SCIENCE CHINA Information Sciences, Volume 63 , Issue 7 : 179201(2020) https://doi.org/10.1007/s11432-018-9514-9

Blocked WDD-FNN and applications in optical encoder error compensation

More info
  • ReceivedApr 27, 2018
  • AcceptedJun 29, 2018
  • PublishedOct 8, 2019


There is no abstract available for this article.


This work was supported by Beijing Nova Program (Grant No. xx2016B027).


[1] Cotton N J, Wilamowski B M. Compensation of sensors nonlinearity with neural networks. In: Proceedings of IEEE International Conference on Advanced Information Networking And Applications, Waina, 2010. 1210--1217. Google Scholar

[2] Radulescu A. Neural network spectral robustness under perturbations of the underlying graph. Neural Comput, 2016, 28: 1-44 CrossRef PubMed Google Scholar

[3] Deng F, Chen J, Wang Y Y. Measurement and calibration method for an optical encoder based on adaptive differential evolution-Fourier neural networks. Meas Sci Technol, 2013, 24: 055007 CrossRef ADS Google Scholar

[4] Wu B, Wu K, L\"{u} J H. A novel compensation-based recurrent fuzzy neural network and its learning algorithm. Sci China Ser F-Inf Sci, 2009, 52: 41-51 CrossRef Google Scholar

[5] Yan H H, Deng F, Sun J. An NN-based SRD decomposition algorithm and its application in nonlinear compensation. Sensors, 2014, 14: 17353-17375 CrossRef PubMed Google Scholar

  • Table 1   Experimental results ($^\circ$ is the unit of angle)
    MeanAbs MaxAbs STD Time (s)
    Pre-compensation0.5387$^\circ$ 1.4654$^\circ$ 0.4610$^\circ$
    LSE 0.3919$^\circ$ 0.9796$^\circ$ 0.4607$^\circ$ 0.27
    BP-net 0.0747$^\circ$ 0.2770$^\circ$ 0.0876$^\circ$ 44.00
    FNN 0.0732$^\circ$ 0.3281$^\circ$ 0.0864$^\circ$ 40.60
    WDD-FNN 0.0229$^\circ$ 0.1108$^\circ$ 0.0212$^\circ$ 1.57