基于MSET诊断技术锅炉受热面泄漏预测算法建模及实践

火电厂锅炉受热面泄漏事故不仅发生几率高、普遍性强,而且影响较大,直接影响接带电量及经营目标的完成;另外在脱硝SCR投运后,若不及时发现炉膛内部受热面泄漏,当泄漏量较大烟气含水率提高后将会导致SCR催化剂中毒的严重后果,所以如何根据现有DCS数据进行受热面泄漏预测,将变得非常有意义。本文以某单位1000MW机组锅炉屏过受热面为研究对象,研究基于MSET诊断技术锅炉屏过受热面泄漏预测算法建模,通过受热面泄漏关联因素因素分析,最终确定了以屏过受热面壁温作为模型输入因素,经过模型训练,成功了预测了锅炉屏过受热面泄漏事故,验证了通过该预测算法模型预测屏过受热面泄漏的可行性。

The leakage accident of the heating surface of the thermal power plant boiler not only has a high probability,is universal,but also has a large impact,directly affecting the completion of the power supply and the completion of the business objectives.In addition,after the denitration SCR is put into operation,if the internal heating surface of the furnace is not leaked in time,the large amount of leakage will increase the moisture content of the flue gas,which will lead to serious consequences of SCR catalyst poisoning,So how to predict the leakage of the heated surface based on the existing DCS data will become very meaningful.In this paper,the heating surface of the boiler superheater of a 1000MW unit is taken as the research object,and the leakage prediction algorithm of the screen superheater based on the MSET diagnostic technology boiler is studied.The factors related to the leakage of the heated surface leakage are finally determined.The wall temperature of the heated surface of the superheater was used as the model input factor.After the model training,the accident of the heating surface leakage of the boiler screen superheater was successfully predicted.The feasibility of predicting the leakage of the heated surface of the screen superheater by the prediction algorithm model was verified.