Neural network controller for nanopositioning of a smooth impact drive mechanism

  In this paper, neural network theory is used to improve the positioning accuracy of smooth impact drive mechanisms (SIDMs), by designing a displacement controller that consists of a neural network identification (NNI) and a neural network controller (NNC). The dynamics of the SIDM are described by the NNI, which consists of an input layer, hidden layer, and output layer. The parameters of the NNI are adjusted using back propagation. The NNC is designed as a proportional-derivative (PD) controller, which is used to accurately control the displacement of the SIDM. The PD parameters are adjusted with an adaptive adjustment algorithm. A prototype of the SIDM was fabricated and an experimental control system was built that consists of a laser displacement sensor, power amplifier, data acquisition board, and SIDM prototype. The experimental results show that nanoscale positioning accuracy can be obtained. The control system can maintain steady operation, even if the output load mass is changed.

___

  • Li JP, Zhou XQ, Zhao HW, Shao MK, Fan ZQ, Liu H. Design and experimental tests of a dual-servo piezoelectric nanopositioning stage for rotary motion. Rev Sci Instrum 2015; 86: 045002.
  • Yong YK, Moheimani SOR, Kenton BJ, Leang KK. Invited Review Article: High-speed flexure-guided nanoposi- tioning: mechanical design and control issues. Rev Sci Instrum 2012; 83: 121101.
  • Tian Y, Zhang D, Shirinzadeh B. Dynamic modeling of a flexure-based mechanism for ultra-precision grinding operation. Prec Eng 2011; 35: 554-565.
  • Nakamura K, Kurosawa M, Ueha S. Design of a hybrid transducer type ultrasonic motor. IEEE T Ultrason Ferr 1993; 40: 395-401.
  • Lee J, Kwon WS, Kim KS, Kim S. A novel smooth impact drive mechanism actuation method with dual-slider for a compact zoom lens system. Rev Sci Instrum 2011; 82: 085105.
  • Zeng P, Sun SJ, Li LA, Xu F, Cheng GM. Design and testing of a novel piezoelectric micro-motor actuated by asymmetrical inertial impact driving principle. Rev Sci Instrum 2014; 85: 035002.
  • Hii KF, Vallance RR, Mengüç MP. Design, operation, and motion characteristics of a precise piezoelectric linear motor. Prec Eng 2010; 34: 231-241.
  • Zhao G, Alujević N, Depraetere B, Pinte G, Swevers J, Sas P. Experimental study on active structural acoustic control of rotating machinery using rotating piezo-based inertial actuators. J Sound Vib 2015; 348: 15-30.
  • Hunstig M, Hemsel T, Sextro W. Stick–slip and slip–slip operation of piezoelectric inertia drives. Part I: Ideal excitation. Sens Actuators A 2013; 200: 90-100.
  • Nishimura T, Hosaka H, Morita T. Resonant-type smooth impact drive mechanism (SIDM) actuator using a bolt- clamped Langevin transducer. Ultrasonics 2012; 52: 75-80.
  • Yokose T, Hosaka H, Yoshida R, Morita T. Resonance frequency ratio control with an additional inductor for a miniaturized resonant-type SIDM actuator Sens Actuators A 2014; 214: 142-148.
  • Suzuki M, Hosaka H, Morita T. Resonant-type smooth impact drive mechanism actuator with two Langevin transducers. Adv Robotics 2012; 26: 277-290.
  • Morita T, Nishimura T, Yoshida R, Hosaka H. Resonant-type smooth impact drive mechanism actuator operating at lower input voltages. Japan J Appl Phys 2013; 52: 1044-1055.
  • Yang S, Li C, Huang T. Exponential stabilization and synchronization for fuzzy model of memristive neural networks by periodically intermittent control. Neural Netw 2016; 75: 162-172.
  • Canudas de Wit C, Olsson H, Astrom KJ, Lischinsky P. A new model for control of systems with friction. IEEE T Automat Contr 1995; 40: 419-425.
  • Dupont P, Hayward V, Armstrong B, Altpeter F. Single state elastoplastic friction models. IEEE T Automat Contr 2002; 47: 787-792.
  • Akbulut A, Öztaş O. Control in networked systems with fuzzy logic. Turk J Elec Eng & Comp Sci 2013; 21: 225-233.
  • Hoskins DA, Hwang JN, Vagners J. Iterative inversion of neural networks and its application to adaptive control. IEEE T Neural Netw 1992; 3: 292-301.
  • Key JW. Part 1: Neural networks in process control. Control Eng 2016; 63: 1-8.