Scholarlink

<p>Refrigerators rank high among the most fundamental machines to keep food fresh by offering a dependable mode of food safety and uniformity. Significant electricity consumers in the household consume large quantities of electrical power in contemporary households. Thus, improving the energy efficiency of refrigeration systems has become more important in meeting sustainable energy objectives. Despite its potential, previous research on integrating Phase Change Material (PCM) in refrigeration systems has faced notable challenges of uneven thermal performance with low-to-no energy savings, and inadequate selection leads to very low thermal conductivity. Integrating PCM with a thermo-electric generator greatly contributes to energy effectiveness because of energy recoverability, which limits the system complexity and energy cost. The optimization of the conventional PCM-based refrigeration system with a deep learning model provides an enhanced thermal performance coefficient by dynamic control operations. This research uniquely integrates PCM and TEG with an Affinity Attention Graph Neural Network-based Quasi-Oppositional Adaptive Whale Optimization (AAGNN-QAWO) controller, marking a novel contribution to the field. The outcomes show that the optimized model reduces power consumption by 8%, enhances the coefficient of performance (CoP) by 30%, reduces PCM melting time by 65%, and stabilizes temperature fluctuations within ± 10 °C, compared to conventional refrigeration systems. The proposed research contributes greatly to cost reduction and improved environmental sustainability.</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

Optimization of vapor compression refrigeration systems using phase change material and thermoelectric generator

  • 期刊论文

  • 发表日期：

    2025年10月10日

查看全文
  • Vallapureddy Siva Nagi Reddy,
  • Lakshmi Naga Vishnu Venkata Swamy,
  • Addanki Naveen Kumar,
  • Cheekatla Sri Lakshman,
  • Mudili Saikiran,
  • Pasupuleti Subrahmanyam Sai Data Swamy,
  • Abdul Arif

摘要

Refrigerators rank high among the most fundamental machines to keep food fresh by offering a dependable mode of food safety and uniformity. Significant electricity consumers in the household consume large quantities of electrical power in contemporary households. Thus, improving the energy efficiency of refrigeration systems has become more important in meeting sustainable energy objectives. Despite its potential, previous research on integrating Phase Change Material (PCM) in refrigeration systems has faced notable challenges of uneven thermal performance with low-to-no energy savings, and inadequate selection leads to very low thermal conductivity. Integrating PCM with a thermo-electric generator greatly contributes to energy effectiveness because of energy recoverability, which limits the system complexity and energy cost. The optimization of the conventional PCM-based refrigeration system with a deep learning model provides an enhanced thermal performance coefficient by dynamic control operations. This research uniquely integrates PCM and TEG with an Affinity Attention Graph Neural Network-based Quasi-Oppositional Adaptive Whale Optimization (AAGNN-QAWO) controller, marking a novel contribution to the field. The outcomes show that the optimized model reduces power consumption by 8%, enhances the coefficient of performance (CoP) by 30%, reduces PCM melting time by 65%, and stabilizes temperature fluctuations within ± 10 °C, compared to conventional refrigeration systems. The proposed research contributes greatly to cost reduction and improved environmental sustainability.