Intelligent method for inhibiting gas-sensitive sensor decussation sensitivity

Abstract

The invention discloses an intelligent method for inhibiting cross sensitivity of gas sensor, which uses intrinsic gas characteristic spectrum amplitude as the input vector of neural network, calculates via an artificial neural network based on a neural network structure marked and trained via standard gas to further eliminate the cross sensitivity of gas sensor caused by laminated frequency to obtain single gas content and improve inhibit effect, thereby improving gas detection precision and accuracy. The invention uses wavelet analysis to input characteristic vector to the artificial neutral network and uses the localization ability of wavelet analysis in time and frequency domains, to analyze characteristic gas response waveform and cross sensitive gas response waveform, to further improving the inhibition effect and improving gas detection precision and accuracy.

Description

technical field [0001] The invention relates to a data analysis method, in particular to an intelligent method for suppressing cross-sensitivity of gas sensors. Background technique [0002] The dissolved gas content in transformer oil is an important parameter to reflect the internal insulation and operation status of the transformer. The online monitoring of dissolved gas in transformer oil is an important means to reflect the gas content in oil in real time and continuously. Semiconductor gas sensor can detect the content of gas and convert it into a specific voltage signal, which is an important way to detect gas content. At present, the technology of using semiconductor gas sensor to monitor the gas content in oil is very extensive. Although a specific semiconductor gas sensor mainly detects a specific single gas, the sensor has poor selectivity to gases and may respond to multiple gases. This non-single selectivity is determined by its sensitive mechanism. Use certai...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, there is a method for eliminating the cross-sensitivity effect of gas sensors by using the neural network method, but there is no cross-sensitivity suppression method under the condition of multi-gas sensors in the relevant gas sensor cross-sensitivity characteristics involved, and the research is on self-inhibition and cross-sensitivity. Sensitive dynamic characteristics and other aspects are not involved in the multi-sensor cross-sensitive content of online monitoring of dissolved gas in transformer oil

In the fault diagnosis of transformers, the neural network is mostly used for the diagnosis of insulation faults and fault mode recognition, and does not suppress the cross-sensitive

Images