Hydrate decomposition

During gas hydrate extraction, insufficient heating or depressurization can lead to incomplete hydrate decomposition, resulting

in lower-than-expected actual gas production. In this paper, a method for assessing the degree of hydrate decomposition based on an electronic nose

system is proposed. First, the electronic nose system was developed to

collect the information of gas produced by gas hydrate decomposition

under different humidity conditions. Then, a Convolutional Neural

Network combined with Domain Adaptive Compensation feature

extractor (CNN-DAC) was used to extract moisture-insensitive features, which can improve the humidity generalization ability of the assessment model. Finally, a CNN-DAC-RF model by combining CNN-DAC with

random forest (RF) was proposed, which can accurately assess the hydrate decomposition degree level. The experimental results show that the accuracy of the model reached 98.67%. In the comparison experiments with other feature extraction methods, the classification accuracy of

CNN-DAC-RF was improved by 1.32% in the source domain (high humidity data), and by 42.49% in the target domain (low

humidity data). In summary, the combination of CNN-DAC-RF and electronic nose provides a reliable technical means for the assessment of the degree of hydrate decomposition during hydrate mining.