Abstract
Aiming at the problem of the coal mine rescue robot's perception of toxic and harmful gas in Coal Mine, The cross sensitivity of partial gas is reduced by using double gas sensor, and the influence of the variable factors such as temperature and humidity is considered, The improved RBF neural network based on genetic neural network algorithm and K clustering algorithm is proposed in combination with the practical application of coal rescue robot, A hybrid gas detection system based on RBF neural network is built. The experimental results show that: the improved RBF neural network algorithm is applied to the training of mixed gas quantitative recognition, The convergence speed is faster than the RBF neural network algorithm, and the learning accuracy is higher, Improve the performance of RBF and the detection accuracy of the mixed gas detection system, the system can take the quantitative detection of H2S, CO, CO2 and CH4 four kinds of gases and their mixed gas in the detection range.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call