Industrial Sensor Data Scheduling With Noise-Based State Forecasting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial environments face challenges in effectively utilizing vast amounts of data from IoT sensors, such as vibration data, to improve operations and maintenance, due to complexity and the need for role-specific insights that current digital twin technologies cannot adequately provide.
Innovation Solution
An enterprise management platform with role-based digital twins that integrate AI-enabled expert agents and enhanced collaboration features, enabling executives to monitor and control industrial plant operations through a converged technology stack for intelligent sensing, data collection, and real-time data handling, providing context-adaptive insights tailored to specific roles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If vast amounts of data from IoT sensors are collected in industrial environments, then the quantity of available information increases, but the complexity of effectively utilizing this data increases
Solution Approach 1:
The patent segments the industrial system into multiple digital twins representing different components, machines, and processes. Each digital twin independently processes and analyzes data relevant to its specific function, dividing the overwhelming data utilization complexity into manageable segments. This allows each digital twin to focus on specific data types and analysis tasks rather than attempting to process all industrial data centrally.
Solution Approach 2:
The patent introduces digital twins as intermediary entities between raw sensor data and human decision-makers. These digital twins act as mediators that automatically process, analyze, and interpret vast amounts of sensor data, transforming raw data into actionable insights. This intermediary layer handles the complexity of data utilization, freeing human operators from directly managing data complexity while still providing comprehensive monitoring and control capabilities.
2Speed
If current digital twin technologies are used to monitor industrial operations, then real-time monitoring capability is provided, but the ability to provide role-specific insights is insufficient
Solution Approach 1:
The patent applies local quality by tailoring the information presentation to specific user roles and contexts. Each user receives customized insights and alerts relevant to their specific responsibilities and decision-making needs. The system adapts the depth, format, and type of information provided based on the user's role, ensuring that each person receives appropriately targeted information without being overwhelmed by irrelevant data.
Solution Approach 2:
The patent implements dynamic adaptation of digital twin behavior and information delivery based on user roles, operational contexts, and real-time conditions. The system dynamically adjusts what information is presented, how it is presented, and which digital twins are most relevant to each user. This dynamic approach ensures that role-specific insights are maintained while preserving real-time monitoring capabilities across all industrial operations.
3Measurement precision
If executives need tailored digital interfaces with relevant real-time information, then decision-making quality improves, but the complexity of the enterprise management platform increases
Solution Approach 1:
The patent creates simplified digital copies (digital twins) of complex industrial systems that present information in role-appropriate formats. These digital twins serve as simplified interfaces that replicate the essential behavior and state of the physical systems they represent, but present information in ways that are easily understood by executives with different roles and expertise levels. This copying approach maintains decision-making quality by preserving accurate system representations while reducing interface complexity for end users.
Data Source
AI summary
Method for data collection in an industrial environment generally including receiving, at a switch, data from one or more variable groups of sensor inputs; monitoring the data from the one or more variable groups of sensor inputs; adaptively scheduling data collection at the switch; determining one or more noise values including one of an ambient noise, a local noise, or a vibration noise; using machine learning to forecast a future state of the industrial environment based at least in part on the determined one or more noise values; and reporting the forecasted future state of the industrial environment to an entity associated with a role type stored within a role taxonomy.