Sensor Data Generation Stack for Fault Tolerance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Networked sensor systems face operational disruptions due to unavailable sensors, leading to reduced performance and downtime, particularly in critical industries like public utilities, healthcare, and agriculture, where timely resource deployment is essential.
Innovation Solution
A multi-layer data generation stack that generates substitute sensor data using static, dynamic, or hybrid relationships between available and unavailable sensors, ensuring continuous operation by providing substitute data that mimics the unavailable sensor type, thereby improving fault tolerance and system uptime.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor data is directly collected from physical sensors, then data accuracy is maintained, but system operation is disrupted when sensors are unavailable
Solution Approach 1:
The patent creates virtual copies of unavailable sensor data by generating substitute data that mimics the characteristics and behavior of the original sensor. This copying approach allows the system to maintain continuous operation by using the virtual copy instead of the unavailable physical sensor data, thereby improving system uptime while preserving data availability.
Solution Approach 2:
The patent introduces an intermediary data generation layer between the physical sensors and the application layer. When sensors are unavailable, this intermediary layer generates substitute data that bridges the gap, allowing the system to continue operating without direct access to the original sensor data while maintaining data flow to dependent systems.
2Reliability
If substitute sensor data is generated for unavailable sensors, then system continuity is maintained, but data authenticity is compromised
Solution Approach 1:
The patent changes the parameters and characteristics of available sensor data to simulate the behavior of unavailable sensors. By transforming and adjusting the parameters of substitute data to match expected patterns of the unavailable sensor, the system maintains fault tolerance while preserving reasonable data accuracy through parameter transformation rather than direct copying.
Solution Approach 2:
The patent creates a universal data generation mechanism that can serve multiple sensor types and applications. The substitute data generation system is designed to be adaptable to different sensor configurations and requirements, allowing a single system to maintain multiple functions while providing authentic-looking data for various unavailable sensor types.
3Measurement precision
If complex relationships between sensors are modeled, then data substitution accuracy improves, but system complexity increases
Solution Approach 1:
The patent segments the data generation system into distinct layers and components, each handling specific aspects of substitute data creation. This segmentation allows complex relationships to be modeled in a modular fashion, where each layer handles a specific transformation or relationship type, reducing overall system complexity while maintaining high substitute data accuracy through specialized processing at each level.
Solution Approach 2:
The patent adds dimensional layers to the data generation process, creating a multi-layered architecture that handles different aspects of data substitution separately. By organizing the complex relationship modeling across multiple dimensions or layers, the system can achieve high accuracy in substitute data while managing complexity through structured organization rather than monolithic design.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A data generation stack executing on data processing circuitry may generate substitute data for provision in place of data sample from sensor circuitry. A configuration layer of the data generation stack may store a configuration file. A data ingestion and generation layer of the data generation stack may access the configuration file to determine static relationships among different sensors within the system. The data ingestion and generation layer may further determine dynamic relationships among the sensors. Based on a hybrid relationship that accounts for the static and dynamic relationships, the data ingestion and generation layer may generate substitute data for a sensor based on sampled data from another sensor. A data export layer of the data generation stack may access the generated substitute data for output.