DocumentCode :
2073191
Title :
Study of global parameters optimization of large caliber sniper rifle based on genetic algorithm
Author :
Li, Peng ; Zhou, Guangfen ; Wang, Ruilin
Author_Institution :
Dept. of Guns Eng., Ordnance Eng. Coll., Shijiazhuang, China
fYear :
2008
fDate :
22-25 Nov. 2008
Firstpage :
395
Lastpage :
398
Abstract :
Large caliber sniper must satisfy several design requirements such as firing accuracy, reliability, weight limit and so on. How to get optimized structure parameters of large caliber sniper is a key target of designers. Global parameters optimization of large caliber sniper rifle based on genetic algorithm was studied in this paper. Firing accuracy was chosen as object function of global parameters optimization. Simulation model of firing accuracy was established firstly. Neural network method was used to fit object function. Genetic algorithm was used to search optimized structure parameters of whole rifle. A group of optimized structure parameters were got finally. The large caliber sniper rifle with these parameters has balanced performance according test. The study of this paper can offer a method for choosing better structure parameters of large caliber sniper rifle. Also the study can improve design efficiency.
Keywords :
genetic algorithms; military computing; neural nets; weapons; firing accuracy; genetic algorithm; global parameters optimization; large caliber sniper rifle; neural network method; object function; Acceleration; Algorithm design and analysis; Design engineering; Design optimization; Educational institutions; Genetic algorithms; Genetic engineering; Neural networks; Reliability engineering; Testing; Genetic algorithm; Optimization; Sniper Rifle;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer-Aided Industrial Design and Conceptual Design, 2008. CAID/CD 2008. 9th International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4244-3290-5
Electronic_ISBN :
978-1-4244-3291-2
Type :
conf
DOI :
10.1109/CAIDCD.2008.4730596
Filename :
4730596
Link To Document :
بازگشت