A Method for Updating Digital Twin Models Based on Multi-Source Heterogeneous Data

By preprocessing and directional mapping of multi-source heterogeneous data, the problem of insufficient matching between digital twin models and multi-source heterogeneous data is solved, enabling accurate model updates and efficient application, and supporting the optimization of industrial production lines and fault prediction.

CN122086992APending Publication Date: 2026-05-26CHINA UNITED NETWORK COMM GRP CO LTD +2
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA UNITED NETWORK COMM GRP CO LTD
Filing Date
2026-02-09
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

In industrial digital twin platforms, multi-source heterogeneous data is difficult to match accurately with digital twin models, resulting in low model update accuracy and an inability to effectively support industrial production line scheduling, equipment fault prediction, and production decision optimization.

Method used

By acquiring raw data from multi-source heterogeneous platforms and model attributes of digital twin models, preprocessing is performed to remove noise and standardize formats. Targeted mapping is then established to generate adapted second data and update the digital twin model.

Benefits of technology

This improves the accuracy and timeliness of digital twin model updates, ensuring that the model can accurately match industrial production line scheduling and equipment failure prediction, optimize production decisions, and unleash the industrial application value of multi-source heterogeneous data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122086992A_ABST
    Figure CN122086992A_ABST
Patent Text Reader

Abstract

This application provides a method for updating a digital twin model based on multi-source heterogeneous data. It accurately acquires the original data from a multi-source heterogeneous platform and the core attributes of the digital twin model, and simultaneously performs targeted preprocessing on the original data to improve data usability and effectiveness. Based on this, by establishing a directional mapping relationship between multi-source heterogeneous data and the model's core attributes, it effectively addresses the core technical pain point of insufficient matching between data and model attributes in existing technologies. Finally, the adapted second data is output to the multi-source heterogeneous platform to complete the model update, effectively releasing the industrial application value of multi-source heterogeneous data, providing reliable technical support for the virtual-physical linkage and intelligent decision-making of industrial digital twin systems, and significantly improving the update accuracy and timeliness of the digital twin model.
Need to check novelty before this filing date? Find Prior Art