The prediction of oxygen content of the flue gas in gas-fired boiler system using neural networks and random forest

Abstract

The oxygen content of the gas-fired boiler flue gas can monitor boiler combustion efficiency. Conventionally, this oxygen content can be measured using an oxygen content sensor. However, because it operates in extreme conditions, this oxygen sensor tends to have the disadvantage of high maintenance costs. In addition, the absence of other sensors as an element of redundancy and when there is damage to the sensor causes manual handling by workers using portable measuring instruments. It is dangerous for these workers, considering environmental conditions with high-risk hazards. To overcome the problems, we propose an artificial neural network (ANN) and random forest based soft sensor on predicting the oxygen content in the flue gas of a gas-fired boiler system. The prediction is made by utilizing measured data on the power plant’s boiler, consisting of 19 process variables accessed from the historical storage of a distributed control system. The research has proved that the proposed soft sensor successfully predicts the oxygen content of the boiler flue gas. Research using random forest shows better performance results than ANN. The random forest prediction errors are MAE of 0.0486, MSE of 0.0052, RMSE of 0.0718, and Std Error of 0.0719. While the errors using ANN are MAE of 0.0715, MSE of 0.0087, RMSE of 0.0935, and Std Error of 0.0935.