Indian Journal of Science and Technology
DOI: 10.17485/ijst/2016/v9i21/94813
Year: 2016, Volume: 9, Issue: 21, Pages: 1-9
Original Article
Muhammad Hamid* , Mohsin Jamil, Syed Omer Gilani, Shahid Ikramullah, Muhammad Nasir Khan, Mazhar Hussain Malik and Ishtiaq Ahmad
School of Mechanical and Manufacturing Engineering (SMME), [email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
*Author for Correspondence
Muhammad Hamid
School of Mechanical and Manufacturing Engineering (SMME),
Email:[email protected]
Background/Objectives: Cranes are used to carry loads effectively. During movement, often undesired fluctuations of lifted payload occur, which needs to be controlled. Control is the basic requirement for desired operation of crane. Objective is to control the trolley position and swing angle of payload. Methods/Statistical Analysis: The continual flow requires an effective control methodology to achieve a high positioning control of the trolley carrying payload and suppression of swing angle of payload during operation. Optimal control techniques can be used to control these undesired vibrations. These techniques result in some undesired overshoot and undershoot causing the payload to swing prior to system getting stable. However if these techniques are combined with intelligent control techniques then a more stable system can be obtained. Findings: In this paper a hybrid controller called neuro-optimal controller has been used to control the swing angle of lifted payload by controlling the trolley position.The proposed technique of using a hybrid controller has stabilized the system by reducing the overshoot, undershoot and settling time. Application/Improvements: The proposed technique is very useful in many industrial applications. Experimental analysis can further provide the insight and limitations of the proposed techniques.
Keywords: Artificial Neural Network (ANN), Algebraic Riccati Equation (ARE), Back Propagation (BP), Linear Quadratic Regulator Controller (LQR), Neural Network Predictive Controller (NNPC), 3 Degree of Freedom (3DOF)
Subscribe now for latest articles and news.