IEEJ Transactions on Electronics, Information and Systems
Online ISSN : 1348-8155
Print ISSN : 0385-4221
ISSN-L : 0385-4221
Volume 143, Issue 2
Displaying 1-17 of 17 articles from this issue
Special Issue on “AI and IoT Technology Application to the Field of Energy”
Preface
Special Issue Review
  • Yoshikazu Fukuyama
    2023 Volume 143 Issue 2 Pages 104-107
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    Recently, many countries focus on achieving carbon neutral by 2050, and researches on optimal operation of energy plants in factories and large commercial buildings have been conducted for energy saving and reduction of CO2 emissions. Since the optimal operation problem of energy plants can be formulated as a mixed integer nonlinear optimization problem, evolutionary computation techniques, which is one of artificial intelligence (AI) techniques, have been applied. On the other hand, in energy facilities, when AI techniques are required, the Least Squares Method (LSM) has been applied in various problems. One of the main purposes to apply the LSM is to solve the problems only using measured data without experts' knowledge. However, in practical fields, outliers may be included in the measured data because of setting errors of sensors, radio interference, and so on. When LSM is applied with the outliers, inappropriate results may be obtained. Maximum Correntropy Criterion (MCC) is one of the technology trends to tackle the challenge. This paper reviews researches on applications of evolutionary computation techniques to optimal operation of energy plants and presents applications of MCC with AI techniques to energy problems.

    Download PDF (870K)
Special Issue Paper
<Systems, Instrument, Control>
  • Ichiro Kosaka, Shota Tanaka, Ryota Sawamura, Shoichi Kitamura
    2023 Volume 143 Issue 2 Pages 108-116
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    This paper presents an optimal operating method for the boiler, turbine and generator considering the start-up and shut-down power trajectories by a mixed integer linear programming problem. A boiler, turbine and generator unit commitment problem is a planning start stop states and inputs and outputs of boilers and steam turbines to minimize the total energy cost. In most of the conventional methods, the start-up and shut-down power trajectories have not been considered for the sake of simplification of calculation, etc. This optimal operating method for the boiler, turbine and generator can consider them by introducing a new set of binary variables and constrains which are operation mode discrimination constraints and power trajectory constraints.

    Download PDF (638K)
  • Kazuhiro Yasunami
    2023 Volume 143 Issue 2 Pages 117-124
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    There is a growing need to use photovoltaic (PV) technology to mitigate global warming and the depletion of fossil fuels while also enhancing energy security. However, the high network penetration of PVs has various negative effects on electrical power systems. In recent years, automated operating systems have been introduced to enable rapid and automatic restoration after a power outage. However, PVs shut down in the case of a power outage and are not automatically restored. Therefore, it is necessary to compensate the electric power output of the PVs by using an extra power supply at the time of power recovery. For this compensation process, it is necessary for a system operator to monitor the unmeasurable power output of the PVs, including those belonging to other organizations and individuals, to ensure that the automated operating system is used properly. Based on these aspects, in this paper, we proposed an estimation method of PVs power output utilizing integral power consumption data obtained from smart meters and solar radiation intensity, and demonstrated the accuracy of the proposed method using measured data.

    Download PDF (4342K)
  • Rikuto Miwa, Hiroyuki Mori
    2023 Volume 143 Issue 2 Pages 125-132
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    This paper proposes a new method for one-step ahead electricity price forecasting. It is based on GRBFN (Generalized Radial Basis Function Network) that is an extension of RBFN of Artificial Neural Network (ANN). GRBFN has advantage over RBFN that the Gaussian function parameters are evaluated by the learning process. The conventional ANN methods consider overfitting with the weight decay method that corresponds to the L2 norm of weights between neurons, but there is still room for improvement. According to the idea of the sparse modeling, this paper proposes the use of Least Absolute Shrinkage and Selection Operator (LASSO) to improve the model performance. Also, this paper presents BSO of evolutionary computation to evaluate the cost function with the term of the L1 norm. That is because the conventional methods with the gradient do not work for the L1 norm. The proposed method is successfully applied to real data of ISO New England in USA.

    Download PDF (661K)
<Intelligence, Robotics>
  • Eriko Sato, Satoshi Yamaguchi, Takashi Kusuda
    2023 Volume 143 Issue 2 Pages 133-140
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    Recently, as it occurs flood disasters due to climate change, it is important to operate dams. Especially, for hydroelectrical power plants of the dams, it is also necessary to predict the discharge to the dams appropriately at the phase of during usual and flood water for managing power generation and preparing for flood. However, conventional methods to predict the discharge have been developed at each phase of usual and flood water separately. In this report, we developed a hybrid-discharge-prediction model, which is composed by a state discriminator and discharge prediction models with machine learning and a flood simulator. This hybrid-discharge-prediction model can detect the state of discharge and adopt an appropriate discharge prediction model each state of discharge and prediction time. As a result, it was shown that the hybrid-discharge-prediction model can detect 7 states and predict the discharge to the dam in 5 hours at the phase from usual to flood water.

    Download PDF (1511K)
<Information Processing, Software>
  • Toshiharu Igarashi, Toshihiro Kobayashi, Misato Nihei
    2023 Volume 143 Issue 2 Pages 141-150
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    Text input, which is essential for a variety of applications, is one of the most difficult operations for older people. So, we propose a prototype to automatically detect and input text from a natural image taken from a user's smartphone. For the evaluation of the system, 232 photo data taken by the actual people were prepared. When all data was processed on the server, the average processing time was less than 10 seconds, and the overall recognition rate was over 94%. For user study, 20 healthy elderly people aged 65 years or older were collected. And, after conducting a simulation with the conventional typing system, the prototype in this proposal was asked to be used. The time required to complete each work was recorded, and the usability was evaluated using System Usability Scale (SUS).

    As a result, both the healthy older group and the MCI older group tended to shorten the task execution times and increase their SUS scores by using our application, compared to the conventional method. Also, comparing the SUS score with other Web applications, it is considered that usability is high as a prototype.

    Download PDF (2058K)
  • Daiki Kiribuchi, Takufumi Yoshida, Fuko Okayama, Kana Konno, Takumi Ma ...
    2023 Volume 143 Issue 2 Pages 151-158
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    To improve the efficiency of wind power plants, multiple wind turbines must be placed in a way that generates a large amount of power while satisfying various constraints. For complex terrain such as mountainous regions in Japan, long simulation runs are required in order to calculate how much power is generated and determine whether the constraints are satisfied. Consequently, the manual processes and conventional simulation methods for deciding wind farm layouts are time-consuming. To automate and accelerate the process of wind farm placement, we propose a simulation-based optimization method for wind farm layout. In this method, simulation data are used to construct a prediction model, based on which the wind farm layout is then obtained by the optimization method. We conducted numerical experiments to evaluate our method and confirmed that it could find a wind farm layout that satisfied all given constraints and increased power generation by more than 30%, whereas the manual method could not find a layout that satisfied all the constraints in the same amount of time.

    Download PDF (1570K)
Paper
<Electronic Materials and Devices>
  • Haruki Goto, Akira Hiroki
    2023 Volume 143 Issue 2 Pages 159-164
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    In this study, we have analyzed the Id-Vg characteristics of In0.53Ga0.47As n-MOSFETs using a quantum drift-diffusion (QDD) model with Fermi-Dirac (FD) distribution. In0.53Ga0.47As is a material with a smaller energy band gap than that of Si. The Id-Vg characteristics using FD distribution are compared with that using Maxwell-Boltzmann (MB) distribution. The difference of the characteristics between FD and MB distributions is observed as the applied gate voltage is increased. To investigate the difference, we have evaluated the electron density distributions and electrostatic potentials. We have calculated the energy difference between the bottom of the conduction band and the Fermi level derived from the electrostatic potential. It is found that the energy difference becomes smaller as the gate voltage is increased. The energy difference affects the difference in the Id-Vg characteristics. We have clarified that the relationship between the energy band gap and quantum confinement effects. It is found that it is necessary for the device simulation model using FD distribution to simulate MOSFETs with semiconductor materials with a smaller energy band gap.

    Download PDF (494K)
<Electrical and Electronic Circuit, LSI>
  • Shimon Hattori, Osamu Matoba, Yusuke Kawakami, Toshiki Tanaka, Tetsuo ...
    2023 Volume 143 Issue 2 Pages 165-171
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    In 1989, B.J. Van Zeghbroeck et al., who was working for IBM Research Center at that time, announced the notion of PTT (Photon Transport Transistor) as an optical coupling device of light emitting diode (LED) and light receiving diode (Photo Diode, PD), where the carrier of the base layer is light (Photon) only. Later, it was theoretically shown that PTT has an amplification function in a positive feedback circuit and works as an extremely low-noise transistor element. In this paper, based on the characteristics of the electronic circuit including the LED and PD, we discuss the expression of the amplification function of the PTT positive feedback circuit. First, we theoretically formulate the fundamental equations for the circuit based on Kirchhoff’s Law and V-I characteristics of LED and PD. Second, we perform the actual circuit operation experiments of PTT positive feedback circuit. Lastly, we analyze the expression of amplification function and its operational behavior based on the measured values in the experiments, using approximated characteristic equations of LED and PD.

    Download PDF (1401K)
<Biomedical Engineering>
  • Ryosuke Nakamura, Kent Nagumo, Kosuke Oiwa, Akio Nozawa
    2023 Volume 143 Issue 2 Pages 172-177
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    Facial skin temperature can be measured remotely with an infrared thermography camera to evaluate the physiological and psychological state of a person. To extract specific patterns, a method for analyzing skin temperature distributions that are independent of time series changes is required. Therefore, we applied sparse coding to the facial thermal images. In this study, we attempted to estimate hemodynamics based on the features obtained by applying sparse coding.

    Download PDF (1576K)
<Systems, Instrument, Control>
  • Mayu Ito, Gaochao Cui, Fumiya Kinoshita, Hideaki Touyama
    2023 Volume 143 Issue 2 Pages 178-184
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    In recent years, with the advent of wearable EEG devices, brain-computer interface (BCI) has become popular not only in the medical field but also for general use. Conventional wearable EEG devices are mainly worn on the head, which induces discomfort when worn for a long time and is unattractive. The area around the ear can be considered as a measurement site that solves these problems and is easy to wear. However, there is still little knowledge about EEG around the ear, and the appropriate measurement site has not been determined. In this study, we investigated the optimal electrode placement and EEG recording method around the right ear for steady-state visual evoked potential (SSVEP), which has a high signal-to-noise ratio among EEGs used in BCI. Electrodes were attached to Pz, Oz, and eight locations around the right ear, and measurements were performed using unipolar and bipolar leads. The cross-correlation coefficients between Pz, Oz, and the electrodes around the right ear were calculated, and two locations with particularly high values were identified. In addition, by calculating the EEG data combination from multiple channels around right ear, some channel combinations were found which can significantly improve the discrimination accuracy of BCI system.

    Download PDF (1138K)
  • Toshiki Tanaka, Tetsuo Hattori, Yusuke Kawakami, Yo Horikawa, Yoshiro ...
    2023 Volume 143 Issue 2 Pages 185-191
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    We propose a novel and simple estimation method of parameters that appear in the impulse response of compartment model, using cumulative function and Linear Regression Analysis, taking the case of PET (Positron Emission Tomography) inspection for example. In PET inspection, the parameters estimation is a very important for the analysis of dynamic function and the presence of cancer, etc. Since the important parameters to be estimated are intricately included in the exponent part of exponential function in impulse response of the compartment model, the Conjugate Gradient Method (CGM), and the extended Newton one, etc., are normally used. However, there is a problem that these iterative computation methods do not converge or take much time, depending on the initial values of those parameters. In this paper, we present an alternative method that does not need to set the initial values of parameters in computing. This paper also shows that the proposed method works well, illustrating the experimental results in comparison with the CGM.

    Download PDF (944K)
  • Motoya Suzuki, Shuichi Yahagi
    2023 Volume 143 Issue 2 Pages 192-200
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    For realizing desired control performances, data-driven tunings called as Fictitious reference iterative tuning (FRIT) were proposed. If FRIT can be applied to vehicle yaw-rate control of autonomous driving, the desired control performance can be realized. However, the conventional FRIT may not realize desired control performances because of slip-angle properties. To solve this problem, we extend FRIT method so as to cancel influence of the vehicle slip-angle. The validity of proposed method is verified through multi-body vehicle simulator.

    Download PDF (668K)
  • Motoya Suzuki
    2023 Volume 143 Issue 2 Pages 201-208
    Published: February 01, 2023
    Released on J-STAGE: February 01, 2023
    JOURNAL RESTRICTED ACCESS

    Input-oriented virtual internal model tuning can tune the feedback controller by using one-shot experiment data This method can realize desired closed-loop responses when the orders of numerator and denominator of the feedback controller is adequate. However, it is difficult to determine the orders of numerator and denominator of the feedback controller when the controlled object is unknown. From this reason, input-oriented virtual internal model tuning is expanded to non-parametric controllers. Proposed methods can obtain the feedback controller which is parametrized by the impulse response of the controlled object. The impulse response is estimated by Ridge regression. The proposed method can realize good controllers because over-learning is not occurred by Ridge regression. The validity of the proposed method is verified via numerical simulation and experiment verification. From verification results, the input-oriented VIMT based on least square methods can not realize desired closed-loop response because of over-learning. Proposed method can realize desired control response even when the controlled object is unknown.

    Download PDF (834K)
 
 
feedback
Top