An electronic nose recognition method based on bionic olfactory bulb model and convolutional neural network

Abstract

The invention relates to an electronic nose identification method based on a bionic olfactory bulb model and a convolutional neural network, comprising: using an electronic nose platform to sample objects to be identified to obtain an electronic nose sample data set S; constructing a bionic olfactory bulb model: the bionic olfactory bulb model is composed of multiple The number of olfactory bulb models in the bionic olfactory bulb model is consistent with the number of sensors in the electronic nose. Each olfactory bulb model is connected by four basic neuron models, each of which is an olfactory neuron model. Receptors, 1 mitral cell, 1 granule cell and 1 periglobular cell; after inputting the sample data set S through the olfactory receptor into the bionic olfactory bulb model for processing, a new multivariate pulse time series data set S' is obtained; data normalization processing ; Obtain the corresponding grayscale data set M; determine the convolutional neural network model; training. The invention can realize automatic feature extraction and end-to-end learning, and improves the universality of the electronic nose recognition algorithm.

Description

technical field [0001] The invention belongs to the field of instruments and measurement, in particular to an electronic nose recognition method based on a bionic olfactory bulb model and a convolutional neural network. Background technique [0002] The electronic nose is a modern bionic detection instrument, which can simulate the structure and function of the human and mammalian olfactory system, and realize the detection and recognition of simple or complex odors. The recognition of smell by electronic nose is a typical pattern recognition problem, and the recognition methods currently used are all classical pattern recognition methods. Electronic nose sampling signals usually need to go through data analysis steps such as data preprocessing, feature extraction, feature dimensionality reduction and classifier identification, and finally obtain the recognition results of different odors. This recognition method based on the classic pattern recognition idea has a mature al...

AI Technical Summary

Problems solved by technology

[0003] However, this idea also has shortcomings: 1) Data preprocessing, feature extraction, feature dimensionality reduction and classifier design, each step has many optional algorithms / methods, and for different electronic nose systems and applications, often It is necessary to try a large number of different algorithm combinations to obtain the "optimal" recognition effect, especially the electronic nose feature extraction step, and there are no guidelines for this algorithm combination trial process, so it is very time-consuming; 2) Different electronic noses Systems and applications often require different algorithm combinations to obtain better recognition results, which means that the algorithm lacks versatility, which is not conducive to the promotion of electronic nose technology in different applications

Images