A Comparative Study for Position Regulation and Anti-Swing Control of Highly Non-Linear Double Inverted Pendulum (DIP) System Using Different Soft Com

A Comparative Study for Position Regulation and Anti-Swing Control of Highly Non-Linear Double Inverted Pendulum (DIP) System Using Different Soft Com

Ashwani Kharola, Pravin P. Patil
Copyright: © 2017 |Pages: 23
DOI: 10.4018/IJFSA.2017040104
(Individual Articles)
No Current Special Offers


This paper presents a comparative analysis for stabilization and control of highly non-linear, complex and multi-variable Double Inverted Pendulum on cart. A Matlab-Simulink model of DIP has been built using governing mathematical equations. The objective is to control both the pendulums at vertical position while cart is free to move in horizontal direction. The control of DIP was achieved using three different soft-computing techniques namely Fuzzy logic reasoning, Neural networks (NN's) and Adaptive neuro fuzzy inference system (ANFIS). The results show that the ANFIS controller is more effective as compared to other two controllers in terms of settling time (sec), maximum overshoot (degree) and steady state error. The regression (R) and mean square error (MSE) values obtained after training of Neural network were adequate and the training error obtained in ANFIS was also optimum. All the three controllers were able to stabilize the DIP system but ANFIS control provides better results as illustrated with the help of graphs and tables.
Article Preview


Inverted Pendulum is a highly non-linear system and exists in different variants (Lee, 1990; Gupta & Qi, 1991). It is a popular laboratory model for practical implementation and demonstration of control systems (Sang, Fan & Liu, 2011). Various Soft computing techniques have been applied to control these systems (Bhangal, 2013). Chen, Li & Gu (2010) applied neural controller based on two stage chaos optimization algorithm for controlling DIP system. The controller was designed to solve local minimum problem which is one of the disadvantage of Back-propagation (BP) neural networks. Zhang, An & Shao (2011) proposed an ANFIS controller based on fusion function for stability and control of DIP. The proposed method reduced dimension of the system by decreasing number of input variables thereby solving the problem of fuzzy rule explosion. Xiu-fen, Hai-bin & Hua-jun (2003) developed an artificial neural network (ANN) based on BP algorithm having 4 inputs and 3 layers for DIP. The proposed controller was compared to fuzzy controller which showed higher precision, better astringency and lower calculations of ANN controller.

According to (Nejafard, Yazdanpanch & Hassanzadeh, 2011) a locally linear neuro fuzzy (LLNF) approach can be applied to build a friction compensation model of DIP. The LLNF model was further compared with multi-layer perceptron network which demonstrated better performance of LLNF approach. (Jung, Cho & Hsia, 2007) experimentally controlled a 2-degree of freedom (DOF) inverted pendulum on an x-y plane using a decentralized neural network. The neural controllers control both pendulum angle and cart position. Fuyan Cheng et al. (1991) designed a fuzzy controller having high accuracy and high resolution to stabilize a DIP at upright position. The study combined fuzzy control theory with optimal control theory to determine composition coefficients. Tatikonda, Buttula & Kumar (2010) addressed ANFIS controllers for stabilization of inverted pendulum. A four input ANFIS controller was presented and compared to most commonly used PID Controller. In a study by Lee and Jung (2008) a Takagi-sugeno neuro fuzzy control scheme was applied to control inverted pendulum system. The authors derived a BP learning algorithm for derived for on-line learning and control. A swing up and stabilization controller for self-erecting inverted pendulum was proposed by Saifizul et al. (2006). The study considered a takagi-sugeno based ANFIS controller to provide stability at unstable positions.

Complete Article List

Search this Journal:
Volume 13: 1 Issue (2024)
Volume 12: 1 Issue (2023)
Volume 11: 4 Issues (2022)
Volume 10: 4 Issues (2021)
Volume 9: 4 Issues (2020)
Volume 8: 4 Issues (2019)
Volume 7: 4 Issues (2018)
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing