Research on a Mixed Gas Recognition and Concentration Detection Algorithm Based on a Metal Oxide Semiconductor Olfactory System Sensor Array

• Published in: Sensors (Basel, Switzerland) Vol. 18; no. 10; p. 3264
• Main Authors: Xu, Yonghui, Zhao, Xi, Chen, Yinsheng, Zhao, Wenjie
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI 28.09.2018; MDPI AG
• Subjects: Algorithms; Chemistry Techniques, Analytical - instrumentation; Chemistry Techniques, Analytical - methods; gas detection; gas identification; Gases - analysis; Gases - chemistry; Humans; kernel principal component analysis; Metals - chemistry; multivariate relevance vector machine; Oxides - chemistry; Principal Component Analysis; Semiconductors; sensor array; Smell; Support Vector Machine; multivariate relevance vector machine; gas identification; kernel principal component analysis; gas detection; sensor array
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s18103264

As a typical machine olfactory system index, the accuracy of hybrid gas identification and concentration detection is low. This paper proposes a novel hybrid gas identification and concentration detection method. In this method, Kernel Principal Component Analysis (KPCA) is employed to extract the nonlinear mixed gas characteristics of different components, and then K-nearest neighbour algorithm (KNN) classification modelling is utilized to realize the recognition of the target gas. In addition, this method adopts a multivariable relevance vector machine (MVRVM) to regress the multi-input nonlinear signal to realize the detection of the concentration of the hybrid gas. The proposed method is validated by using CO and CH4 as the experimental system samples. The experimental results illustrate that the accuracy of the proposed method reaches 98.33%, which is 5.83% and 14.16% higher than that of principal component analysis (PCA) and independent component analysis (ICA), respectively. For the hybrid gas concentration detection method, the CO and CH4 concentration detection average relative errors are reduced to 5.58% and 5.38%, respectively.