Abstract
This document describes the implementation of a neuro-fuzzy adaptive system MIMO (Multiple Input Multiple Output), using two neuro-fuzzy MIMO systems: one for control and the other for identifying the plant. Under this approach, the controller is optimized, employing the model obtained during the identification of the plant that utilizes data generated from the controller’s operation. In this way, the plant identification and the controller optimization is performed iteratively. The application case consists of controlling a MIMO non-linear hydraulic system fed by a pump and a three-way valve. In order to observe the controller performance various experimental configurations are considered.
Highlights
When having uncertainty, inaccuracy, and ambiguity in the phenomenon to model and control, the fuzzy logic systems seem a suitable option given the flexibility when describing this type of behavior [1], [2]
The document is distributed as follows: Section II shows the structure of the hydraulic Multiple Input Multiple Output (MIMO) plant to know the parts of this system; Section III describes the general architecture of the adaptive neuro-fuzzy control system employed, presenting the adaptive strategy used to control the plant; a detailed design of a compact neuro-fuzzy system based on Boolean relations is shown in Section IV, where first the configuration of the compact system used is described, and how it can be configured to achieve the analogy with dynamic systems in discrete time obtaining neuro-fuzzy subsystems
MIMO HYDRAULIC SYSTEM This section focuses on showing the characteristics of the plant to be controlled, where the model of the system is presented in a block diagram used as a reference to build the MIMO neuro-fuzzy system employed for plant identification
Summary
Inaccuracy, and ambiguity in the phenomenon to model and control, the fuzzy logic systems seem a suitable option given the flexibility when describing this type of behavior [1], [2]. The document is distributed as follows: Section II shows the structure of the hydraulic MIMO plant to know the parts of this system; Section III describes the general architecture of the adaptive neuro-fuzzy control system employed, presenting the adaptive strategy used to control the plant (some key aspects are described); a detailed design of a compact neuro-fuzzy system based on Boolean relations is shown, where first the configuration of the compact system used is described, and how it can be configured to achieve the analogy with dynamic systems in discrete time obtaining neuro-fuzzy subsystems.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
