Real-time Digital Twin Generation from User Device Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge in real-time asset management is the time-consuming process of discovering and onboarding assets with diverse origins and generations, leading to slower onboarding speeds and potential undetected faults in industrial settings with numerous interconnected devices and sensors.
Innovation Solution
A method and system that utilize input data from user devices, such as image and sound data, to determine asset attributes, query asset databases, and generate digital twins in real-time or near real-time, leveraging contextual discovery models and sensor data to create accurate digital representations of assets, even when initial attributes do not satisfy predefined thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional asset discovery and data collection methods are used, then comprehensive asset data can be obtained, but the process becomes time-consuming and slows down onboarding speed
Solution Approach 1:
The system performs preliminary actions by pre-processing and storing asset data in databases before actual asset onboarding. When an asset needs to be onboarded, the system queries pre-processed data from databases rather than collecting data from scratch, significantly reducing onboarding time while maintaining data accuracy.
Solution Approach 2:
The system creates digital copies of asset data by generating digital twins that replicate physical asset characteristics. These digital twins are stored in databases and can be quickly retrieved and used for onboarding, eliminating the need to physically inspect and document each asset manually.
2Loss of information
If manual asset discovery processes are used, then detailed asset attributes can be captured, but the complexity of the process increases
Solution Approach 1:
The system employs a universal asset data collection architecture that can handle multiple asset types, data formats, and collection methods through a single platform. The system can collect data from various sources (sensors, databases, user input) and process different asset attributes through unified workflows, reducing process complexity while maintaining information completeness.
Solution Approach 2:
The system introduces intermediary components such as data normalization layers and standardized data models that mediate between diverse data sources and the asset management system. These intermediaries translate various data formats into a common structure, simplifying the discovery process while ensuring no asset attributes are lost.
3Reliability
If comprehensive asset data collection is performed, then accurate digital twins can be generated, but the time required for data gathering increases
Solution Approach 1:
The system performs preliminary data processing and validation before digital twin generation. By pre-processing asset data, validating formats, and organizing information in advance, the system ensures that when digital twins need to be generated, the data is already ready and verified, maintaining accuracy while speeding up the overall process.
Solution Approach 2:
The system implements a tiered approach to digital twin creation where essential attributes are collected and processed first to create basic digital twins quickly, and additional detailed attributes are added subsequently. This allows the system to maintain high onboarding throughput while still achieving comprehensive digital twin accuracy over time.
Data Source
AI summary
Various embodiments described herein relate to real-time generation of digital twins using asset data captured from a user device. In this regard, input data is received and one or more attributes of an asset are determined based on the input data. In accordance with determining whether the one or more attributes satisfy a predefined threshold, a digital twin or suggested digital twin is generated. Data associated with the digital twin or suggested digital twin is presented at a user interface of the user device enabling a user to extend or modify the data.