The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dalam makalah ini, pendekatan rangkaian saraf yang diubah suai dipanggil Rangkaian Neural Berpandu dicadangkan untuk pengenalan dinamik membujur kenderaan menggunakan algoritma keturunan kecerunan yang terkenal. Sumbangan utama kertas kerja ini adalah untuk mengambil kira maklumat yang diketahui tentang sistem dalam pengecaman dan untuk meningkatkan penumpuan ralat pengenalan. Dalam pendekatan ini, pengenalan dilakukan dalam dua peringkat. Pertama, Rangkaian Panduan digunakan untuk mendapatkan ciri dinamik anggaran daripada maklumat yang diketahui seperti model tak linear atau pengalaman pakar. Kemudian ralat antara loji dan Rangkaian Panduan diberi pampasan menggunakan Rangkaian Kompensasi dengan algoritma penurunan kecerunan. Dengan pendekatan ini, kelajuan penumpuan ralat pengenalan boleh dipertingkatkan dan model dinamik yang lebih tepat boleh diperolehi. Pendekatan yang dicadangkan digunakan pada pengenalan dinamik membujur kenderaan dan peningkatan prestasi yang dihasilkan diberikan.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Gu-Do LEE, Sun JUN, Sang Woo KIM, "Guided Neural Network and Its Application to Longitudinal Dynamics Identification of a Vehicle" in IEICE TRANSACTIONS on Fundamentals,
vol. E83-A, no. 7, pp. 1467-1472, July 2000, doi: .
Abstract: In this paper, a modified neural network approach called the Guided Neural Network is proposed for the longitudinal dynamics identification of a vehicle using the well-known gradient descent algorithm. The main contribution of this paper is to take account of the known information about the system in identification and to enhance the convergence of the identification errors. In this approach, the identification is performed in two stages. First, the Guiding Network is utilized to obtain an approximate dynamic characteristics from the known information such as nonlinear models or expert's experiences. Then the errors between the plant and Guiding Network are compensated using the Compensating Network with the gradient descent algorithm. With this approach, the convergence speed of the identification error can be enhanced and more accurate dynamic model can be obtained. The proposed approach is applied to the longitudinal dynamics identification of a vehicle and the resultant performance enhancement is given.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e83-a_7_1467/_p
Salinan
@ARTICLE{e83-a_7_1467,
author={Gu-Do LEE, Sun JUN, Sang Woo KIM, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Guided Neural Network and Its Application to Longitudinal Dynamics Identification of a Vehicle},
year={2000},
volume={E83-A},
number={7},
pages={1467-1472},
abstract={In this paper, a modified neural network approach called the Guided Neural Network is proposed for the longitudinal dynamics identification of a vehicle using the well-known gradient descent algorithm. The main contribution of this paper is to take account of the known information about the system in identification and to enhance the convergence of the identification errors. In this approach, the identification is performed in two stages. First, the Guiding Network is utilized to obtain an approximate dynamic characteristics from the known information such as nonlinear models or expert's experiences. Then the errors between the plant and Guiding Network are compensated using the Compensating Network with the gradient descent algorithm. With this approach, the convergence speed of the identification error can be enhanced and more accurate dynamic model can be obtained. The proposed approach is applied to the longitudinal dynamics identification of a vehicle and the resultant performance enhancement is given.},
keywords={},
doi={},
ISSN={},
month={July},}
Salinan
TY - JOUR
TI - Guided Neural Network and Its Application to Longitudinal Dynamics Identification of a Vehicle
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1467
EP - 1472
AU - Gu-Do LEE
AU - Sun JUN
AU - Sang Woo KIM
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E83-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 2000
AB - In this paper, a modified neural network approach called the Guided Neural Network is proposed for the longitudinal dynamics identification of a vehicle using the well-known gradient descent algorithm. The main contribution of this paper is to take account of the known information about the system in identification and to enhance the convergence of the identification errors. In this approach, the identification is performed in two stages. First, the Guiding Network is utilized to obtain an approximate dynamic characteristics from the known information such as nonlinear models or expert's experiences. Then the errors between the plant and Guiding Network are compensated using the Compensating Network with the gradient descent algorithm. With this approach, the convergence speed of the identification error can be enhanced and more accurate dynamic model can be obtained. The proposed approach is applied to the longitudinal dynamics identification of a vehicle and the resultant performance enhancement is given.
ER -