Abstract
Predictive emission monitoring systems (PEMS) are software solutions for the validation and supplementation of costly continuous emission monitoring systems for natural gas electrical generation turbines. The basis of PEMS is that of predictive models trained on past data to estimate emission components. The gas turbine process dataset from the University of California at Irvine open data repository has initiated a challenge of sorts to investigate the quality of models of various machine learning methods to build a model for predicting CO and NOx emissions depending on ambient variables and the parameters of the technological process. The novelty and features of this paper are: (i) a contribution to the study of the features of the open dataset on CO and NOx emissions for gas turbines, which will enable one to more objectively compare different machine learning methods for further research; (ii) for the first time for the CO and NOx emissions, a model based on symbolic regression and a genetic algorithm is presented—the advantage of this being the transparency of the influence of factors and the interpretability of the model; (iii) a new classification model based on the symbolic regression model and fuzzy inference system is proposed. The coefficients of determination of the developed models are: R2=0.83 for NOx emissions, R2=0.89 for CO emissions.
Highlights
One of the essential sources of harmful pollutants (NOx and carbon monoxide (CO)) released in the atmosphere is the combustion process in the power industry
The idea of crisp presentation of the intervals leads to the fact that an emission of 4.7 mg/m3 belongs to the standard emission class and an emission of 4.8 mg/m3 belongs to the extreme emission class, we decided to apply the approach based on fuzzy logic, a concept first introduced in [21]
This paper presents a study of an open dataset on CO and nitrogen dioxide (NOx) emissions from gas turbines
Summary
One of the essential sources of harmful pollutants (NOx and CO) released in the atmosphere is the combustion process in the power industry. In [8], the authors presented a new class of reliable-based multiple linear regression (MLR) models called Etemadi and evaluated the performance of the Etemadi model and classic MLR model using the same dataset to predict the hourly net energy yield (TEY) of the turbine with gas turbine parameters and the ambient variables as predictors. The purpose of our research was to study the open dataset on CO and NOx emissions in order to choose suitable machine learning algorithms for emission predictions, investigate the quality of the resulting models and build symbolic regression models as an explainable method of prediction
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
