A rapid modelling method for machine tool power consumption using transfer learning

被引：1
|
作者：
Wang, Qi [1 ,2 ]
Chen, Xi [1 ]
Chen, Ming [2 ]
He, Yafeng [1 ]
Guo, Hun [1 ]
机构：
[1] Changzhou Inst Technol, Dept Aeronaut & Mech Engn, Changzhou 213032, Peoples R China
[2] Shanghai Jiao Tong Univ, State Key Lab Mech Syst & Vibrat, Shanghai 200240, Peoples R China
来源：
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY | 2024年 / 131卷 / 3-4期
基金：
中国国家自然科学基金;
关键词：
Machine tool; Power consumption modelling; Transfer learning; Energy efficiency; ENERGY-CONSUMPTION; PREDICTION; EFFICIENCY; MECHANICS; WEAR;
D O I：
10.1007/s00170-024-13100-1
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Accurate power consumption models are the basis for improving energy efficiency of machine tools. The acquisition of energy consumption characteristics of different machine tools requires a large number of calibration experiments, which leads to low modelling efficiency. This paper proposes a rapid modelling method using transfer-learning to obtain the power consumption model of the target machine tool. After obtaining the power consumption model of the source machine tool through detailed experiments, this method only needs a few experiments to obtain the power consumption model of the target machine tool, which greatly improves the modelling efficiency, and the method is experimentally verified on different machine tools.
引用
收藏
页码：1551 / 1566
页数：16
相关论文
共 50 条
  • [41] Human dialogue modelling using machine learning
    Wilks, Y
    Webb, N
    Setzer, A
    Hepple, M
    Catizone, R
    Recent Advances in Natural Language Processing III, 2004, 260 : 17 - 28
  • [42] Modelling cryptographic distinguishers using machine learning
    Carlo Brunetta
    Pablo Picazo-Sanchez
    Journal of Cryptographic Engineering, 2022, 12 : 123 - 135
  • [43] Modelling cryptographic distinguishers using machine learning
    Brunetta, Carlo
    Picazo-Sanchez, Pablo
    JOURNAL OF CRYPTOGRAPHIC ENGINEERING, 2022, 12 (02) : 123 - 135
  • [44] Potential distribution modelling using machine learning
    Lorena, Ana C.
    de Siqueira, Marinez F.
    De Giovanni, Renato
    de Carvalho, Andre C. P. L. F.
    Prati, Ronaldo C.
    NEW FRONTIERS IN APPLIED ARTIFICIAL INTELLIGENCE, 2008, 5027 : 255 - +
  • [45] Power electronic systems modelling & controller rapid prototyping - An efficient method using VHDL
    Cirstea, M
    PROCEEDINGS OF THE 2004 IEEE WORKSHOP ON COMPUTERS IN POWER ELECTRONICS, 2004, : 228 - 231
  • [46] Tool Wear Monitoring Using Machine Learning
    Li, Ming
    Burzo, Mihai
    2021 IEEE CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (CCECE), 2021,
  • [47] Energy Consumption Prediction for Fused Deposition Modelling 3D Printing Using Machine Learning
    El Idrissi, Mohamed Achraf El Youbi
    Laaouina, Loubna
    Jeghal, Adil
    Tairi, Hamid
    Zaki, Moncef
    APPLIED SYSTEM INNOVATION, 2022, 5 (04)
  • [48] Rapid building detection using machine learning
    Cohen, Joseph Paul
    Ding, Wei
    Kuhlman, Caitlin
    Chen, Aijun
    Di, Liping
    APPLIED INTELLIGENCE, 2016, 45 (02) : 443 - 457
  • [49] Rapid building detection using machine learning
    Joseph Paul Cohen
    Wei Ding
    Caitlin Kuhlman
    Aijun Chen
    Liping Di
    Applied Intelligence, 2016, 45 : 443 - 457
  • [50] Machine learning fuzzy method for the modelling of experts and systems
    Otto, P
    Modelling and Simulation 2003, 2003, : 237 - 241
12345