生活垃圾由于其成分复杂,存在焚烧热值波动大的特点,造成焚烧过程运行控制难度大等问题。利用机器学习等智能算法和燃烧图像视觉分析技术,建立关键运行参数预测模型和燃烧工况实时诊断,结合垃圾焚烧技术工艺构建了垃圾焚烧关键设备的控制模块,形成了垃圾焚烧智能优化控制系统,实现燃烧过程的超前调控,解决现有焚烧过程调控手段滞后和适应性差的问题。以650t/d垃圾焚烧炉为测试对象,结果表明：智能控制系统相比于纯人工操作,可以显著提升运行参数的稳定性,参数目标值与实际值平均偏差降低25%以上,标准差降低了超过20%,同时控制系统明显降低人工操作频次达92%以上,显示出该控制系统良好的应用效果,为垃圾焚烧炉智能化控制提供了解决方案。

Municipal solid waste, due to its complex composition, exhibits significant fluctuations in calorific value during incineration, leading to challenges in operational control. By employing intelligent algorithms such as machine learning and combustion image visual analysis technology, prediction models for key operating parameters and real-time diagnosis of combustion conditions were established. Combined with waste incineration processes, control modules for key equipment were developed, forming an intelligent optimization control system for waste incineration. This system enables predictive control of the combustion process, addressing the lagging and poor adaptability of existing regulation methods. Tested on a 650t/d waste incinerator, the results show that compared to manual operation alone, the intelligent control system significantly enhances the stability of operating parameters. The average deviation between target and actual values decreased by over 25%, and the standard deviation was reduced by more than 20%. Additionally, the system substantially reduced manual operation frequency by over 92%, demonstrating its excellent performance. This provides an effective solution for the intelligent control of waste incinerators.

国家重点研发计划资助项目(2024YFC3909000)