Open Access Open Access  Restricted Access Subscription Access

Identification of Real-Time Maglev Plant using Long-Short Term Memory Network based Deep Learning Technique


Affiliations
1 Department of EEE, Centurion University of Technology and Management, Odisha, India
2 Department of EEE, Birla Institute of Technology, Mesra, Ranchi, India
3 Department of ECE, Birla Institute of Technology, Mesra, Ranchi, India
 

Deep neural network has emerged as one of the most effective networks for modeling of highly non-linear complex real-time systems. The long-short term memory network (LSTM) which is a one of the variants of recurrent neural network (RNN) has been proposed for the identification of a highly nonlinear Maglev plant. The comparative analysis of its performance is carried out with the functional link artificial neural network- least mean square (FLANN-LMS), FLANN-particle swarm optimization (FLANN-PSO), FLANN-teaching learning based optimization (FLANN-TLBO) and FLANN-black widow optimization (FLANN-BWO) algorithm. The proposed LSTM model is a feed forward neural network trained by a simple iterative method called the ADAM algorithm. The obtained results indicate that the proposed network has better performance than the other competitive networks in terms of the MSE, CPU time and convergence rate. To validate the dominance of the proposed network, a statistical tests, i.e. the Friedman test, is also applied.

Keywords

FLANN, Maglev System, Mean Square Error, Recurrent Neural Network, System Identification.
User
Notifications
Font Size

  • Narendra K S & Parthasarathy K, Identification and control of dynamical systems using neural networks, IEEE Trans Neural Networks, 1 (1990) 4–26.
  • Majhi L, Borah M & Roy P, A new method for power system load modeling using a nonlinear system identification estimator, IEEE Int Conf Adv Commun Control Comput Technol, 61 (2016) 1–6.
  • Dhanalakshmi R, Vadivel A, Chandrasekaran R M & Parthiban P, Nature inspired heuristic approach to balance the resource in the multiple distribution centers, J Sci Ind Res, 74 (2015) 77–81.
  • Majhi B & Panda G, Robust identification of nonlinear complex systems using low complexity ANN and particle swarm optimization technique, Expert Syst Appl, 38 (2011) 321–333.
  • Rao R V, Savsani V J & Balic J, Teaching-learning-based optimization algorithm for unconstrained and constrained real-parameter optimization problems, Eng Optim, 44 (2012) 1447–1462.
  • Niranjan T & Parthiban P, Modelling and analysing an integrated multi channel food supply chain distribution of an indian dairy firm using modified TLBO algorithm, J Sci Ind Res, 78 (2019) 31–34.
  • Mallikarjuna B R, Viswanathan & Naib B B, Feedbackbased gait identification using deep neural network classification, J Crit Rev, 7 (2020) 661–667.
  • Wan H, Guo S, Yin K, Liang X & Lin Y, CTS-LSTM: LSTM-based neural networks for correlatedtime series prediction, Knowl-Based Syst, (in press)(2020).
  • Subudhi B & Jena D, Nonlinear system identification using memetic differential evolution trained neural networks, Neurocomputing, 74 (2011) 1696–1709.
  • Satapathy S & Naik A, Improved teaching learning based optimization for global function optimization, Decis Sci Lett, 2 (2013) 23–34.
  • Kumar M, Kulkarni A J & Satapathy S C, Socio evolution & learning optimization algorithm: A socio-inspired optimization methodology, Future Gener Comput Syst, 81 (2018) 252–272.
  • Hayyolalam V & Kazem A A P, Black widow optimization algorithm: A novel meta-heuristic approach for solving engineering optimization problems, Eng Appl Artif Intel, 87 (2020) 103249.
  • Ogunmolu O, Gu X, Jiang S & Gans N, Nonlinear systems identification using deep dynamic neural networks, 2016.
  • Sakinah N, Tahir M, Badriyah T & Syarif I, LSTM with adam optimization-powered high accuracy preeclampsia classification, Int Electron Symp, (2019) 314–319.
  • Sain D, Swain S K & Mishra S K, Real time implementation of optimized i-pd controller for the magnetic levitation system using jaya algorithm, IFAC-Papers On Line, 51 (2018) 106–111.
  • Gonzalez J & Yu W, Non-linear system modeling using LSTM neural networks, IFAC-Papers On Line, 51 (2018) 485–489.
  • www.medium.com (11 June 2020)

Abstract Views: 9

PDF Views: 2




  • Identification of Real-Time Maglev Plant using Long-Short Term Memory Network based Deep Learning Technique

Abstract Views: 9  |  PDF Views: 2

Authors

Amit Kumar Sahoo
Department of EEE, Centurion University of Technology and Management, Odisha, India
Rudra Narayan Pandey
Department of EEE, Birla Institute of Technology, Mesra, Ranchi, India
Sudhansu Kumar Mishra
Department of EEE, Birla Institute of Technology, Mesra, Ranchi, India
Prajna Parimita Dash
Department of ECE, Birla Institute of Technology, Mesra, Ranchi, India

Abstract


Deep neural network has emerged as one of the most effective networks for modeling of highly non-linear complex real-time systems. The long-short term memory network (LSTM) which is a one of the variants of recurrent neural network (RNN) has been proposed for the identification of a highly nonlinear Maglev plant. The comparative analysis of its performance is carried out with the functional link artificial neural network- least mean square (FLANN-LMS), FLANN-particle swarm optimization (FLANN-PSO), FLANN-teaching learning based optimization (FLANN-TLBO) and FLANN-black widow optimization (FLANN-BWO) algorithm. The proposed LSTM model is a feed forward neural network trained by a simple iterative method called the ADAM algorithm. The obtained results indicate that the proposed network has better performance than the other competitive networks in terms of the MSE, CPU time and convergence rate. To validate the dominance of the proposed network, a statistical tests, i.e. the Friedman test, is also applied.

Keywords


FLANN, Maglev System, Mean Square Error, Recurrent Neural Network, System Identification.

References