移动式余热回收节能系统建模及应用

基于粒子群优化算法,提出了通过优化支持向量机移动式蓄能控制参数,建立了移动式余热回收蓄热温度质量模型,针对供应链客户端对余热温度需求不同,进行了热能温度分类问题的仿真实验。利用支持向量机算法所获得的实验数据,使用粒子群搜索优化算法分析了蓄能参数对回收余热能质量的影响,仿真实验结果表明,基于粒子群优化检索算法的支持向量机在对余热回收蓄能温度分类问题上,其热能质量损耗受蓄能参数影响是稳健的;基于粒子群优化算法的支持向量机在移动式余热供应链上的使用,能够提高余热回收蓄热温度质量分类效果和准确度。在移动式余热回收供应链过程中,从供应链前端即工业产品生产的终端排放尾热开始,对回收热能的收热时间、终端配送商的收热时间,以及整个过程中热能流量、流速等蓄热参数进行控制,移动式蓄热温度在余热回收供应链各个节点的变化是稳健的,也验证了基于粒子群优化算法的支持向量机余热回收温度分类在数据分类中的可行性。

Based on the Algorithm of Particle Swarm Optimization, this paper proposes that according to optimize the support vector machine mobile energy storage control parameters, establishing a mobile of waste heat recovery and heat storage temperature quality. Aiming at the different residual heat temperature requirements of the supply chain customers, the simulation experiment on the thermal energy temperature classification problem was carried out. Based on the experimental data , paper analyzes the influence of energy storage parameters on the quality of recovered waste heat energy. The results show that the support vector machine based on particle swarm optimization retrieval algorithm has a strong influence on the energy storage parameters of the waste heat recovery storage temperature classification problem. It can improve the classification effect and accuracy of waste heat recovery and heat storage temperature. In the mobile waste heat recovery supply chain, the heat storage time, heat recovery time, heat energy flow rate, flow rate and other heat storage parameters in the process of recovering heat energy are controlled, and the loss of thermal energy quality is stable under different recovery waste heat temperatures. At the same time, the feasibility of the support vector machine residual heat recovery temperature classification based on particle swarm optimization algorithm in data classification is also verified.