Scholarlink

Purpose <p>Hybrid polymers and hybrid metal nanoparticles have gained attention due to their enhanced properties compared to their individual components. However, Polymer Metal Nanocomposites (PMNC) fabrication with precise control over nanoparticle dispersion and interfacial interactions remains a challenge. This study aims to address these challenges by presenting a hybrid co-precipitation and in situ polymerization (HCISP) fabrication method for synthesizing PMNCs.</p> Methods <p>The PMNCs were fabricated by combining a hybrid polymer matrix consisting of Polyether Ether Ketone (PEEK) with Polyhedral OligomericSilsesquioxane (POSS) and Graphene Oxide (GO), along with a hybrid composition of aluminium and copper nanoparticles. The fabricated nanoresonators were subjected to vibration and acoustic chamber testing. Design of Experiments and a hybrid Deep Neural Network with Cuckoo Search Algorithm (DNN-CSA) was used to validate and prediction of experimentation.</p> Results <p>The Analysis of Variance (ANOVA) for both vibration and acoustic chamber testing results confirms the significance of models. The hybrid DNN-CSA model shows better performances than the Response Surface Method (RSM), hybrid Random Forest based Artificial Bee Colony Algorithm (RF-ABC), and hybrid Deep Neural Network based Genetic Algorithms (DNN-GA) models in terms of prediction accuracy.</p> Conclusion <p>This study presents a hybrid polymer matrix that exhibits enhanced acoustic properties. Hybrid metal nanoparticles are incorporated into the polymer matrix to improve thermal conductivity and overall performance. The hybrid HCISP method is used for efficient synthesis, while SLS enables the fabrication of nanoresonator structures. Physical testing using RSM evaluates the thermo-elastic behavior of PMNC, and DNN combined with CSA improves prediction accuracy and optimization performance.</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

Thermo-Elastic Vibration Analysis of Acoustic Liners Using Polymer-Metal Nanocomposites: Prediction and Optimization of Hybrid Deep Neural Network and Cuckoo Search Algorithm

  • 期刊论文

  • 发表日期：

    2025年1月9日

查看全文
  • T. J. Prasannakumar,
  • K. Sivajibabu,
  • B. Durgaprasad

摘要

Purpose

Hybrid polymers and hybrid metal nanoparticles have gained attention due to their enhanced properties compared to their individual components. However, Polymer Metal Nanocomposites (PMNC) fabrication with precise control over nanoparticle dispersion and interfacial interactions remains a challenge. This study aims to address these challenges by presenting a hybrid co-precipitation and in situ polymerization (HCISP) fabrication method for synthesizing PMNCs.

Methods

The PMNCs were fabricated by combining a hybrid polymer matrix consisting of Polyether Ether Ketone (PEEK) with Polyhedral OligomericSilsesquioxane (POSS) and Graphene Oxide (GO), along with a hybrid composition of aluminium and copper nanoparticles. The fabricated nanoresonators were subjected to vibration and acoustic chamber testing. Design of Experiments and a hybrid Deep Neural Network with Cuckoo Search Algorithm (DNN-CSA) was used to validate and prediction of experimentation.

Results

The Analysis of Variance (ANOVA) for both vibration and acoustic chamber testing results confirms the significance of models. The hybrid DNN-CSA model shows better performances than the Response Surface Method (RSM), hybrid Random Forest based Artificial Bee Colony Algorithm (RF-ABC), and hybrid Deep Neural Network based Genetic Algorithms (DNN-GA) models in terms of prediction accuracy.

Conclusion

This study presents a hybrid polymer matrix that exhibits enhanced acoustic properties. Hybrid metal nanoparticles are incorporated into the polymer matrix to improve thermal conductivity and overall performance. The hybrid HCISP method is used for efficient synthesis, while SLS enables the fabrication of nanoresonator structures. Physical testing using RSM evaluates the thermo-elastic behavior of PMNC, and DNN combined with CSA improves prediction accuracy and optimization performance.