Sensor Data Packet Labeling via Protocol and Signal Identification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current systems lack the ability to automatically identify the source of sensor data in industrial networks, making manual labeling of millions of data points a laborious and time-consuming process, and there is a need for efficient metadata creation for data processing and security monitoring.

Innovation Solution

A hardware and software system that automatically identifies data tags within data streams, consumes various industrial network protocols, and uses machine learning to create metadata files that label sensor data, enabling the identification of source sensors and enhancing network security by detecting potential attacks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual labeling of sensor data is performed, then data can be processed, but the process is laborious and time-consuming

Engineering Contradiction:

Improvedata processing speedVSAvoidtime for labeling data

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs automatic self-labeling of sensor data by extracting metadata from data packets themselves. The computer system automatically identifies protocol types, signal characteristics, and sensor classifications without human intervention, making the labeling process self-service and eliminating manual labor

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual process of data labeling with an automated computer-based system that uses protocol analysis and machine learning models to automatically classify and label sensor data, substituting human manual work with automated computational processes

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automatic identification system is implemented, then productivity improves, but device complexity increases

Engineering Contradiction:

Improvedata labeling efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system is designed to handle multiple industrial protocols (Modbus, Profibus, Profinet, Ethernet IP) and various sensor types through a unified automated labeling framework. The single system performs protocol identification, signal characteristic extraction, sensor classification, and metadata generation simultaneously, demonstrating multi-functionality that improves productivity without proportionally increasing complexity

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Measurement precision

If manual data review and labeling is performed, then data accuracy can be ensured, but the process becomes impractical for millions of data points

Engineering Contradiction:

Improvedata labeling accuracyVSAvoiddata processing capacity

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system introduces an intermediary automated classification layer between raw sensor data and final processed data. The computer system extracts protocol types and signal characteristics as intermediate metadata, then uses these intermediates to classify sensor data automatically, maintaining accuracy while enabling processing of millions of data points that would be impractical to review manually

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11586182B2System and device to automatically identify data tags within a data stream

Publication Date: 2023.02.21 THE BOEING CO

AI summary

A method including receiving a data packet over a network, the data packet having a size. The method also includes parsing the data packet into a header and a body. The method also includes identifying a protocol type from the header and the size. The method also includes identifying a signal characteristic of signal data in the body. The method also includes identifying a classification of a source sensor which generated the data packet based on the protocol type and the signal characteristic. The method also includes generating a metadata file based on the source sensor. The method also includes labeling the data packet with the metadata file to form a labeled data packet.