关键词:

垃圾焚烧炉排炉')">

垃圾焚烧炉排炉, 人工智能, 深度学习, 神经网络, 时间序列预测

Abstract:

Against the current environmental backdrop of the "dual carbon goals," integrating technologies like artificial intelligence ( AI), big data, and cloud computing to achieve intelligent, green, and low-carbon municipal solid waste (MSW) incineration for power generation presents a significant challenge. This study employed the cross-correlation method to analyze the correlations among 110 variables in a waste incinerator. The analysis identified variables exhibiting strong correlations with three key predicted variables: Main Steam Flow, Average Furnace Temperature, and Average Oxygen Content. Based on this correlation analysis, the time delay steps between these three predicted variables (Main Steam Flow, Average Furnace Temperature, Average Oxygen Content) and the equipment control parameters were calculated. Four time-series forecasting models were then utilized to predict the Main Steam Flow, Average Furnace Temperature, and Average Oxygen Content. The results demonstrate that the PatchTST time-series forecasting model exhibits superior generalization and predictive capabilities. Trained on actual operational data, it effectively addresses data time delays and reduces errors stemming from subjective operator judgments. This approach provides robust data support for real-time online operations.

Key words: Grate-type waste incinerator')">

Grate-type waste incinerator, Artificial intelligence, Deep learning, Neural network,  ')"> Time series prediction

 ,