Secondary combustion chamber high-temperature gas concentration detection method, system and device based on convolutional neural network and storage medium

Abstract

The invention discloses a secondary combustion chamber high-temperature gas concentration detection method, system and device based on a convolutional neural network and a storage medium. The method comprises the steps that collecting laser spectrum signals corresponding to different gas concentrations based on a tunable semiconductor laser absorption spectrum technology; carrying out voltage value sampling on the collected laser spectrum signals, and adding a gas concentration label to each piece of sample data obtained by sampling to obtain a sample data set; establishing a gas concentrationmeasurement model based on the convolutional neural network based on the sample data set; selecting a training sample from the sample data set to perform network training on the gas concentration measurement model; and monitoring the concentration of the high-temperature gas in a secondary combustion chamber in real time based on the trained gas concentration measurement model. By establishing the detection models of different gas concentrations offline, online real-time monitoring can be performed on the high-temperature gas concentration of the secondary combustion chamber, and the detection precision of the high-temperature gas concentration is improved, so that the ignition time of a combustor is automatically and reasonably controlled.

Description

technical field [0001] The invention relates to the technical field of high-temperature gas concentration detection, in particular to a method, system, device and storage medium for detecting high-temperature gas concentration in a secondary combustion chamber based on a convolutional neural network. Background technique [0002] The garbage incinerator adopts a two-stage combustion method, the first combustion chamber burns solids, and the second combustion chamber burns gas: the gas produced by pyrolysis in the first combustion chamber enters the second combustion chamber for full combustion, the purpose is to deal with toxic and harmful gases, and the second combustion chamber is set If the burner is used to support the combustion, it is usually ignited when the gas in the second combustion chamber is full and reaches the threshold concentration. If it is ignited in advance, the service life of the burner will be shortened. If it is ignited too late, the gas concentration ...

AI Technical Summary

Problems solved by technology

[0006] The present invention aims to solve at least one of the technical problems existing in the prior art, and especially innovatively proposes a method, system, device and storage medium for detecting the concentration of high-temperature gas in the secondary combustion chamber based on convolutional neural network, and establishes the The detection model of different gas concentrations can carry out online real-time monitoring of the high-temperature gas concentration in the second combustion chamber, which improves the detection accuracy of the high-temperature gas concentration, thereby realizing automatic and reasonable control of the ignition timing of the burner, and effectively solving the problems in the existing technology. The detection accuracy of the gas concentration in the second combustion chamber is not enough, so the problem of early ignition may shorten the service life of the burner or cause explosion if ignition is too late

Images