Scholarlink

<p>Trigeneration system generates electricity, cooling, and heating from a single energy source of the system. It supports the advancement of various applications such as hospitals and industrial facilities. The challenges such as low efficiency due to the large sorbent beds, limited heat transfer, and longer cycle times. To address these challenges, optimized Micro-Combined Cooling, Heating, and Power system is intended to provide sustainable energy, cost savings, and waste minimization to support a green environment. Aquila optimization algorithm is used to optimize the sizes of the chilled water storage system of lithium bromide absorption, which initially minimizes the chilled water temperature of 277&#xa0;K with cooling capacities of 20&#xa0;kW and the energy efficiency of about 82%. Using the deep belief neural network (DBNN) model to predict the key performances of the Micro-Combined Cooling, Heating, and Power based on the input variables like exhaust gas temperature, evaporation outlet temperature, absorption chiller temperature, generator output power, and inlet fluid pressure. By improving the energy efficiency, the system minimizes the need for additional energy and reduces carbon emissions. The model shows an accuracy is 95.2%, 96.2% F1-score, 94.2% specificity, and 95.67% recall. Furthermore, as fuel prices rise, parametric findings such as net present values and payback period tend to rise and usually fall. Overall, the study highlights that the optimized system is cost-effective, energy-efficient, and eco-friendly, making it ideal for applications like hospitals, where reliable and sustainable energy management is essential. In the future, we could focus on integrating renewable energy sources such as solar or biomass to further reduce fossil fuel dependence and carbon emissions.</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

Cooling capacity and energy efficiency enhancement in hospital trigeneration systems using aquila optimization and deep learning

  • 期刊论文

  • 发表日期：

    2025年12月8日

查看全文
  • Sunil Dhondiram Bagade,
  • Prasad B. Rampure

摘要

Trigeneration system generates electricity, cooling, and heating from a single energy source of the system. It supports the advancement of various applications such as hospitals and industrial facilities. The challenges such as low efficiency due to the large sorbent beds, limited heat transfer, and longer cycle times. To address these challenges, optimized Micro-Combined Cooling, Heating, and Power system is intended to provide sustainable energy, cost savings, and waste minimization to support a green environment. Aquila optimization algorithm is used to optimize the sizes of the chilled water storage system of lithium bromide absorption, which initially minimizes the chilled water temperature of 277 K with cooling capacities of 20 kW and the energy efficiency of about 82%. Using the deep belief neural network (DBNN) model to predict the key performances of the Micro-Combined Cooling, Heating, and Power based on the input variables like exhaust gas temperature, evaporation outlet temperature, absorption chiller temperature, generator output power, and inlet fluid pressure. By improving the energy efficiency, the system minimizes the need for additional energy and reduces carbon emissions. The model shows an accuracy is 95.2%, 96.2% F1-score, 94.2% specificity, and 95.67% recall. Furthermore, as fuel prices rise, parametric findings such as net present values and payback period tend to rise and usually fall. Overall, the study highlights that the optimized system is cost-effective, energy-efficient, and eco-friendly, making it ideal for applications like hospitals, where reliable and sustainable energy management is essential. In the future, we could focus on integrating renewable energy sources such as solar or biomass to further reduce fossil fuel dependence and carbon emissions.