Dataset for: Research on Predicting Thermal Efficiency of Natural Gas Boilers Using a Deep Learning Ensemble Model

This dataset contains the historical operational data used in the study titled 'Research on Predicting Thermal Efficiency of Natural Gas Boilers Using a Deep Learning Ensemble Model'. The data was collected from the Distributed Control System (DCS) of three identical natural gas boilers in a cogeneration plant over a one-year period, with a sampling frequency of 5 minutes. The dataset includes the following 11 features used for model training and prediction: Steam flow, Flue gas temperature, Flue gas oxygen content, Gas net calorific value, Gas flow, Steam temperature, Feedwater flow, Steam pressure (gauge), Feedwater pressure, Feedwater temperature, and Air Inlet Temperature. This data was used to train, validate, and test an RNN-CNN ensemble model for predicting boiler thermal efficiency. Due to the proprietary nature of the operational data, the files are under restricted access. The data can be made available from the corresponding author upon reasonable request.