Automatic interpretation model construction method and device for mass chromatograms and electronic equipment

Abstract

The invention provides an automatic interpretation model construction method and device for mass chromatograms and electronic equipment, and the method comprises the steps: obtaining the mass chromatograms corresponding to a plurality of samples, processing each mass chromatogram to obtain corresponding feature data, and calculating to obtain a sample label of each feature data; and training the constructed neural network model by using the feature data carrying the sample labels until a preset requirement is met, thereby obtaining an interpretation model which can be used for performing automatic information analysis on the to-be-processed quality chromatogram. According to the scheme, a machine learning mode is adopted, and the explanation model is obtained through training by obtaining the feature data and the sample labels, so that analysis and explanation of the quality chromatogram data can be automatically realized, and the purposes of extracting more features of the quality chromatogram, reflecting more comprehensive information and realizing high-dimensional analysis can be supported.

Description

technical field [0001] The invention relates to the technical field of automatic processing, in particular to a method, device and electronic equipment for building an automatic interpretation model of a mass chromatogram. Background technique [0002] Gas chromatography-mass spectrometry (GC-MS) is an important analytical and testing method for petroleum exploration. The GC-MS system realizes the identification and quantification of many compounds in petroleum through the separation of mixed organic matter by chromatography and the identification of molecular structure by mass spectrometer. The mass chromatogram is the raw data obtained by GC-MS analysis. It consists of a fluctuating curve. Various raised peaks reflect the response of the instrument to different compounds, and the area (or height) of the peak reflects the content of the compound. Based on this data, petroleum geochemists can analyze the age, parent material type, thermal maturity and other information of o...

AI Technical Summary

Problems solved by technology

[0003] Under the existing technical methods, mass chromatograms cannot be directly used for oil exploration related work, they need to be manually processed and interpreted by geochemical or analytical chemistry technicians, the general process includes peak labeling, identification of compounds, integration and calculation of peaks A series of tedious operations such as the area and the formation of the analysis report, etc., and finally calculated such as sterane C 29 αα20S / (20S+20R), Terpenes Ts / Tm and Ga / C 30 αβ and other parameters used to describe the geochemical characteristics of sample petroleum

Therefore, under the existing technical methods, mass chromatograms rely heavily on the manual interpretation of professionals, the processing process is cumbersome and time-consuming, and has a high technical and use threshold, which limits the wide use of this data to a certain extent.

Moreover, due to the limitation of manual analysis methods, for very complex mixtures such as petroleum, only a small number of typical compounds can be used in actual work and research, which reduces the accuracy of interpretation results and follow-up research. defect

Images