Online drift compensation method for sensor in bionic olfaction system

Abstract

The invention relates to an online drift compensation method for a sensor in a bionic olfaction system, and belongs to the technical field of sensors. The method comprises the following steps: 1) performing source domain reconstruction according to an input sample batch number; and 2) constructing a classification model by using the reconstructed source domain and target domain samples, and storing a prediction result; using output response samples of sensors in two successive batches of bionic olfaction systems; performing source domain reconstruction on a previous batch of samples predictedby a classification model and an initial batch of manually labeled samples, and establishing the classification model through conditional distribution adaptation and manifold regularization to realizeonline drift compensation of the sensor in the bionic olfaction system. According to the invention, the gas identification model can be continuously updated along with the drifting of the sensor, theactual production and use scenes of the bionic olfaction system in a real scene are better met, and the service life of equipment can be prolonged.

Description

technical field [0001] The invention belongs to the technical field of sensors and relates to an online drift compensation method for sensors in a bionic olfactory system. Background technique [0002] The bionic olfactory system consists of a gas sensor array, a signal preprocessing unit, and a pattern recognition algorithm, which can be used for gas recognition. When the gas enters the system, the sensor array generates a corresponding electrical signal response according to the characteristics of the gas, and converts the preprocessed signal into a gas recognition result through a pattern recognition algorithm. [0003] The sensor will drift due to its own aging or gas poisoning. Drift problems have long existed with the use of bionic olfactory systems and cannot be avoided. Drift will change the output response of the sensor, which will lead to the inability of the initially constructed classification model to accurately predict the samples collected later. [0004] I...

AI Technical Summary

Problems solved by technology

Drift is a long-standing problem with the use of bionic olfactory systems and cannot be avoided

Drift will change the output response of the sensor, which will lead to the inability of the initially constructed classification model to accurately predict the samples collected later

[0004] In recent years, many algorithms for sensor drift compensation have been proposed, which are mainly divided into three categories: signal preprocessing, component correction and machine learning. Although these algorithms can achieve sensor drift compensation to a certain extent, most of them are offline methods and need to be recycled regularly. The equipment needs to be manually corrected, which is not suitable for practical application scenarios

In addition, there is a difference in the characteristic distribution of the output response samples before and after the sensor drifts. Previous work related to drift compensation has focused on reducing the difference in edge distribution, without considering the impact of the difference in conditional distribution.

Images