基于ADAM-BPNN优化模型的磨煤机智能启动技术研究

Research and Application of Automatic Control Technology Based on ADAM-BPNN Model for Pulverizing System in Thermal Power Plant

为改善制粉系统的启动效率,提高机组对电网负荷的响应速度,对影响设备正常启动的因素进行了分析,认为原煤仓落煤不畅及磨煤机预暖迟缓制约了中速磨制粉系统的可靠投用。基于给煤量指令与皮带转速的偏差,利用ADAM-BPNN优化模型,对原煤仓下煤不畅建立了智能预警模型,显著提高了给煤可靠性监测的时效性;采用模糊自适应算法对磨煤机预暖程序进行了针对性优化,程控暖磨时间相较手动操作大大缩短。经优化调整后,制粉系统在机组调峰过程中投用快速、运行稳定,相关经验可供后续同类型机组参考。

In order to improve the start-up efficiency of the pulverizing system and the response speed of the unit to the power grid load, the factors affecting the normal start-up of the equipment are analyzed. Based on the deviation between the coal feeding instruction and the belt speed, an intelligent early warning model was established for the coal failure in the original coal bunker by using adam-BPNN optimization model, which significantly improved the timeliness of coal feeding reliability monitoring. Fuzzy adaptive algorithm is used to optimize the pre-heating program of coal mill, and the heating time of program control is greatly shortened compared with manual operation. After optimization and adjustment, the pulverizing system can be put into use quickly and run stably in the process of unit peak regulation, and the relevant experience can be used for reference for the following units of the same type.