Loading...

Control of a 5-Link Parallel Robot with Computational Intelligent Techniques

Rafizadeh, Roya | 2010

849 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 40745 (55)
  4. University: Sharif University of Technology, International Campus, Kish IslandScience and Engineering
  5. Department: Science and Engineering
  6. Advisor(s): Seifipour, Navid; Jahed, Mehran
  7. Abstract:
  8. Control of parallel robots continues to be a challenging research topic. The structural variety of such robots dictated by the application and function makes such control strategies even more unique. As these robots often require nonlinear control schemes, such research has been focused towards two general controlling computational intelligent methods, namely adaptive (and optimal) control and artificial intelligence (e.g. fuzzy and Neural Net) based control. This study considers Neural Net (NNs) and fuzzy control method in order to propose a control scheme for a newly introduced 5-link parallel robot which has 3 degrees of freedom operating in a single plane environment (i.e. two dimensions). The kinematics and dynamics of the proposed structure was initially studied through known robotic analytical approach followed by a systematic SIMULINK simulation under MATLAB environment. Our first effort was based on a NNs MLP model with a SD learning algorithm. As the results of NNs control implementation proved to be unacceptable and unstable in critical dynamic conditions, a fuzzy controller was introduced. Our results indicate that the parallel robot was suitably and adequately controlled through the combination of two fuzzy control algorithms which were introduced depending on the condition prescribed in the rules and therefore the stability condition of the controller. Our novel combinatory fuzzy controller proves to be an appropriate intelligent controller for the proposed nonlinear parallel manipulation system
  9. Keywords:
  10. Control ; Neural Network ; Fuzzy Logic ; Parallel Robot ; Computational Intelligent Technique

 Digital Object List

 Bookmark

No TOC