垃圾焚烧炉稳态运行燃烧参数的优化研究与应用  

Optimization Research and Application of Steady State Operation Combustion Parameters for Waste Incinerators

作　　者：容毅浜 刘效洲[2] 刘杰成 朱光羽 RONG Yibang;LIU Xiaozhou;LIU Jiecheng;ZHU Guangyu(Guangdong Guangye Investment Group Co.,Ltd.,Guangzhou,China,510006;School of Materials and Energy,Guangdong University of Technology,Guangzhou,China,510006)

机构地区：[1]广东广业投资集团有限公司,广东广州510006 [2]广东工业大学材料与能源学院,广东广州510006

出　　处：《热能动力工程》2025年第2期94-99,共6页Journal of Engineering for Thermal Energy and Power

摘　　要：现存的垃圾焚烧炉在运行过程中存在较大的不稳定性,关键运行数据呈现出滞后、强耦合及多扰动的特点,所以需要实时动态调节垃圾焚烧炉运行参数,以保障垃圾焚烧炉的稳定高效运行。本文采集垃圾焚烧炉的历史运行数据,采用多层LSTM神经网络,利用离线训练建立垃圾焚烧炉运行参数与热效率之间的高度非线性耦合数学模型,以垃圾焚烧炉热效率最大为目标,利用强化学习技术对垃圾焚烧炉的运行参数进行优化,并提供了具体的应用实例。优化结果表明:每吨垃圾最大蒸汽产量由原来的2.22 t上升到了2.5 t,垃圾焚烧炉的热效率提高了11.1%,优化效果明显。The existing waste incinerators have significant instability during operation,with the characteristics of hysteresis,strong coupling and multiple disturbances in key operating data.Therefore,the operating parameters of waste incinerators need to be dynamically adjusted in real time to ensure stable and efficient operation.This paper collects historical operating data of waste incinerator and uses multi-layer LSTM neural network to establish a highly nonlinear coupled mathematical model between the operating parameters and thermal efficiency of the waste incinerator through offline training.With the goal of maximizing the thermal efficiency of the waste incinerator,reinforcement learning technology is used to optimize the operating parameters of the waste incinerator,and the detailed application examples are provided.The optimization results show that the maximum steam production per ton of waste has increased from 2.22 to 2.5 tons,and the thermal efficiency of waste incinerator has increased by 11.1%,with the significant optimization effect.

关 键 词：垃圾焚烧炉 深度学习 人工智能 燃烧优化 强化学习 

分 类 号：TK16[动力工程及工程热物理—热能工程]