Open AccessResearch on Adaptive Comprehensive Learning Artificial Bee Colony Algorithm and Its Application in Constant Pressure Water Supply
Author(s) -
Mingzhu Li,
Xiao Feng
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1650/3/032150
Subject(s) - pid controller , control theory (sociology) , convergence (economics) , constant (computer programming) , artificial bee colony algorithm , controller (irrigation) , computer science , water supply , population , mathematical optimization , control engineering , engineering , mathematics , control (management) , artificial intelligence , temperature control , agronomy , demography , sociology , economics , biology , programming language , economic growth , environmental engineering
The constant pressure water supply control system is nonlinear and hysteretic, which makes the control problem difficult to solve. In order to achieve accurate closed-loop control of water supply pressure, this paper designs ACLABC-PID controller based on improved Artificial Bee Colony algorithm. First of all, in view of the slow convergence speed and easy to fall into the local optimum of the ABC algorithm, an adaptive comprehensive learning strategy of the ABC algorithm (ACLABC) is proposed. The algorithm adopts the learning strategy of learning from other excellent individuals and global optimal individuals, enriches the diversity of the population, adaptively and gradually reduces the search area, and effectively eliminates the defects of easily falling into local extremum and slow convergence in the later stage. ACLABC algorithm takes both local development and global exploration into account, which improves the convergence speed and accuracy of the algorithm. Then, the ACLABC algorithm is applied to the PID control parameter optimization of constant pressure water supply, and compared with the ABC-PID controller and the critical proportion method PID controller, the simulation results show that the ACLABC-PID controller significantly improves the dynamic and steady performance of the system.