Abstract
Simulation results of our previous papers show a neural network direct controller which performs well by the use of folding behavior. This paper presents an analytical approach for the questions related to the folding behavior. The intermediate value theorem answers these questions. There is the suitable plant input for any plant output, although the plant is nonlinear. The same sign of the plant Jacobian can be selected for any plant output. We can use the same sign of the neural network parameter η, although the plant is nonlinear. This paper also presents how we tune the neural network parameter η based on the above analytical approach. The approach of this paper deals with the static continuous nonlinear plant. However, I believe that it is helpful to understand the neural network performance for the dynamical plant. This paper also presents future works based on this analytical approach.
Similar content being viewed by others
References
Albus JS (1975) “A new approach to manipulator control: the cerebellar model articulation controller”. Trans ASME J Dyn Syst 97(3):270–277
Narendra KS, Parthictsarathy K (1990) “Identification and control of dynamics system using neural networks”. IEEE Trans Neural Netw 1(1):4–27
Jordan MI (1989) “Generic Constrains on Uderspecified Target Trajectories”. Proceedings of international Joint Conference on Neural Networks, Washington D.C, pp 217–225
Kawato M, Uno Y, Isobe M, Suzuki R (1987) “A Hierarchical Model for Voluntary Movement and its Application to Robotics”. Proceedings of 1987 IEEE International Conference on Neural Networks, IV, pp. 573–582
Yabuta T, Yamada T (1990) “Possibility of Neural Networks Controller for Robot Manipulators”. Proceedings of the 1990 IEEE International Conference on Robotics and Automation, pp. 1686–1691
Yamada T, Yabuta T (1990) “Nonlinear Neural Network Controller for Dynamic System”. Proceedings of 16th Annual Conference of IEEE Industrial Electronics Society, pp 1244–1249
Yamada T, Yabuta T (1990) “An Extension of Neural Network Direct Controller”. Proceedings of IEEE International Workshop on Intelligent Robots and Systems’90, pp 619–626
Yamada T, Yabuta T (1990) “Adaptive neural network controllers for dynamics systems”. J Robot Mechatron 2:245–257
Yamada T, Yabuta T (1991) “Some remarks on characteristics of direct neuro-controller with regard to adaptive control”. Trans Soc Instrum Control Eng 27(7):784–791. (in Japanese)
Yabuta T, Yamada T (1991) “Learning Control Using Neural Network”. Proceedings of the 1991 IEEE International Conference on Robotics and Automation, pp 740–745
Aoshima S, Takeda K, Yamada T, Yabuta T (1991) “Auto-tuning of Feedback Gain Using Neural Network for a Small Tunnelling Robot”. Proceedings of IEEE/RSJ International Workshop on Intelligent Robots and Systems’91, pp 221–226
Yamada T, Yabuta T, Takahashi K (1991) “Remarks on an Adaptive Type Self-tuning Controller Using Neural Network”. Proceedings of 1991 International Conference on Industrial Electronics, Control and Instrument, pp 1389–1394
Yabuta T, Yamada T (1992) “Learning and Adaptive Ability of Neuro-control”. Proceedings of Canadian Conference on Electrial and Computer Engineering, TA6.19.1-TA6.19.4
Yabuta T, Yamada T (1992) “Learning control using neural network”. J Syst Eng 2:180–191
Yabuta T, Yamada T (1992) “Neural network controller characteristics with regard to adaptive control”. IEEE Trans Syst Man Cybern 22:170–177
Yamada T, Yabuta T (1992) “Neural network controller using autotuning method for nonlinear functions”. IEEE Trans Neural Netw 3:595–601
Yamada T, Yabuta T (1992) “Learning Type Direct Transfer Function Identifier For Discrete Time Systems Which Uses Neural Networks”. Proceedings of the Fourth International ISEM Symposium on Nonlinear Phenomena in Electromagnetic Fields, pp 25–28
Yamada T, Yabuta T, Shoji T (1992) “Application of a Neural Network Controller to a Dynamic System with an Unstable Inverse”. Proceedings of International Symposium on Neural Information. Proceeding as a part of International Symposia on Information Science, Kyushu Institute of Technology, pp 207–210
Yamada T, Yabuta T (1992) “Remarks on a Neural Network Controller which Uses an Auto-tuning Method for Nonlinear Functions”. Proceedings of International Joint Conference on Neural Networks, II-775-II-780
Yamada T, Aoshima S, Yabuta T (1992) “Application of a Neural Network Identifier to a Small Diameter Tunneling Robot”. Proceedings of 2nd IEEE International Workshop on Advanced Motion Control, pp 230–237
Yabuta T, Aoshima S, Yamada T (1993) “Learning and Adaptive Ability of Neuro-control”. Proceedings of IEEE International Workshop on Neuro-Fuzzy Control, pp 194–200
Yamada T, Yabuta T (1993) “Dynamic system identification using neural network”. IEEE Trans Syst Man Cybern 23:204–211
Yamada T, Takahashi K, Yasue N, Yabuta T (1993) “Remarks on a Learning Type Self-tuning Neural Network Controller”. Proceedings of International Conference on Advanced Robotics, pp 43–48
Yamada T, Yabuta T (1993) “Remarks on Neural Network Controller which Uses Genetic Algorithm”. Proceedings of International Joint Conference on Neural Networks, pp 2783–2786
Yamada T, Yabuta T (1993) “Application of Learning Type Feedforward Feedback Neural Network Controller to Dynamic Systems”. Proceedings of IEEE/RSJ International Conference on Intelligent Robotics and Systems, pp 225–231
Yamada T, Yabuta T (1994) “Remarks on Neural Network Controller Using Different Sigmoid Functions”. Proceedings of IEEE International Conference on Neural Networks, pp 2628–2632
Yamada T (1995) “Remarks on Neural Network Controller for Inverse Dynamics of Many-to-one Plant”. Proceedings of 1995 International IEEE/IAS Conference on Industrial Automation and Control : Emerging Technologies, pp 314–319
Yamada T (1995) “Remarks on Hybrid Neural Network Controller Using Different Convergence Speeds”. Proceedings of 1995 International Conference on Robotics and Automation, pp 562–568
Takahashi K, Yamada T (1996) “Remarks on a Radial-Basis-Function-Network-Based Controller Derived from Neural-Network-Based Controller”. Proceedings of 3rd International Conference on Motion and Vibration Control Vol. 2, 86–91
Yamada T, Yasue N, Morimitsu T (1996) “Self-organization and basic functions of neural network controllers”. J Robot Mechatron 8:333–337
Yamada T, Yasume N, Morimitsu T (1996) “Remarks on Plant Expressions for Dynamic System Control Using Neural Network”. Proceedings of International Workshop on Soft Computing in Industry’96 IWSCI’96, pp 191–196
Yamada T (1997) “An Application of Radial Basis Function Derived from Neural Networks to Servo Control”. Proceedings of 5th European Congress on Intelligent Techniques & Soft Computing EUFIT’97, pp 2074–2078
Takahashi K, Yamada T (1997) “A radial-basis-function-network-based controller derived from neural-network-based controller and its application to controlling mechanical systems”. JSME Int J C 40:42–51
Takahashi K, Yamada T (1998) “Hybrid Learning of Direct Neural Controller Using Approximated Potential Function”. Proceedings of 1998 IEEE International Conference on Systems, Man, and Cybernetics, pp 1708–1713
Takahashi K, Yamada T (1998) “Application of an immune feedback mechanism to control systems”. JSME Int J C 41:184–191
Takahashi K, Yamada T, Sasaki M (1998) “A radial-basis-function-network-based controller with application to controlling a flexible micro-actuator”. Trans IEE Jpn E 118-E:14–21
Yamada T (2003) “Remarks on Connection Methods of Neural Network Controller Using Reference Model With Conventional Controller”. Proceedings of The Eighth Int. Sym. on Artificial Life and Robotics AROB8th ‘03, pp. 198–201
Yamada T (2007) “Remarks on adaptive type neural network direct controller with separate learning rule of each layer”. Proceeding of The Twelfth International Symposium on Artificial Life and Robotics AROB12th ‘06, GS21-5
Yamada T (2007) “Characteristic of adaptive type neural network direct controller with separate learning rule of each layer”. Proceeding of SICE Annual Conference 2007, sept17–20, kagawa University, Japan, pp 985–990
Yamada T (2008) “Remarks on feedback loop gain characteristics of adaptive type neural network feedforward feedback controller”. Proceeding of SICE Annual Conference 2008 Aug 20–22,University of Electro-Communications, Japan, pp 2244–2249
Yamada T (2008) “Remarks on tracking method of neural network weight change for adaptive type neural network feedforward feedback controller”. Artif Life Robot 13(1):286–289
Yamada T (2009) “Remarks on tracking method of neural network weight change for a learning-type neural network feedforward feedback controller”. Artif Life Robot 14(3):384–387
Yamada T (2010) “Transformation of neural network weight trajectories on a 2D plane for a learning-type neural network direct controller”. Artif Life Robot 15(4):413–416
Yamada T (2011) “Remarks on folding behavior of mapping capability of neural network direct controller for many-to-one plant”. Proceedings of AROB 16th ‘11 (The Sixteenth International Symposium on Artificial Life and Robotics 2011), pp 881–884
Yamada T (2011) “Discussion of neural network controllers from the point of view of inverse dynamics and folding Behavior”. Proceeding of SICE Annual Conference 2011 sept.13–18,Waseda University, Tokyo, Japan, pp 2210–2215
Yamada T (2012) “Discussion of stability of learning type neural network direct controller and its folding Behavior”. Proceeding of SICE Annual Conference 2012 August 20–23, Akita University, Akita, Japan, pp 459–464
Yamada T (2012) “Discussion of Stability of Adaptive Type Neural Network Direct Controller and Its Folding Behavior”. Proceedings of AROB 17th ‘12 (The Seventeenth International Symposium on Artificial Life and Robotics 2012), pp 1033–1036
Yamada T (2013) “3rd Order Function and Folding Behavior of Neural Network Direct Controller”. Proceeding of SICE Annual Conference 2013 September 14–17, Nagoya University, Nagoya, Japan, pp 1387–1392
Yamada T (2015) “Remarks on Adaptive Type Neural Network Self-Tuning Controller and Its Stability”. Proceeding of The Twentieth International Symposium on Artificial Life and Robotics 2015 (AROB 20th 2015), B-Con Plaza, Beppu, Japan, January 21–23, pp 434–437
Yamada T (2016) “Remarks on Folding Behavior and Plant Jacobian of Neural Network Direct Controller for Its Stability”. Proceeding of The Twenty-First International Symposium on Artificial Life and Robotics 2016 (AROB 21st 2016), B-Con Plaza, Beppu, Japan, January 20–22, pp 246–249
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was presented in part at the 21st International Symposium on Artificial Life and Robotics, Beppu, Oita, January 20–22, 2016.
About this article
Cite this article
Yamada, T. Remarks on folding behavior and plant Jacobian of neural network direct controller for its stability. Artif Life Robotics 22, 321–326 (2017). https://doi.org/10.1007/s10015-017-0358-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10015-017-0358-1