基于PSO-Attention-LSTM算法的煤电脱硫脱硝运行状态预测方法
Method forpredicting the operation status of coal electricity desulfurization and denitration based on PSO-Attention-LSTM algorithm
侯深 1祝业青 1李祥 1潘云1
作者信息
- 1. 国电环境保护研究院有限公司,江苏南京 210000
- 折叠
摘要
煤电脱硫脱硝的正常运行对电力系统的安全稳定有着重要影响,但是传统预测方法存在准确率不高的问题,因此提出一种改进PSO-Attention-LSTM的煤电脱硫脱硝运行状态预测方法.首先,建立优化煤电脱硫脱硝运行状态的主要指标及其权重指标,在数据输入阶段,通过PSO-Attention-LSTM获取运行状态数据相关的时空特征,对煤电脱硫脱硝运行状态作出预测,完成煤电脱硫脱硝潜在性故障的预警信息.试验结果显示,该预测方法对煤电脱硫脱硝运行状态的预测精度在84％,能够较好准确预测煤电脱硫脱硝的运行状态,可用于煤电脱硫脱硝运维管理的参考辅助.
Abstract
The normal operation of coal-fired desulfurization and denitrification has a significant impact on the safety and stability of the power system.However,traditional prediction methods have the problem of low accuracy.An improved PSO-Attention LSTM method for predicting the operational status of coal-fired desulfurization and denitrification is proposed.Firstly,establish the main indicators and their weight indicators for optimizing the operation status of coal-fired power desulfurization and denitrification.In the data input stage,obtain the spatiotemporal characteristics related to the operation status data through PSO-Attention LSTM,predict the operation status of coal-fired power desulfurization and denitrification,and complete the warning information of potential faults in coal-fired power desulfurization and denitrification.The experimental results show that the prediction accuracy of this prediction method for the operational status of coal-fired power desulfurization and denitrification is 84％,which can effectively and accurately predict the operational status of coal-fired power desulfurization and denitrification.It can be used as a reference assistance for the operation and maintenance management of coal-fired power desulfurization and denitrification.
关键词
煤电脱硫脱硝/状态预测/粒子群优化/注意力机制/长短期记忆网络Key words
coal electric desulfurization and denitrification/state prediction/PSO/attention mechanism/LSTM引用本文复制引用
出版年
2024
NETL
NSTL
万方数据