Control- Relevant Neural Networks for Intelligent Motion Feedforward

Neural networks have large potential for motion feedforward because of their ability to approximate a wide range of functions. The aim of this paper is to develop a systematic framework for application of neural networks to motion feedforward, that leads to an intelligent motion feedforward approach in the sense that it achieves both flexibility for varying references and high performance. Iterative learning control is used to generate training data, and a control-relevant performance function is introduced. Non-causal feedforward is enabled through two network configurations that enable respectively finite and infinite preview. The approach is experimentally validated on an industrial flatbed printer.

[1]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition , 2012 .

[2]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[3]  Cristian R. Rojas,et al.  Sparse Iterative Learning Control with Application to a Wafer Stage: Achieving Performance, Resource Efficiency, and Task Flexibility , 2017, ArXiv.

[4]  O. Sørensen,et al.  Additive Feed Forward Control with Neural Networks , 1999 .

[5]  Pieter Abbeel,et al.  Learning for control from multiple demonstrations , 2008, ICML '08.

[6]  Tae Tom Oomen,et al.  On inversion-based approaches for feedforward and ILC , 2017 .

[7]  Theodorus J.A. de Vries,et al.  Linear motor motion control using a learning feedworward controller , 1997 .

[8]  F. Lewis,et al.  Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers , 2012, IEEE Control Systems.

[9]  Frank Boeren,et al.  Frequency-Domain ILC Approach for Repeating and Varying Tasks: With Application to Semiconductor Bonding Equipment , 2016, IEEE/ASME Transactions on Mechatronics.

[10]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[11]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[12]  Tom Oomen.  Learning for Advanced Motion Control , 2020, 2020 IEEE 16th International Workshop on Advanced Motion Control (AMC).

[13]  M Maarten Steinbuch,et al.  Using iterative learning control with basis functions to compensate medium deformation in a wide-format inkjet printer , 2014 .

[14]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[15]  Thomas B. Schön,et al.  Deep Learning and System Identification , 2020, IFAC-PapersOnLine.

[16]  A.G. Alleyne,et al.  A survey of iterative learning control , 2006, IEEE Control Systems.

[17]  Lennart Blanken,et al.  Batch-to-Batch Rational Feedforward Control: From Iterative Learning to Identification Approaches, With Application to a Wafer Stage , 2017, IEEE/ASME Transactions on Mechatronics.

[18]  Richard D. Braatz,et al.  On the "Identification and control of dynamical systems using neural networks" , 1997, IEEE Trans. Neural Networks.

[19]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..

[20]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[21]  Tom Oomen,et al.  Control for Precision Mechatronics , 2019, Encyclopedia of Systems and Control.

[22]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[23]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.