On-line Prediction of Resistant Force During Soil-tool Interaction

Sencheng Yu; Xingyong Song; Zongxuan Sun

doi:10.1016/j.ifacol.2023.12.013

On-line Prediction of Resistant Force During Soil-tool Interaction

Sencheng Yu, Xingyong Song, Zongxuan Sun

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

For off-road vehicles such as excavators and wheel loaders, a large portion of energy is consumed to overcome the soil resistant force in the digging process. For optimal control of the digging tool, a high-fidelity model of the soil-tool interaction force is important to reduce energy consumption. In this paper, an on-line soil resistant force prediction method is proposed. In this method, a hybrid model, which combines a physical model and a data-driven model, is used for the force prediction. In addition, the parameters of the hybrid model can be updated on-line based on real-time data. Comparisons with experimental data demonstrate that the proposed prediction method has an average error of around 12.7%.

Original language	English (US)
Title of host publication	IFAC-PapersOnLine
Editors	Marcello Canova
Publisher	Elsevier B.V.
Pages	133-138
Number of pages	6
Edition	3
ISBN (Electronic)	9781713872344
DOIs	https://doi.org/10.1016/j.ifacol.2023.12.013
State	Published - Oct 1 2023
Externally published	Yes
Event	3rd Modeling, Estimation and Control Conference, MECC 2023 - Lake Tahoe, United States Duration: Oct 2 2023 → Oct 5 2023

Publication series

Name	IFAC-PapersOnLine
Number	3
Volume	56
ISSN (Electronic)	2405-8963

Conference

Conference	3rd Modeling, Estimation and Control Conference, MECC 2023
Country/Territory	United States
City	Lake Tahoe
Period	10/2/23 → 10/5/23

Bibliographical note

Publisher Copyright:
Copyright © 2023 The Authors.

Keywords

data-driven model
fundamental earthmoving equation
Off-road vehicle
soil-tool interaction forces

Access

10.1016/j.ifacol.2023.12.013

OpenUrl availability

Full text

Cite this

@inproceedings{d0b652b31cca4ae380bc40a336189fc9,

title = "On-line Prediction of Resistant Force During Soil-tool Interaction",

abstract = "For off-road vehicles such as excavators and wheel loaders, a large portion of energy is consumed to overcome the soil resistant force in the digging process. For optimal control of the digging tool, a high-fidelity model of the soil-tool interaction force is important to reduce energy consumption. In this paper, an on-line soil resistant force prediction method is proposed. In this method, a hybrid model, which combines a physical model and a data-driven model, is used for the force prediction. In addition, the parameters of the hybrid model can be updated on-line based on real-time data. Comparisons with experimental data demonstrate that the proposed prediction method has an average error of around 12.7%.",

keywords = "data-driven model, fundamental earthmoving equation, Off-road vehicle, soil-tool interaction forces",

author = "Sencheng Yu and Xingyong Song and Zongxuan Sun",

note = "Publisher Copyright: Copyright {\textcopyright} 2023 The Authors.; 3rd Modeling, Estimation and Control Conference, MECC 2023 ; Conference date: 02-10-2023 Through 05-10-2023",

year = "2023",

month = oct,

day = "1",

doi = "10.1016/j.ifacol.2023.12.013",

language = "English (US)",

series = "IFAC-PapersOnLine",

publisher = "Elsevier B.V.",

number = "3",

pages = "133--138",

editor = "Marcello Canova",

booktitle = "IFAC-PapersOnLine",

edition = "3",

}

TY - GEN

T1 - On-line Prediction of Resistant Force During Soil-tool Interaction

AU - Yu, Sencheng

AU - Song, Xingyong

AU - Sun, Zongxuan

PY - 2023/10/1

Y1 - 2023/10/1

N2 - For off-road vehicles such as excavators and wheel loaders, a large portion of energy is consumed to overcome the soil resistant force in the digging process. For optimal control of the digging tool, a high-fidelity model of the soil-tool interaction force is important to reduce energy consumption. In this paper, an on-line soil resistant force prediction method is proposed. In this method, a hybrid model, which combines a physical model and a data-driven model, is used for the force prediction. In addition, the parameters of the hybrid model can be updated on-line based on real-time data. Comparisons with experimental data demonstrate that the proposed prediction method has an average error of around 12.7%.

AB - For off-road vehicles such as excavators and wheel loaders, a large portion of energy is consumed to overcome the soil resistant force in the digging process. For optimal control of the digging tool, a high-fidelity model of the soil-tool interaction force is important to reduce energy consumption. In this paper, an on-line soil resistant force prediction method is proposed. In this method, a hybrid model, which combines a physical model and a data-driven model, is used for the force prediction. In addition, the parameters of the hybrid model can be updated on-line based on real-time data. Comparisons with experimental data demonstrate that the proposed prediction method has an average error of around 12.7%.

KW - data-driven model

KW - fundamental earthmoving equation

KW - Off-road vehicle

KW - soil-tool interaction forces

UR - http://www.scopus.com/inward/record.url?scp=85184349374&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85184349374&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2023.12.013

DO - 10.1016/j.ifacol.2023.12.013

M3 - Conference contribution

AN - SCOPUS:85184349374

T3 - IFAC-PapersOnLine

SP - 133

EP - 138

BT - IFAC-PapersOnLine

A2 - Canova, Marcello

PB - Elsevier B.V.

T2 - 3rd Modeling, Estimation and Control Conference, MECC 2023

Y2 - 2 October 2023 through 5 October 2023

ER -

On-line Prediction of Resistant Force During Soil-tool Interaction

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this