An experimental study of the effect of pulverization on the thermal destruction of coal is carried out. Artificial neural networks are used to develop a model that allows predicting the degree of...
1 December 2019 in Journal of Physics: Conference Series
This paper is devoted to study combustion of pulverized coal in a 5 MW thermal furnace with tangential scroll supply of coal-air suspension and cylindrical reaction chamber. Deep learning approaches were used to monitor the combustion of a coal flame in a furnace and to determine combustion anomalies from flame images. We have developed a deep neural network autoencoder, which is a combination of convolutional layers, fully-connected layers and upsampling layers. The autoencoder was trained to reconstruct the combustion regimes that corresponded to high values of the coefficient of excess air. The trained autoencoder was then used to identify abnormal burning regimes with a lower excess air ratio, in which there is an increase in the amount of unburned coal dust. The best classification model had AUC ROC quality metric value on a test image sample AUC ROC = 0.8. The average precision of the model was 77% and the average recall was 66%. The metrics obtained is limited by the quality of the image labeling due to poorly controlled experimental conditions. The paper concluded that the use of upsampling with convolutional layers show themselves better than the deconvolutional layers, and the combination of convolutional layers with fully-connected layers constitutes the optimal architecture of the model.
1 July 2020 in Journal of Engineering Thermophysics
The possibility of increasing the reactivity of low grade Kansk-Achinsk brown coal 2 BR from the Irsha-Borodino deposit due to mechanically activated micronizing by means of special mill disintegrators has been shown on the 5-MW experimental firing stand at the Institute of Thermophysics SB RAS (IT). This coal is used in the coal-fired PK-38 boiler of station 2B of the Krasnoyarsk State District Power Station-2 (SDPS-2). The experimental studies to ensure ignition and achievement of stable autothermal coal combustion have yielded the minimum operation time of the gas ignition device; to determine the effect of temperature on the ignition and combustion, the temperature of the burner muffle wall was controlled. In accordance with the experimental data on burning the coal with increased reactivity and the economic efficiency evaluation, the coal can be recommended for replacement of highly reactive fuel oil for ignition and lighting of the boiler considered.
9 February 2026 in Engineering Applications of Artificial Intelligence
This paper describes the application of Recurrent Neural Networks (RNN) for effectively detecting anomalies in time series data obtained from experimental study of the combustion and gasification of mechanically activated coal fuel in a thermal furnace. We train Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM) units to learn the normal time series patterns and predict anomaly values. The resulting prediction errors between real and expected values are analyzed to give anomaly scores. To investigate the most suitable configuration of RNN and evaluate the effectiveness of the anomaly detection model, we used three datasets of real-world data that contain several types of anomalies. The developed RNN algorithm detected 9 out the 9 collective anomalies in the hold-out sample with one false positive anomaly event.
27 July 2022 in Journal of Engineering Thermophysics
The conditions of coal ignition and combustion with application of plasma ignition system have been studied experimentally. Research on plasma ignition of coal fuel flow was carried out on a pilot setup. The conditions were close to the industrial ones used for start-up of coal boilers. The operating range of the velocities of pulverized coal flow in the electric arc unit has been determined. It has been established that a stable process of ignition and further combustion of coal is possible at these flow velocities in the electric arc unit. The experimental setup was started up from a cold state and heated to a temperature of 1000°C; the start-up time did not exceed 200 s. Based on the obtained experimental results, an industrial prototype of plasma ignition system (PIS) was designed and tested with a TP-10 boiler with a capacity of 220 tons of steam per hour. The boiler was started up from a cold state by means of the PIS technology without use of fuel oil; the start-up time was 5 hours. After the pass of pulverized coal through the PIS, stable ignition and combustion of pulverized coal flame with a temperature of 1350°C was observed in the boiler. For the first time, a technology for ignition of pulverized coal boilers without use of fuel oil was created and implemented on the basis of a starting burner with plasma ignition of fuel. The technology features positive economic and environmental parameters in comparison with the widespread technology of starting up coal-fired boilers with liquid fuel combustion.