Research and Application of Improved Genetic Algorithm in Lanzhou Self-service Terminal Patrol System

  • Jiangwei Bai
  • Yi YangEmail author
  • Lian Li
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 905)


During the 2016–2017 period, Lanzhou government deployed 5000 self-service terminals throughout the city [1]. In order to ensure the normal operation of these devices, a patrol team of about 20 people was organized to check the operating status of the devices and repair the faulty every day. However, due to the wide distribution, and large quantity of devices and the frequent drainage of patrol personnel, the patrol task cannot be completed scientifically and efficiently. Most employees arrange the patrol sequence of devices on rules of thumb so that the efficiency of the patrol work cannot be further improved. In this paper, we made three new improvements to the genetic algorithm, such as using Greedy Ideas to generate initial population, combinating of superior group retains and roulette strategy and superior offspring to stop mutation. And we use the genetic algorithm to design the daily patrol path, ensuring that the patrol work of the devices can be conducted scientifically and efficiently.


Genetic algorithm Path planing Patrol system 



This study is supported by Science and Technology Innovation Project of Foshan City, China (Grant No. 2015IT100095), the Fundamental Research Funds for the Central Universities (Grant No. lzujbky-2016-br03), CERNET Innovation Project (Grant No. NGII20150603) and Science and Technology Planning Project of Guangdong Province, China (Grant No. 2016B010108002).


  1. 1.
    The new practice of governing the country - the Gansu chapter. Serving the last mile and more provinces and cities to praise the Lanzhou 3D digital platform. (in Chinese). Accessed 17 Jan 2017–7 May 2018
  2. 2.
    Li, J.W.: Research on Logistics Distribution TSP. Harbin Institute of Technology (2017). (in Chinese)Google Scholar
  3. 3.
    Wang, L., Li, M., Cai, J.C., Liu, Z.H.: Research on application of improved genetic algorithm in path planning of mobile robot. Mech. Sci. Technol. Aerosp. Eng. 36(05), 711–716 (2017). (in Chinese)Google Scholar
  4. 4.
    Liu, S.T., Ling, J., Xiao, P.: The computational complexity of TSP. Mod. Comput. 06, 6–9 (2001). (in Chinese)Google Scholar
  5. 5.
    Chen, L., Pan, D.Z.: Improved genetic algorithm to solve TSP problem. Intell. Comput. Appl. 6(05) (2016). (in Chinese)Google Scholar
  6. 6.
    Jiang, R.: Application of improved genetic algorithm in TSP. Softw. Guide 15(12), 127–129 (2016). (in Chinese)Google Scholar
  7. 7.
    Zhao, X.C., Guo, S.: Genetic algorithm for solving multiple traveling salesman problem with relative solution space. CAAI Trans. Intell. Syst. 1–9 (2018). (in Chinese)Google Scholar
  8. 8.
    Chen, G., Deng, Y.: Some new methods of constructing fitness function in feature selection of genetic algorithms and their applications. Mech. Sci. Technol. Aerosp. Eng. 30(01) (2011). (in Chinese)Google Scholar
  9. 9.
    Zhang, G.J., Wu, J.F., Liu, L.F., Peng, Z.F.: Digital community learning map development based on WeChat applet. J. Guangzhou Univ. (Soc. Sci. Ed.) 16(11), 57–63 (2017). (in Chinese)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.School of Information Science and EngineeringLanzhou UniversityLanzhouChina
  2. 2.Silk Road Economic Belt Research CenterLanzhou UniversityLanzhouChina

Personalised recommendations