首页|Multi-models associated with process information-driven process autonomous digital twin for multi-variety production of intelligent machines

Multi-models associated with process information-driven process autonomous digital twin for multi-variety production of intelligent machines

扫码查看
The intelligent development of machines,as one of the essential research components of smart manufacturing,is urgently needed to improve the intelligent production of product manufacturing processes within product families.The uncertainty of the process requirements within a product family and the time-varying nature of the processing performance of machines pose significant challenges for intelligent manufacturing.Digital twins(DTs)have proven to be very effective architectures for intelligent manufacturing;DTs support dynamic modeling capabilities in time and space and can provide effective technical support for manufacturing intelligence under multi-variety production.Therefore,a process autonomous digital twin(PADT)framework driven by characterization,prediction,and evaluation-based multi-models(CPEM)associated with process information is constructed to realize intelligent production.First,the multidimensional information contained in the machining process is analyzed to accurately locate the features of machining precision,and a machine performance characterization model is built.Second,a machine capacity prediction model based on time-scale information fusion is established to predict the processing capacities of machines under different production demands.Finally,a product distribution evaluation model based on the 3σ rule is established,which provides an effective evaluation index for the optimization of processing parameters.The application of CPEM-driven PADT in a commutator machining machine provides predictive manufacturing intelligence within a product family.

process autonomous digital twinprecision performance characterizationperformance prediction modeldistribution evaluation modelmanufacturing intelligence

ZHANG Lu、WANG Xiao、HE SongPing、MAO XinYong、LI Bin、LIU HongQi

展开 >

State Engineering Research Center of Digital Manufacturing and Equipment,Huazhong University of Science and Technology,Wuhan 430074,China

Wuhan Heavy Duty Machine Tool Group Corporation,Wuhan 430205,China

National NC System Engineering Research Center Huazhong University of Science and Technology,Wuhan 430074,China

2024

中国科学:技术科学(英文版)
中国科学院

中国科学:技术科学(英文版)

CSTPCDEI
影响因子:1.056
ISSN:1674-7321
年,卷(期):2024.67(12)