Khan,
  • Ahmad Zeeshan,
  • Nouman Ijaz,
  • Azzam Hazim

摘要

The ability of nanofluids to carry nutrients and promote cellular connections makes them valuable for tissue engineering, pharmacokinetics, and stability enhancement in biomedical engineering. Energy transfer devices, cooling systems, and medication administration systems all benefit from their use. Additionally, they accelerate heat transfer. They also speed up the transfer of heat in manufacturing, polymer processing, and drug delivery, among other operations. Using the Levenberg–Marquardt scheme (LMS) algorithm, the work offers an AI-based approach to understanding stretching sheet behavior. Appropriate conversions are used to convert governing flow PDEs into ODEs. Scenarios 1–7 are given an initial reference solution created with MATLAB function ‘bvp4c’. Eighty percent is used for training, ten percent is for validation, and ten percent is for testing. Responses are estimated using LMS-BPNN in each of these scenarios. The effectiveness and reliability of the method are evaluated using regression analysis, correlation index, and error-based fitness curves. The study also examines flow performance indicators using LMS-BPNN to gain insights. The reliability and consistency of the proposed AI-driven technique are shown through error analysis.