Multi-scale analysis and ensemble learning gas sensor fault mode identification method

Abstract

The invention discloses a gas sensor fault mode recognition method based on multi-scale analysis and ensemble learning, and the method comprises: carrying out the multi-scale analysis of a gas sensorfault signal, obtaining time sequences under different scale factors, and respectively calculating the weighted permutation entropy of each time sequence to form a composite multi-scale weighted permutation entropy feature vector; performing dimensionality reduction on the composite multi-scale weighted permutation entropy through a Fisher discrimination method, and enabling the composite multi-scale weighted permutation entropy to serve as a fault feature sample of pattern recognition; and constructing a plurality of base learners by using an ensemble learning method, carrying out classification prediction on the sub-sample sets of the fault feature sample set, and then summarizing classification results of the plurality of base learners to obtain a gas sensor fault mode identification result. According to the method, the difference of different fault types can be highlighted, the selected ensemble learning classifier has more excellent generalization performance and better classification accuracy for gas sensor fault recognition, and serious accidents are avoided.

Description

technical field [0001] The invention belongs to the technical field of machine olfaction, and relates to a gas sensor fault pattern recognition method based on multi-scale analysis and integrated learning. Background technique [0002] Pattern recognition is the main method to realize sensor fault recognition at present. The main process is as follows: First, collect the sensor signals under normal conditions and various fault conditions to form a training sample set for various states of the sensor; then select an appropriate fault signal feature extraction method to extract The fault feature information constitutes the fault feature training sample set; next, the fault feature training sample set is used to train the classifier based on the pattern recognition method; finally, the trained classifier is used to perform pattern recognition on the sensor test samples, and the classifier Output the type of fault identified. From the above process description, we can see that...

AI Technical Summary

Problems solved by technology

[0006] The present invention aims at the problem of poor discrimination of the extracted fault features for differe

Images