Application of Multivariate Statistical Models to Prediction of ${\mathrm{NO}}_x$ Emissions from Complex Industrial Heater Systems

Industrial fired heaters are a major source of nitrogen oxides ( ${\mathrm{NO}}_x$ ). On-line analyzers, kinetic models with computational fluid dynamics, and empirical predictive models have been developed to monitor ${\mathrm{NO}}_x$ emissions and analyze excessive ${\mathrm{NO}}_x$ emissions. However, previous approaches have been applied only to single heater systems, not to large-scale multiheater systems. This paper proposes a hierarchical monitoring and diagnosis procedure to monitor ${\mathrm{NO}}_x$ emissions from large-scale multiheater systems and to identify the root causes of excessive ${\mathrm{NO}}_x$ emissions as well as heater malfunctions. The procedure provides a functional three-layer hierarchy: (1) prediction of ${\mathrm{NO}}_x$ concentrations; (2) estimation of the influence of individual heaters on the predicted ${\mathrm{NO}}_x$ ; and (3) identification of the root causes by examining the detailed contributions of process variables to variations of the heater identified in step 2 as being the principal source of ${\mathrm{NO}}_x$ . An integrated multiblock partial least-squares (PLS) model, created by combining standard PLS and multiblock PLS, is employed to predict the ${\mathrm{NO}}_x$ emissions and estimate the influences of the heaters on the emissions. The validity of the proposed method is demonstrated through its application in two case studies.