Prediction model to design standard production period for steel plate mills

Masanori Shioya, Kenko Uchida

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Steel plate products are manufactured through many refining processes. Among the refining processes, there are some processes where it is determined during the production whether the plates need to go through, and the uncertainty of the production period and the workload derived by these processes make the production control of the steel plate difficult. In this paper, we propose a method to predict the standard production period that is especially important for the production control. Since black-box models are avoided in the production field, we contrived a model which first predicts the process flow of the refining processes by decision trees and then predicts the probability density function for the production period by adding up the processing periods of the transit processes. These probability density functions for the processing periods are calculated by means of a maximum likelihood estimation under normal distribution assumption, but it was found that the values of the standard production period were not as much different as those under exponential distribution assumption. Moreover, although it does not satisfy the requirements of the production field, we found that the average of the standard production periods improved 0.7 days using quantile regression forest predicting the standard production period directly.

    Original languageEnglish
    Title of host publication2017 3rd International Conference on Control, Automation and Robotics, ICCAR 2017
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages346-351
    Number of pages6
    ISBN (Electronic)9781509060870
    DOIs
    Publication statusPublished - 2017 Jun 7
    Event3rd International Conference on Control, Automation and Robotics, ICCAR 2017 - Nagoya, Japan
    Duration: 2017 Apr 222017 Apr 24

    Other

    Other3rd International Conference on Control, Automation and Robotics, ICCAR 2017
    CountryJapan
    CityNagoya
    Period17/4/2217/4/24

    Fingerprint

    Prediction Model
    Steel
    Refining
    Production Control
    Production control
    Predict
    Probability density function
    Design
    Standards
    Quantile Regression
    Maximum likelihood estimation
    Normal distribution
    Decision trees
    Processing
    Black Box
    Exponential distribution
    Maximum Likelihood Estimation
    Decision tree
    Workload
    Gaussian distribution

    Keywords

    • Decision tree
    • Maximum likelihood estimation
    • Prediction model
    • Production control
    • Production period

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Control and Optimization
    • Control and Systems Engineering

    Cite this

    Shioya, M., & Uchida, K. (2017). Prediction model to design standard production period for steel plate mills. In 2017 3rd International Conference on Control, Automation and Robotics, ICCAR 2017 (pp. 346-351). [7942716] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCAR.2017.7942716

    Prediction model to design standard production period for steel plate mills. / Shioya, Masanori; Uchida, Kenko.

    2017 3rd International Conference on Control, Automation and Robotics, ICCAR 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 346-351 7942716.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Shioya, M & Uchida, K 2017, Prediction model to design standard production period for steel plate mills. in 2017 3rd International Conference on Control, Automation and Robotics, ICCAR 2017., 7942716, Institute of Electrical and Electronics Engineers Inc., pp. 346-351, 3rd International Conference on Control, Automation and Robotics, ICCAR 2017, Nagoya, Japan, 17/4/22. https://doi.org/10.1109/ICCAR.2017.7942716
    Shioya M, Uchida K. Prediction model to design standard production period for steel plate mills. In 2017 3rd International Conference on Control, Automation and Robotics, ICCAR 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 346-351. 7942716 https://doi.org/10.1109/ICCAR.2017.7942716
    Shioya, Masanori ; Uchida, Kenko. / Prediction model to design standard production period for steel plate mills. 2017 3rd International Conference on Control, Automation and Robotics, ICCAR 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 346-351
    @inproceedings{c17122ae694740beaa914c9788903c29,
    title = "Prediction model to design standard production period for steel plate mills",
    abstract = "Steel plate products are manufactured through many refining processes. Among the refining processes, there are some processes where it is determined during the production whether the plates need to go through, and the uncertainty of the production period and the workload derived by these processes make the production control of the steel plate difficult. In this paper, we propose a method to predict the standard production period that is especially important for the production control. Since black-box models are avoided in the production field, we contrived a model which first predicts the process flow of the refining processes by decision trees and then predicts the probability density function for the production period by adding up the processing periods of the transit processes. These probability density functions for the processing periods are calculated by means of a maximum likelihood estimation under normal distribution assumption, but it was found that the values of the standard production period were not as much different as those under exponential distribution assumption. Moreover, although it does not satisfy the requirements of the production field, we found that the average of the standard production periods improved 0.7 days using quantile regression forest predicting the standard production period directly.",
    keywords = "Decision tree, Maximum likelihood estimation, Prediction model, Production control, Production period",
    author = "Masanori Shioya and Kenko Uchida",
    year = "2017",
    month = "6",
    day = "7",
    doi = "10.1109/ICCAR.2017.7942716",
    language = "English",
    pages = "346--351",
    booktitle = "2017 3rd International Conference on Control, Automation and Robotics, ICCAR 2017",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    address = "United States",

    }

    TY - GEN

    T1 - Prediction model to design standard production period for steel plate mills

    AU - Shioya, Masanori

    AU - Uchida, Kenko

    PY - 2017/6/7

    Y1 - 2017/6/7

    N2 - Steel plate products are manufactured through many refining processes. Among the refining processes, there are some processes where it is determined during the production whether the plates need to go through, and the uncertainty of the production period and the workload derived by these processes make the production control of the steel plate difficult. In this paper, we propose a method to predict the standard production period that is especially important for the production control. Since black-box models are avoided in the production field, we contrived a model which first predicts the process flow of the refining processes by decision trees and then predicts the probability density function for the production period by adding up the processing periods of the transit processes. These probability density functions for the processing periods are calculated by means of a maximum likelihood estimation under normal distribution assumption, but it was found that the values of the standard production period were not as much different as those under exponential distribution assumption. Moreover, although it does not satisfy the requirements of the production field, we found that the average of the standard production periods improved 0.7 days using quantile regression forest predicting the standard production period directly.

    AB - Steel plate products are manufactured through many refining processes. Among the refining processes, there are some processes where it is determined during the production whether the plates need to go through, and the uncertainty of the production period and the workload derived by these processes make the production control of the steel plate difficult. In this paper, we propose a method to predict the standard production period that is especially important for the production control. Since black-box models are avoided in the production field, we contrived a model which first predicts the process flow of the refining processes by decision trees and then predicts the probability density function for the production period by adding up the processing periods of the transit processes. These probability density functions for the processing periods are calculated by means of a maximum likelihood estimation under normal distribution assumption, but it was found that the values of the standard production period were not as much different as those under exponential distribution assumption. Moreover, although it does not satisfy the requirements of the production field, we found that the average of the standard production periods improved 0.7 days using quantile regression forest predicting the standard production period directly.

    KW - Decision tree

    KW - Maximum likelihood estimation

    KW - Prediction model

    KW - Production control

    KW - Production period

    UR - http://www.scopus.com/inward/record.url?scp=85022346065&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85022346065&partnerID=8YFLogxK

    U2 - 10.1109/ICCAR.2017.7942716

    DO - 10.1109/ICCAR.2017.7942716

    M3 - Conference contribution

    SP - 346

    EP - 351

    BT - 2017 3rd International Conference on Control, Automation and Robotics, ICCAR 2017

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -