Abstract
This paper presents an adaptive functional-based neuro-fuzzy PID incremental controller structure that can be tuned either offline or online according to required controller performance. First, differential membership functions are used to represent the fuzzy membership functions of the input–output space of the three-term controller. Second, controller rules are generated based on the discrete proportional, derivative, and integral functions for the fuzzy space. Finally, a fully differentiable fuzzy neural network is constructed to represent the developed controller for either offline or online controller parameter adaptation. Two different adaptation methods are used for controller tuning, offline method based on controller transient performance cost function optimization using bees algorithm and online method based on tracking error minimization using back-propagation with momentum algorithm. The proposed control system was tested to show the validity of the controller structure over a fixed PID controller gains to control SCARA® type robot arm.
Similar content being viewed by others
Abbreviations
- BA:
-
Bees algorithm
- BP:
-
Back-propagating
- FNN:
-
Fuzzy neural network
- FFNN:
-
Feed-forward fuzzy neural network
- FLC:
-
Fuzzy logic control
- FLS:
-
Fuzzy logic system
- FAM:
-
Fuzzy associative memory
- FCE:
-
Fuzzy control element
- FPCE:
-
Fuzzy proportional control element
- FDCE:
-
Fuzzy derivative control element
- FICE:
-
Fuzzy integral control element
- MSF:
-
Membership function
- MOM:
-
Mean of maxima defuzzification method
- NN:
-
Neural network
- NFPID:
-
Neuro-fuzzy proportional, integral, derivative controller
- PID:
-
Proportional, integral, derivative controller
- TS model:
-
Takagi and Sugeno model
References
Ahn KK, Anh HPH (2009) Identification of the pneumatic artificial muscle manipulators by MGA-based nonlinear NARX fuzzy model. IFAC J Mechatron 19(1):106–133
Anh HPH (2010) Online tuning scheduling MIMO neural PID control of the 2-axes pneumatic artificial muscle (PAM) robot arm. Expert Syst Appl 37(9):6547–6560
Arabshahi P, Choi JJ, Marks RJ, Caudell TP (1992) Fuzzy control of Backpropagation. IEEE international conference on fuzzy systems, 8–12 March 1992, San Diego, California, USA, pp 967–972
Bao-Gang H, George KIM, Raymond GG (2001) A systematic study of fuzzy PID controllers-function-based evaluation approach. IEEE Trans Fuzzy Syst 9(5):699–712
Berenji HR, Khedkar P (1992) Learning and tuning fuzzy logic controllers through reinforcements. IEEE Trans Neural Netw 3(5):724–740
Breedon PJ, Sivayoganathan K, Balendran V, Al-Dabass D (2002) Multi-axis fuzzy control and performance analysis for an industrial robot. In: Proceedings of the IEEE international conference on fuzzy systems, vol 1, 12–17 May 2002, Honolulu, HI, USA, pp 500–505
Er MJ, Yap SM, Yeaw CW, Luo FL (1997) A review of neural-fuzzy controllers for robotic manipulators. Thirty-second IAS annual meeting, IEEE industry applications conference, vol 2, 5–9 October 1997, New Orleans, Los Anglos, USA, pp 812–819
Erbatur K, Kaynak O, Rudas I (1995) A study of fuzzy schemes for control of robotic manipulators. IECON twenty-first IEEE international conference on industrial electronics, control, and instrumentation, vol 1, 6–10 November 1995, Orlando, Florida, USA, pp 63–68
Estevez PA, Nakano R (1995), Hierarchical mixture of experts and max–min propagation neural networks. IEEE international conference on neural networks, 27 November–1 December 1995, Perth, WA, Australia, pp 651–565
Fahmy AA, Abdel Ghany AM (2013) Neuro-fuzzy inverse model control structure of robotic manipulators utilized for physiotherapy applications. Proc Ain Shams Eng J 4(4):805–829
Fahmy AA, Kalyoncu M, Castellani M (2011) Automatic design of control systems for robot manipulators using the bees algorithm. Proc Inst Mech Eng Part I J Syst Control Eng. doi:10.1177/0959651811425312
Huang Y, Yasunobu S (2000) A general practical design method for fuzzy PID control from conventional PID control. The ninth IEEE international conference on fuzzy systems, vol 2, 2000
Karasakal O, Yesil E, Guzelkaya M, Eksin I (2005) Implementation of a new self-tuning fuzzy PID controller on PLC. Turk J Electr Eng 13(2):277–286
Kawato M, Uno Y, Isobe M, Suzuki R (1988) Hierarchical neural network model for voluntary movement with application to robotics. IEEE Control Syst Mag 8(2):8–15
Khan S, Adam A, Zahirul Alam AHM, Islam MR, Khalifa OO (2008) Rule-based fuzzy logic controller with adaptable reference. Int J Electr Comput Eng 3(5):574–586
Lee CC (1990) Fuzzy logic in control systems fuzzy logic controller part I. IEEE Trans Syst Manuf Cybern 20(2):404–418
Lee CC (1990) Fuzzy logic in control systems fuzzy logic controller part II. IEEE Trans Syst Manuf Cybern 20(2):419–435
Lin C-T, Lee CSG (1991) Neural network-based fuzzy logic control and decision system. IEEE Trans Comput 40(12):1320–1336
Mann G, Bao-Gang Hu, Gosine R (1999) Analysis of direct action fuzzy PID controller structures. IEEE Trans Syst Man Cybern B Cybern 29(3):371–388
Ming-Kun C, Jeih-Jang L, Ming-Lun C (2011) T–S fuzzy model-based tracking control of a one-dimensional manipulator actuated by pneumatic artificial muscles. Control Eng Pract 19:1442–1449
Miyamoto H, Kawato M, Setoyama T, Suzuki R (1988) Feedback-error learning neural network for trajectory control of robotic manipulator. Neural Netw 1(3):251–265
Miyamura A, Kimura H (2002) Stability of feedback error learning scheme. Syst Control Lett 45(4):303–316
Moudgal VG, Kwong WA, Passino KM (1995) Fuzzy learning control for a flexible-link robot. IEEE Trans Fuzzy Syst 3(2):199–210
Nauck D, Kruse R (1993) A fuzzy neural network learning fuzzy control rules and membership functions by fuzzy error back propagation. IEEE international conference on neural networks, pp 1022–1027
Pedrycz W (1993) Fuzzy control and fuzzy systems. Wiley, NewYork
Petrov M, Ganchev I, Taneva A (2002) Fuzzy PID control of nonlinear plants. In: First international IEEE symposium intelligent systems, 2002
Pham DT, Fahmy AA (2005) Neuro-fuzzy modelling and control of robot manipulators for trajectory tracking. In: Proceedings of the 16th IFAC world congress, vol 16, part 1, 2005, Czech Republic, pp 415–429
Pham DT, Fahmy AA, Eldukhri EE (2008) Adaptive fuzzy neural network for inverse modeling of robot manipulators. In: Proceedings of the 17th IFAC world congress, 2008, Seoul, Korea, 6–11 July 2008, pp 5308–5313
Runkler TA (1997) Selection of appropriate defuzzification methods using application specific properties. IEEE Trans Fuzzy Syst 5(1):72–79
Saade JJ (1996) A unifying approach to defuzzification and comparison of the outputs of fuzzy controllers. IEEE Trans Fuzzy Syst 4(3):227–237
Shankir Y (2001) Fuzzy logic systems and fuzzy neural networks for dynamic systems modelling and control. Ph.D. Thesis, University of Wales, Cardiff School of Engineering, Cardiff University, UK
Shing J, Jang R (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23(3):665–685
Sinthipsomboon K, Hunsacharoonroj I, Khedari J, Pongaen W, Pratumsuwan P (2011) A hybrid of fuzzy and fuzzy self-tuning PID controller for servo electro-hydraulic system. 6th IEEE conference on industrial electronics and applications (ICIEA), 2011
Takagi T, Sugeno M (1985) Fuzzy identification of systems and its applications to modelling and control. IEEE Trans Syst Manuf Cybern SMC-15(1):116–132
Tang W, Chen G, Lu R (2001) A modified fuzzy PI controller for a flexible-joint robot arm with uncertainties. Fuzzy Sets Syst 118(1):109–119
Terashita J, Kimura H (2002) Robustness of feedback error learning method with time delay. In: Proceedings of the 41st SICE/IEEE annual conference, vol 4, 5–7 August 2002, Tokyo, Japan, pp 2240–2244
Ying H (1993) The simplest fuzzy controllers using different inference methods are different non-linear proportional-integral-controllers with variable gains. Automatica 29(6):1579–1589
Ying H, Siler W, Buckley JJ (1990) Fuzzy control theory: a non-linear case. Automatica 26(3):513–520
Yuan F, Feldkamp LA, Davis LI Jr, Puskorius GV (1992), Training a hybrid neural-fuzzy system. IEEE/IJCNN international joint conference on neural networks, vol 2, 7–11 June 1992, Baltimore, MD, USA, pp 739–744
Zhang X, Hang CC, Tan S, Wang P-Z (1996) The min–max function differentiation and training of fuzzy neural networks. IEEE Trans Neural Netw 7(5):1139–1150
Author information
Authors and Affiliations
Corresponding author
Appendix: SCARA® robot dynamics
Appendix: SCARA® robot dynamics
The equations of motion can be described by a set of differential or difference equations. The equation set consists of two parts, the kinematics equations and the dynamic equation. Robot arm kinematics deals with the geometry of robot arm motion as a function of time (position, velocity, and acceleration) without reference to the forces and moments that cause this motion, while the dynamics of robot is the study of motion with regard to forces and torques.
In robotics manipulators, there are two methodologies used for dynamic modeling.
-
(a)
Newton–Euler formulation.
-
(b)
Lagrangian formulation.
An analytical approach based on the Lagrange’s energy function, known as Lagrange–Euler method, results in a dynamic solution that is simple and systematic. In this method, the kinetic energy (K) and the potential energy (P) are expressed in terms of joint motion trajectories. The resulting differential equations then provide the forces (torques) which drive the robot. Closed-form equations result in a structure that is very useful for robot control design and also guarantee a solution. The dynamics of n-link manipulators are conveniently described by Lagrangian dynamics. In the Lagrangian approach, the joint variables, q = (q 1, …, q n )T, serve as a suitable set of generalized coordinates. The kinetic energy is a quadratic function of the vector \(\dot{q}\) of the form:
where the n × n “inertia matrix” D(q) is symmetric and positive definite for each q. The gravitational potential energy P = P(q) is independent of \(\mathop q\limits^{.}\). The Euler–Lagrange equations for such a system can be derived as follows. Since
where L is the Lagrangian, then the dynamic equations of an n-joint robotic manipulator described by Lagrange’s equations can be expressed as:
where q is the generalized coordinates of the robot arm, \(\dot{q}_{i}\) is the first derivative of q i ; D(q) is the symmetric, bounded, positive-definite inertia matrix; vector C(q, \(\dot{q}\)) \(\dot{q}\) presents the centrifugal and Coriolis torque; G(q), B(\(\dot{q}\)) and τ represent the gravitational torque, friction and applied joint torque, respectively.
D(q) (n × n matrix) expressed as:
where A k and B k represent 3 × n Jacobian submatrices, m k is the mass of link k, and D k is the n × n link inertia tensor which depends on q. The equation of velocity coupling vector C(q, \(\dot{q}\)) is:
The equation of gravity loading vector (n × 1) is:
and the frictional force model for joint k is expressed as:
where f = \(\frac{{ - \left| {\dot{q}_{k} } \right|}}{\varepsilon }\), \(b_{k}^{v}\) represent the coefficient of viscous friction, \(b_{k}^{d}\) is the coefficient of dynamic friction, and \(b_{k}^{s}\) is the coefficient of static friction for joint k, and ε is a small positive parameter. The dynamic equation derived by using the Euler–Lagrangian method for the first two arms of the SCARA configuration will be as follows [6]:
First joint:
Second joint:
where m i is the mass and a i is the length of link i, C and S represent the cos(q) and sin(q), respectively. Let the state defines as x T = [q T, v T], where v = q. Since n = 2, the manipulator inertia tensor is a symmetric 2 × 2 matrix. From the coefficients of the joint accelerations, the distinct components of D(q) are:
Because D(q) is symmetric, then
Rights and permissions
About this article
Cite this article
Fahmy, A.A., Abdel Ghany, A.M. Adaptive functional-based neuro-fuzzy PID incremental controller structure. Neural Comput & Applic 26, 1423–1438 (2015). https://doi.org/10.1007/s00521-014-1807-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-014-1807-6