Correction model for CO detection in the coal combustion loss process in mines based on GWO-SVM

Abstract

Accurate detection of CO gas is crucial to the prevention of coal combustion. Tuneable diode laser absorption spectroscopy (TDLAS) is a reliable method for CO detection during coal combustion. The influences of temperature and pressure cause changes in the line strength and linewidth of the index gases’ absorption spectra, leading to sizable measurement errors. To correct the distortion of the CO absorption spectrum caused by temperature and pressure fluctuation, a compensation model based on the grey wolf optimizer–support vector machine (GWO–SVM) was proposed. The results were compared with those of the single SVM, the back propagation neural network (BPNN), and multiple regression analysis (MRA). MRA was revealed to result in the lowest accuracy, which indicated that MRA is not ideal for compensation in TDLAS. The hyperparameter selection of the SVM had the disadvantages of randomness and blindness, which led to instability and large errors. The BPNN achieved better correction in the training stage, but severe overfitting occurred in the testing stage. The modified results revealed that the GWO–SVM model had higher accuracy and stability than the other models. It effectively inhibited the effects of temperature and pressure on the measured concentration and greatly improved the measurement accuracy. The equipment is thus suitable for CO gas detection with the aim to preventing coal combustion loss, and it can be further applied to loss prevention in other process fields.