Research on a soft-measurement model of gasification temperature based on recurrent neural network

Gasification temperature measurement is one of the most challenging tasks in an entrained-flow gasifier and often requires indirect calculation using the soft-sensor method,a parameter prediction method using other parameters that are more easily measurable and using correlation equations that are widely accepted in the gasification field for the temperature data.Machine learning is a non-linear prediction method that can adequately act as a soft sensor.Furthermore,the recurrent neural network(RNN)has the function of memorization,which makes it capable of learning how to deal with temporal order.In this paper,the oxygen-coal ratio,CH_(4)content and CO_(2)content determined through the process analysis of a 3000-t/d coal-water slurry gasifier are used as input parameters for the soft sensor of the gasification temperature.The RNN model and back propagation(BP)neural network model are then established with training-set data from gasification results.Compared with prediction set data from the gasification results,the RNN model is found to be much better than the BP neural network based on important indexes such as the mean square error(MSE),mean absolute error(MAE)and standard deviation(SD).The results show that the MSE of the prediction set of the RNN model is 6.25℃,the MAE is 10.33℃and the SD is 3.88℃,respectively.The overall accuracy,the average accuracy and the stability effects are well within the accepted ranges for the results as such.

A back analysis of the temperature field in the combustion volume space during underground coal gasification

The exact shape and size of the gasification channel during underground coal gasification(UGC) are of vital importance for the safety and stability of the upper parts of the geological formation.In practice existing geological measurements are insufficient to obtain such information because the coal seam is typically deeply buried and the geological conditions are often complex.This paper introduces a cylindrical model for the gasification channel.The rock and soil masses are assumed to be homogeneous and isotropic and the effect of seepage on the temperature field was neglected.The theory of heat conduction was used to write the equation predicting the temperature field around the gasification channel.The idea of an excess temperature was introduced to solve the equations.Applying this model to UCG in the field for an influence radius,r,of 70 m gave the model parameters,u1,2,3...,of 2.4,5.5,8.7...By adjusting the radius(2,4,or 6 m) reasonable temperatures of the gasification channel were found for 4 m.The temperature distribution in the vertical direction,and the combustion volume,were also calculated.Comparison to field measurements shows that the results obtained from the proposed model are very close to practice.

Temperature field distribution of burnt surrounding rock in UCG stope

In order to study temperature field distribution in burnt surrounding rock and to determine ranges of burnt surrounding rock, coal-wall coking cycle and heat influence in the underground coal gasification(UCG) stope, based on the Laplace transform and inversion formula, we studied the temperature analytical solution of one-dimensional unsteady heat conduction for multi-layer overlying strata under the first and the forth kinds of boundary conditions, and we also carried out a numerical simulation of twodimensional unsteady heat conduction by the COMSOL multiphysics. The results show that when the boundary temperature of surrounding rock has a linear decrease because of a directional movement of heat source in the UCG flame working face, the temperature in surrounding rock increases first and then decreases with time, the peak of temperature curve decreases gradually and its position moves inside surrounding rock from the boundary. In the surrounding rock of UCG stope, there is an envelope curve of temperature curve clusters. We analyzed the influence of thermophysical parameters on envelope curves and put forward to take envelope curve as the calculation basis for ranges of burnt surrounding rock, coal-wall coking cycle and heat influence. Finally, the concrete numerical values are given by determining those judgement standards and temperature thresholds, which basically tally with the field geophysical prospecting results.