Application of physics-informed machine learning for excavator working resistance modeling

被引：9

作者：

Li, Shijiang ^{[1
]}

Wang, Shaojie ^{[1
,2
]}

Chen, Xiu ^{[1
]}

Zhou, Gongxi ^{[1
]}

Wu, Binyun ^{[1
]}

Hou, Liang ^{[1
]}

机构：

[1] Xiamen Univ, Pen Tung Sah Inst Micronano Sci & Technol, Xiamen 361102, Peoples R China

[2] Xiamen Univ, Shenzhen Res Inst, Shenzhen 518057, Peoples R China

来源：

MECHANICAL SYSTEMS AND SIGNAL PROCESSING | 2024年 / 209卷

基金：

中国国家自然科学基金;

关键词：

Excavator; Working resistance; Soft sensing; Physics -informed machine learning; FORCE;

D O I：

10.1016/j.ymssp.2024.111117

中图分类号：

TH [机械、仪表工业];

学科分类号：

0802 ;

摘要：

Accurate measurement of the working resistance encountered during excavation plays a vital role in improving production efficiency, reducing energy consumption, and enabling intelligent capabilities in excavators. To address the challenges of the inaccurate measurement of working resistance, we present a novel method for measuring excavator working resistance based on physics-informed machine learning (PIML). Firstly, we construct a mechanism model, which incorporates the kinematic and dynamic models of the excavator working device. Next, by integrating the mechanism models with machine learning algorithms, a soft sensing model for excavator working resistance based on the PIML method is developed. Finally, experimental analysis is conducted to compare the predictive performance of three different methods: mechanism modeling, data-driven modeling, and PIML. The results indicate that the PIML method allows for a more precise estimation of the working resistance experienced during the excavation process of excavators, and it holds significant theoretical and practical implications.

引用

页数：18

共 45 条

[1] Integrity assessment and determination of residual fatigue life of vital parts of bucket-wheel excavator operating under dynamic loads [J].

Arsic, Dusan ;

Gnjatovic, Nebojsa ;

Sedmak, Simon ;

Arsic, Aleksandra ;

Uhricik, Milan .

ENGINEERING FAILURE ANALYSIS, 2019, 105 :182-195

[2]

Bergstra J., 2013, Hyperopt: a python library for optimizing the hyperparameters of machine learning algorithms, P13, DOI [10.25080/Majora-8b375195-003, DOI 10.25080/MAJORA-8B375195-003]

[3]

Bergstra J., 2011, Advances in neural information processing systems, P24

[4] Modeling and forecasting building energy consumption: A review of data-driven techniques [J].

Bourdeau, Mathieu ;

Zhai, Xiao Qiang ;

Nefzaoui, Elyes ;

Guo, Xiaofeng ;

Chatellier, Patrice .

SUSTAINABLE CITIES AND SOCIETY, 2019, 48

[5] Intelligent energy-saving operation of wheel loader based on identifiable materials [J].

Cao, Bing-wei ;

Liu, Xin-hui ;

Chen, Wei ;

Yang, Kuo ;

Liu, Dan .

JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY, 2020, 34 (03) :1081-1090

[6] Design and modeling of hardware-in-loop test bench for hydraulic excavator based on dynamic load emulation [J].

Chen, Jinshi ;

Huo, Dongyang ;

Liu, Changyi ;

Zhang, Han ;

Wang, Yuqi .

AUTOMATION IN CONSTRUCTION, 2022, 137

[7]

Chen Qiangen, 2017, Journal of Beijing University of Technology, V43, P1135, DOI 10.11936/bjutxb2016040013

[8] A review of physics-based models in prognostics: Application to gears and bearings of rotating machinery [J].

Cubillo, Adrian ;

Perinpanayagam, Suresh ;

Esperon-Miguez, Manuel .

ADVANCES IN MECHANICAL ENGINEERING, 2016, 8 (08)

[9] A review of machine learning methods applied to structural dynamics and vibroacoustic [J].

Cunha, Barbara Zaparoli ;

Droz, Christophe ;

Zine, Abdel-Malek ;

Foulard, Stephane ;

Ichchou, Mohamed .

MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2023, 200

[10]

Damnjanovic V, 2014, J VIBROENG, V16, P1212

← 1 2 3 4 5 →