Adaptive parameter control of search group algorithm using fuzzy logic applied to networked control systems

• Published in: Soft computing (Berlin, Germany) Vol. 22; no. 23; pp. 7939 - 7960
• Main Authors: Noorbin, Seyedeh Fa’ezeh Hosseini, Alfi, Alireza
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2018; Springer Nature B.V
• Subjects: Adaptive control; Artificial Intelligence; Computational Intelligence; Control; Control systems design; Controllers; Engineering; Evolutionary algorithms; Exploitation; Fuzzy control; Fuzzy logic; Fuzzy sets; Mathematical Logic and Foundations; Mechatronics; Methodologies and Application; Mutation; Network control; Optimization algorithms; Parameters; Proportional integral derivative; Random variables; Robotics; Robust control; Set theory; Fuzzy logic; Network-based control systems; Search group algorithm; PID controller; Smith predictor; Null hypothesis significance testing
• ISSN: 1432-7643; 1433-7479
• DOI: 10.1007/s00500-017-2742-0

Search group algorithm (SGA) is one of the newest nature-inspired heuristics for solving different engineering optimization problems. Like other evolutionary algorithms, SGA suffers from the parameters tuning, which is considerably dependent on the problem. The purpose of this paper is to introduce an adaptive parameter control using fuzzy logic, namely fuzzy SGA (FSGA), for enhancing the solution quality of the basic SGA. In FSGA, a fuzzy system is incorporated to dynamically adjust the control parameter value with respect to normalized iteration and normalized error value, which are the inputs of the system. To evaluate the performance of FSGA, firstly, it is compared against those of state-of-the-art algorithms over the well-known benchmark functions. Null hypothesis significance testing is then applied to make algorithm ranking. Finally, in order to demonstrate the potential applicability of FSGA in the field of control, it is adopted to design of robust proportional-integral-derivative controller for the network-based control system dealing with time delays existed in the communication channel. The results verify the feasibility of the proposed FSGA.