Steel Science Portal

Transactions of the Institute of Systems, Control and Information Engineers
New Arrival Alert : OFF

You can use this feature after you logged into the site.
Please click the button below.

Log in / Sign up
ONLINE ISSN: 2185-811X
PRINT ISSN: 1342-5668

Transactions of the Institute of Systems, Control and Information Engineers Vol. 27 (2014), No. 8

  • Proposal of New Reinforcement Learning with a State-independent Policy

    Daichi Nakano, Shin-ichi Maeda, Shin Ishii

    pp. 327-332

    Bookmark

    You can use this feature after you logged into the site.
    Please click the button below.

    Log in / Sign Up

    DOI:10.5687/iscie.27.327

    Abstract

    Usually, reinforcement learning (RL) algorithms have a difficulty to learn the optimal control policy as the dimensionality of the state (and action) becomes large, because of the explosive increase in the search space to optimize. To avoid such an unfavorable explosive increase, in this study, we propose BASLEM algorithm (Blind Action Sequence Learning with EM algorithm) which acquires a state-independent and time-dependent control policy starting from a certain fixed initial state. Numerical simulation to control a non-holonomic system shows that RL of state-independent and time-dependent policies attain great improvement in efficiency over the existing RL algorithm.

  • Tuning of Nonlinear Model Predictive Controller for Parameter-Dependent Systems and its Application to the Speed Control of Spark Ignition Engines

    Fatima Tahir, Toshiyuki Ohtsuka

    pp. 333-342

    Bookmark

    You can use this feature after you logged into the site.
    Please click the button below.

    Log in / Sign Up

    DOI:10.5687/iscie.27.333

    Abstract

    In this paper, we propose a systematic method for the efficient tuning of the performance index in Nonlinear Model Predictive Control (NMPC) of parameter-dependent systems. The quadratic cost function in NMPC is tuned by applying the inverse optimality conditions on the linear quadratic regulator designed for the linearized model using the Inverse Linear Quadratic (ILQ) regulator design method. This approach provides some tuning parameters that give a trade-offbetween the speed of the system’s response and the magnitude of the control input. We propose two systematic methods for the selection of parameter-dependent tuning parameter. This approach is applied to the speed control of mean-value model of Spark Ignition (SI) engines. Effectiveness of the proposed methods is elaborated in simulation results.

  • The Observable Formed Delta Operator Model to Simplify the Identification

    Kazuyuki Iwamoto, Noriyoshi Kumazawa, Hiroyuki Ichihara, Naoto Abe, Yasuyoshi Fukui

    pp. 343-351

    Bookmark

    You can use this feature after you logged into the site.
    Please click the button below.

    Log in / Sign Up

    DOI:10.5687/iscie.27.343

    Abstract

    A delta operator model is usually applied to identification problems with short sampling periods. To identify the system, we have to compute the difference of the input and output data in discrete time and design a noise filter. In this paper, we propose the delta operator model with the observable canonical form. By using this model, we can easily estimate the parameters of the delta operator model without the difference of the input and output data. We derive the Cramer Rao inequality, which evaluates the performance for estimating parameters in the proposed model. Finally, we show the results of the identification experiments for an inertia rotor pendulum and a nonminimum phase system.
  • © 2014 THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE)

Article Access Ranking

22 Sep. (Last 30 Days)

  1. Formation and Evolution of Inclusions in High Chromium Steel ISIJ International Vol.61(2021), No.9
  2. Perspective toward Long-term Global Goal for Carbon Dioxide Mitigation in Steel Industry Tetsu-to-Hagané Vol.105(2019), No.6
  3. Preface to the Special Issue on “Recent Progress in Inclusion/ Precipitate Engineering” ISIJ International Vol.61(2021), No.9
  4. Effect of Heating Rate on Carbothermic Reduction and Melting Behavior of Iron Ore-Coal Composite Pellets ISIJ International Advance Publication
  5. Evaluation of Interfacial Energy between Molten Fe and Fe-18%Cr-9%Ni Alloy and Non-Metallic Inclusion-Type Oxides ISIJ International Vol.61(2021), No.9
  6. Modeling of Wall Shear Stress Induced Inclusion Transport and Removal in Multi-Strand Tundish ISIJ International Vol.61(2021), No.9
  7. Three-dimensional Quantitative Evaluation of the Lamellar Curvature in Pearlitic Steel Based on an Orientation Analysis of Cementite ISIJ International Advance Publication
  8. Production and Technology of Iron and Steel in Japan during 2020 ISIJ International Vol.61(2021), No.6
  9. Analysis of Air-Mist Cooling Effect for Coil in the Electromagnetic Induction Controlled Automated Steel Teeming System ISIJ International Vol.61(2021), No.9
  10. Simultaneous Analysis of Soluble and Insoluble Oxygen Contents in Steel Specimens Using Inert Gas Fusion Infrared Absorptiometry ISIJ International Vol.61(2021), No.9

Search Phrase Ranking

22 Sep. (Last 30 Days)

  1. blast furnace
  2. inconel 600
  3. blast furnace productivity
  4. miyamoto goro
  5. nozzle clogging
  6. b2o3 mold flux
  7. blue carbon
  8. investigation of arc behavior and temperature distribution corresponding to electrode and phase configurations in a multiphase ac arc
  9. ohno
  10. sei kimura