Rapid determination of radon progeny concentration based on artificial neural networks

The rapid measurement of radon progeny concentration is of great significance for improving the efficiency of radon exposure dose evaluation in a specific area. In order to achieve rapid measurement of radon progeny concentration in engineering applications, this study is based on the rapid calculation function of BP (back propagation) neural network and uses other relevant environmental parameters to quickly obtain the radon progeny alpha potential energy. The relative standard uncertainty is 7.6% (k = 2), which met the uncertainty requirements of the standard of JJG (Military) 99-2015.The radon progeny alpha potential energy and its related parameters are substituted into the constructed neural network for training. According to the set training requirements, the range is set to 0-760 mu J/m(3), and the simulation results meet the requirements of the JJG (Military Industry) 99-2015 standard. The effect of rapid measurement can be achieved under the condition of ensuring measurement accuracy.

Automated summary

This study utilizes the BP neural network and environmental parameters for rapid calculation of radon progeny concentration, meeting uncertainty requirements and achieving rapid measurement in engineering applications.