Abstract
The increasing use of nuclear technology in various fields makes it necessary to provide the required safety to work with this industry. Gamma source is one of the most widely used sources in industry and medicine. Finding a lost gamma source in a gamma irradiation room without human presence is challenging due to the particular arrangements and barriers in the room for radiation shielding and requires an efficient and robust method. In this paper, locating and routing the lost gamma source in the gamma irradiation room containing radiation blocking barriers are done simultaneously by using two methods, convolutional neural network (CNN) and Q-learning, which are powerful algorithms for deep learning and machine learning. Environment simulation with gamma source was performed using Geant4 simulation. The results show that by combining these two methods in geometries with radiation blocking barriers, in addition to locating with 90% accuracy, routing can also be performed. Although the presence of thick barriers in the room reduces the accuracy, increases the time required to finding the lost gamma source or the inefficiency of other methods, nevertheless, the results show that combination of CNN and Q-learning reduces the time and greatly increases the accuracy.
Highlights
The increasing use of nuclear technology in various fields makes it necessary to provide the required safety to work with this industry
In other words, increasing the wall thickness from 50 cm to 2 m reduces the accuracy by more than 25%. These results show that in the geometry with thick walls, the convolutional neural network (CNN) is not enough alone to determine the location of the lost gamma source in a short time and with high reliability
Using a method in which the agent can identify the environment geometry and search the gamma radiation to simultaneously estimate the location of the gamma source and routing toward the gamma source can be a suitable method in this room
Summary
A convolutional neural network (CNN) is a deep learning algorithm that receives an image input. According to the Q-learning table, five new measurements are measured to get closer to the gamma source After this step, the agent records ten measurements as a 10-steppath matrix, which will give to CNN again as input. The CNN re-estimates the gamma source location with a higher percentage of accuracy This process continues until a 25-step path is formed, unless the agent reaches the. While forming a longer path, the agent gets closer to the gamma source, which helps the measurement process be carried out optimally to route and increase accuracy. The Q-learning algorithm detects the environment and helps the CNN purposefully record the deposited gamma radiation energy in different places and use them to predict the gamma source location with appropriate accuracy
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
