BACK PROPAGATION NEURAL NETWORK MODEL FOR TEMPERATURE AND HUMIDITY COMPENSATION OF A NON DISPERSIVE INFRARED METHANE SENSOR

The infrared absorption gas sensor detects CH4, CO, CO2, and other gases accurately and rapidly. However, temperature and humidity have a great impact on the gas sensor's performance. This article studied the response of an infrared methane gas sensor under different temperatures and humidity conditions. After analyzing the compensation methods, a back propagation neural network was chosen to compensate the nonlinear error caused by temperature and humidity. The optimal parameters of the neural network are reported in this article. After the compensation, the mean error of the gas sensor's output was between 0.02–0.08 vol %, and the maximum relative error dropped to 8.33% of the relative error before compensation. The results demonstrated that the back propagation neural network is an effective method to eliminate the influence of temperature and humidity on infrared methane gas sensors.

[1]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[2]  Junhua Liu,et al.  Improving selectivity of infrared gas analyzer with neural network , 2003, International Symposium on Instrumentation and Control Technology.

[3]  Dermot Diamond,et al.  Non-linear carbon dioxide determination using infrared gas sensors and neural networks with Bayesian regularization , 2009 .

[4]  Zhuangde Jiang,et al.  Note: response characteristics of the sensor based on LaF3 thin film to different humidified gases. , 2012, The Review of scientific instruments.

[5]  Chen Yuan-yuan.  A prediction model of volume fraction of mixed gas based on neural network , 2011 .

[6]  Zhang Fan,et al.  BP Neural Network Modeling of Infrared Methane Detector for Temperature Compensation , 2007, 2007 8th International Conference on Electronic Measurement and Instruments.

[7]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[8]  Yu-qiang Yang,et al.  A Novel Carbon Monoxide Detection System Based on Infrared Absorption Used in Mine , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[9]  Guangjun Zhang,et al.  A novel CO2 gas analyzer based on IR absorption , 2004 .

[10]  Yuhui Xu,et al.  A One ppm NDIR Methane Gas Sensor with Single Frequency Filter Denoising Algorithm , 2012, Sensors.

[11]  Changying Li,et al.  Neural network and Bayesian network fusion models to fuse electronic nose and surface acoustic wave sensor data for apple defect detection , 2007 .