Machine learning-based method for linearization and error compensation of a novel absolute rotary encoder

Abstract The main objective of this work is to develop a miniaturized, high accuracy, single-turn absolute, rotary encoder called ASTRAS360. Its measurement principle is based on capturing an image that uniquely identifies the rotation angle. To evaluate this angle, the image first has to be classified into its sector based on its color, and only then can the angle be regressed. Inspired by machine learning, we built a calibration setup, able to generate labeled training data automatically. We used these training data to test, characterize, and compare several machine learning algorithms for the classification and the regression. In an additional experiment, we also characterized the tolerance of our rotary encoder to eccentric mounting. Our findings demonstrate that various algorithms can perform these tasks with high accuracy and reliability; furthermore, providing extra-inputs (e.g. rotation direction) allows the machine learning algorithms to compensate for the mechanical imperfections of the rotary encoder.

[1]  Zhu Ge,et al.  An absolute displacement measurement method of simple graphic decimal shift encoding , 2020 .

[2]  Hai Yu,et al.  Small-sized visual angular displacement measurement technology , 2019, Measurement.

[3]  Min Fu,et al.  An absolute displacement measurement method of simple graphic decimal shift encoding , 2020, International Conference on Optical Instruments and Technology.

[4]  Resat Celikel,et al.  ANN based angle tracking technique for shaft resolver , 2019 .

[5]  P. Cattin,et al.  Clinical applicability of robot-guided contact-free laser osteotomy in cranio-maxillo-facial surgery: in-vitro simulation and in-vivo surgery in minipig mandibles. , 2015, The British journal of oral & maxillofacial surgery.

[6]  Pengfei Yuan,et al.  An improved high-precision subdivision algorithm for single-track absolute encoder using machine vision techniques , 2019, Measurement and Control.

[7]  Donald H. Breslow.  Installation And Maintenance Of High Resolution Optical Shaft Encoders , 1978, Other Conferences.

[8]  Andrew J. Fleming,et al.  A review of nanometer resolution position sensors: Operation and performance , 2013 .

[9]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[10]  Danna Zhou,et al.  d. , 1840, Microbial pathogenesis.

[11]  Andriy Burkov,et al.  The Hundred-Page Machine Learning Book , 2019 .

[12]  Shakeb A Khan,et al.  Sensor calibration and compensation using artificial neural network. , 2003, ISA transactions.

[13]  Sami Sikilae.  The positioning system and method , 2000 .

[14]  Michel Dard,et al.  A comparative investigation of bone surface after cutting with mechanical tools and Er:YAG laser , 2015, Lasers in surgery and medicine.

[15]  Philippe C. Cattin,et al.  Proof of principle of a novel angular sensor concept for tracking systems , 2018, Sensors and Actuators A: Physical.

[16]  Domenico Accardo,et al.  MEMS gyros temperature calibration through artificial neural networks , 2018, Sensors and Actuators A: Physical.

[17]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[18]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[19]  V. K. Dhar,et al.  Artificial neural network-based error compensation procedure for low-cost encoders , 2009, ArXiv.

[20]  Huseyin Atakan Varol,et al.  Sensors for Robotic Hands: A Survey of State of the Art , 2015, IEEE Access.

[21]  Giuseppe Bonaccorso,et al.  Machine Learning Algorithms , 2018, Optimization Techniques and Applications with Examples.

[22]  Azhar Zam,et al.  Preliminary Tests of the Miniaturization of a Novel Concept of Angular Sensors , 2019, 2019 IEEE SENSORS.

[23]  Tarikul Islam,et al.  Linearization of the sensors characteristics: a review , 2019, International Journal on Smart Sensing and Intelligent Systems.

[24]  Jae Wan Kim,et al.  Absolute Planar Position and Full Angle Orientation Sensor Using a 2-D Color-Coded Binary Scale , 2020, IEEE Transactions on Instrumentation and Measurement.

[25]  Kayoko Taniguchi,et al.  An angle encoder for super-high resolution and super-high accuracy using SelfA , 2014 .

[26]  Wilhelm Burger,et al.  Digital Image Processing - An Algorithmic Introduction using Java , 2008, Texts in Computer Science.

[27]  Philippe C. Cattin,et al.  Proof of concept of a novel absolute rotary encoder , 2020, Sensors and Actuators A: Physical.

[28]  Goutam Chakraborty,et al.  Neural-Network-Based Robust Linearization and Compensation Technique for Sensors Under Nonlinear Environmental Influences , 2008, IEEE Transactions on Circuits and Systems I: Regular Papers.

[29]  Siti Anom Ahmad,et al.  Self-Calibration Algorithm for a Pressure Sensor with a Real-Time Approach Based on an Artificial Neural Network , 2018, Sensors.