Laser Raman spectroscopy has obvious advantages in detecting transformer fault characteristic gases. With the development of intelligent transformer condition monitoring, it is of great significance to study the fast and accurate quantitative analysis method of mixed fault characteristic gases.Conventional Raman spectral analysis requires a preprocessing process that greatly relies on human experience and spectral feature extraction. Although it can reduce the signal dimensions, it can also result in partially missing or altered spectral features. Aiming at the above problems, a method for quantitative analysis of Raman spectra based on the fusion of improved 1DCNN and LSSVR is proposed; that is, the introduction of global mean pooling and least squares support vector regression improves traditional CNN, and the use of the Dropout method to improve model generalization performance and prevent over-fitting. Design and build the transformer fault characteristic gas Raman spectroscopy detection platform, collect the Raman signal of 7 kinds of fault characteristic gases and N2, O2 mixed gases, in the spectrogram near 2 900 cm-1 frequency shift, CH4, C2H6 gases show the overlap of the spectral peaks, and when transformer overheating or partial discharge fault occurs, it will produce the main fault characteristic gas CH4, choose different content ratio of CH4, C2H6 mixed gas as a representative research object, 146 groups of mixed gas samples with different contents of CH4 and C2H6 are prepared according to different ratios. Nitrogen is chosen as the standard gas for detection, the Raman spectral data of the mixed gas samples with different content ratios are collected, and the spectral data enhancement method is utilized to construct the gas sample dataset suitable for deep neural networks. Through continuous experiments, we optimize the network structure parameters and network weights, complete the model training and test its prediction effect, compare and analyze with multiple quantitative models, study the effect of spectral preprocessing on different quantitative models, and then evaluate the model performance. The results show that when using the original data set for modeling, the improved CNN model has the best prediction accuracy and regression fitting goodness, the R2 can reach 0.999 8, and the RMSE is only 0.000 5 MPa; using preprocessed data. When modeling the set, the RMSE of the improved convolutional neural network model is 0.002 3 MPa, which is an increase of 0.001 8 compared to the modeling error using the original data set. In contrast, the errors of traditional methods have declined.The results of this study show that the proposed method integrates the spectral pre-processing, feature extraction, and quantitative analysis processes compared with the traditional Raman spectroscopy quantitative method, which simplifies the spectral analysis process based on ensuring the prediction accuracy and provides new ideas and references for the fast and accurate analysis of transformer mixed fault characteristic gases.