Modified monarch butterfly optimization with distribution functions and its application for 3 DOF Hover flight system

Ateş A., Akpamukçu M.

NEURAL COMPUTING AND APPLICATIONS, cilt.34, sa.1, ss.3697-3722, 2022 (SCI-Expanded)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 34 Sayı: 1
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1007/s00521-021-06635-x
  • Dergi Adı: NEURAL COMPUTING AND APPLICATIONS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Applied Science & Technology Source, Biotechnology Research Abstracts, Compendex, Computer & Applied Sciences, Index Islamicus, INSPEC, zbMATH
  • Sayfa Sayıları: ss.3697-3722
  • İnönü Üniversitesi Adresli: Evet

Özet

In this study, Modified Monarch Butterfly Optimization Algorithm (M2BO) is proposed by modeling stochastic processes

in Monarch Butterfly Optimization (MBO) algorithm with different random distribution functions. The proposed M2BO algorithm has been firstly tested with benchmark functions and the results have been compared with the literature and classical MBO algorithm. In order to analyze the performance of the proposed M2BO algorithm for the real engineering problem, the feedback gain matrix (K matrix) for the control of the 3 Degree of Freedom (3 DOF) Hover system has been

optimized. The results have been compared with classical MBO, DSO (Discrete Stochastic Optimization), and SMDO (Stochastic Multi-parameter Divergence Optimization) optimization algorithms. The obtained results have been compared on 3 DOF Hover simulation models and real-time 3 DOF Hover experimental sets. The performance of the proposed M2BOalgorithm in benchmark and real engineering problem tests has been shown theoretically and experimentally. Thus, it has

been shown that the performance of algorithms can be increased without changing the basic philosophy of algorithms by modeling stochastic processes in algorithms with random distributions other than a uniform distribution. In addition to these, it has been determined that distribution function-based contributions can be applied to many of these algorithms.