CEP Event Modeling for Real-Time Resource Usage Decomposition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current IoT and analytics technologies face challenges in implementing real-time monitoring and disaggregation of resource usage data from aggregated readings, particularly in brown field scenarios where specialized sensors are lacking, leading to computational bottlenecks and inefficiencies in streaming analytics.
Innovation Solution
The integration of complex event processing technology with data approximation techniques to automatically generate CEP events and queries, enabling real-time decomposition of resource usage data using existing sensors, reducing computational load and allowing for real-time monitoring without the need for extensive sensor infrastructure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If specialized sensors and IoT functionalities are deployed for real-time monitoring, then measurement precision and reliability are improved, but device complexity and implementation difficulty increase significantly in brown field scenarios
Solution Approach 1:
The patent creates virtual copies of sensor data by generating synthetic sensor readings through simulation models. Instead of deploying physical sensors on every component, the system generates virtual sensor data that mimics what physical sensors would measure, thereby achieving monitoring precision without the complexity of extensive physical sensor deployment
Solution Approach 2:
The patent replaces the mechanical/physical sensor system with a computational model-based system. Rather than using physical sensors to directly measure component states, the system uses simulation models that compute component states from available data, substituting physical measurement mechanisms with computational ones
2Measurement precision
If comprehensive sensor deployment is implemented for brown field scenarios, then measurement precision improves, but ease of manufacture and implementation worsen due to retrofitting difficulties
Solution Approach 1:
The patent creates a universal monitoring approach that works across different component types and scenarios without requiring component-specific sensor deployment. The simulation-based framework can model various components (bearings, motors, pumps) using general-purpose computational models, making the system universally applicable to brown field scenarios without custom retrofitting
Solution Approach 2:
The system creates virtual representations of physical components through simulation models, allowing monitoring of component states without physical sensor attachment. This copying approach enables retrofitting-free deployment where virtual models replicate the behavior and state of physical components
3Productivity
If real-time streaming analytics are implemented, then productivity and response time are improved, but use of energy and computational resources increase
Solution Approach 1:
The patent applies partial action by focusing computational resources only on the most critical monitoring tasks and components rather than performing exhaustive real-time analysis on all possible parameters. The simulation models prioritize computing only the component states and metrics that are most important for predictive maintenance, reducing overall computational energy consumption while maintaining productivity for critical functions
Solution Approach 2:
The system dynamically adjusts simulation parameters and model complexity based on operational conditions and available computational resources. By changing parameters such as simulation time steps, model fidelity, and update frequencies, the system optimizes the balance between real-time analytics productivity and energy consumption, using more detailed models only when necessary
Data Source
AI summary
Certain example embodiments automatically generate complex event processing (CEP) events and query definitions for real-time decomposition of resource usage data. Component models specifying measureable characteristics related to an aggregate reading and state(s) into which respective components are enterable are defined. For components that can have plural states, the models further specify valid state transitions, including predecessor and/or successor states. Plausible and composite state definitions are generatable from the component models. The former defines when a CEP engine is to trigger a corresponding plausible state event to signify that a corresponding state is potentially active. The latter corresponds to a representation of two or more component states that potentially are concurrently active. The CEP engine is configured to trigger events based on the aggregate reading and the generated plausible and composite state event definitions. The CEP engine can establish individualized component states from the aggregate reading based on triggered events.