{"title":"Output Feedback Controller for a Class of Unknown Nonlinear Discrete Time Systems Using Fuzzy Rules Emulated Networks and Reinforcement Learning","authors":"C. Treesatayapun","doi":"10.1080/16168658.2021.1943887","DOIUrl":null,"url":null,"abstract":"A model-free adaptive control for non-affine discrete time systems is developed by utilising the output feedback and action-critic networks. Fuzzy rules emulated network (FREN) is employed as the action network and multi-input version (MiFREN) is implemented as the critic network. Both networks are constructed using human knowledge based on IF–THEN rules according to the controlled plant and the learning laws are established by reinforcement learning without any off-line learning phase. The theoretical derivation of the convergence of the tracking error and internal signal is demonstrated. The numerical simulation and the experimental system are given to validate the proposed scheme.","PeriodicalId":37623,"journal":{"name":"Fuzzy Information and Engineering","volume":"5 1","pages":"368 - 390"},"PeriodicalIF":1.3000,"publicationDate":"2021-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fuzzy Information and Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/16168658.2021.1943887","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATHEMATICS, APPLIED","Score":null,"Total":0}
引用次数: 1
Abstract
A model-free adaptive control for non-affine discrete time systems is developed by utilising the output feedback and action-critic networks. Fuzzy rules emulated network (FREN) is employed as the action network and multi-input version (MiFREN) is implemented as the critic network. Both networks are constructed using human knowledge based on IF–THEN rules according to the controlled plant and the learning laws are established by reinforcement learning without any off-line learning phase. The theoretical derivation of the convergence of the tracking error and internal signal is demonstrated. The numerical simulation and the experimental system are given to validate the proposed scheme.
期刊介绍:
Fuzzy Information and Engineering—An International Journal wants to provide a unified communication platform for researchers in a wide area of topics from pure and applied mathematics, computer science, engineering, and other related fields. While also accepting fundamental work, the journal focuses on applications. Research papers, short communications, and reviews are welcome. Technical topics within the scope include: (1) Fuzzy Information a. Fuzzy information theory and information systems b. Fuzzy clustering and classification c. Fuzzy information processing d. Hardware and software co-design e. Fuzzy computer f. Fuzzy database and data mining g. Fuzzy image processing and pattern recognition h. Fuzzy information granulation i. Knowledge acquisition and representation in fuzzy information (2) Fuzzy Sets and Systems a. Fuzzy sets b. Fuzzy analysis c. Fuzzy topology and fuzzy mapping d. Fuzzy equation e. Fuzzy programming and optimal f. Fuzzy probability and statistic g. Fuzzy logic and algebra h. General systems i. Fuzzy socioeconomic system j. Fuzzy decision support system k. Fuzzy expert system (3) Soft Computing a. Soft computing theory and foundation b. Nerve cell algorithms c. Genetic algorithms d. Fuzzy approximation algorithms e. Computing with words and Quantum computation (4) Fuzzy Engineering a. Fuzzy control b. Fuzzy system engineering c. Fuzzy knowledge engineering d. Fuzzy management engineering e. Fuzzy design f. Fuzzy industrial engineering g. Fuzzy system modeling (5) Fuzzy Operations Research [...] (6) Artificial Intelligence [...] (7) Others [...]