Aircraft Engine Thermal Neuromorphic Sensing for Event-Driven Data Capture

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional synchronous sensors in aircraft engines generate large volumes of data at high frequencies, posing challenges in efficient analysis and storage, especially on aircraft with limited capabilities, and often collect unnecessary data during nominal operating conditions.

Innovation Solution

Implementing a thermal neuromorphic sensor system that asynchronously reports changes in thermal data characteristics, activating additional sensors only upon detecting events that warrant further data collection, thereby reducing data analysis and storage needs during normal operations and enabling efficient fault diagnosis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If synchronous sensors are used to continuously monitor engine parameters, then measurement precision and reliability are improved, but data processing load and storage requirements increase significantly

Engineering Contradiction:
Improveanomaly detection capabilityVSAvoiddata processing and storage requirements
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts only the essential information (temperature changes indicating anomalies) from the continuous sensor data stream. The neuromorphic sensor outputs sparse event data representing only significant thermal changes, rather than transmitting all raw sensor readings, thereby reducing data processing and storage requirements while maintaining anomaly detection capability

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent changes the parameter representation from continuous synchronous data to asynchronous event-based data. By transforming the data format to represent only significant thermal events with timestamps and location information, the system reduces the volume of data requiring processing and storage while preserving the ability to detect anomalies

Inventive Principle:
Principle #35Parameter changes

2Loss of information

If all sensors are activated continuously, then complete data coverage is achieved, but energy consumption and data processing load increase

Engineering Contradiction:
Improvedata coverage completenessVSAvoidsensor system energy consumption
Core Design Contradiction:
Loss of informationVSUse of energy by moving object

Solution Approach 1:

The patent implements preliminary monitoring using the low-power thermal neuromorphic sensor before activating other sensors. The thermal sensor continuously monitors engine temperature in a power-efficient manner and only triggers additional sensor activation when anomalies are detected, ensuring complete data coverage is achieved only when necessary

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements dynamic sensor activation where the sensor system transitions from a static continuous-operation mode to a dynamic mode with variable activation states. The thermal neuromorphic sensor operates continuously at low power, while other sensors are dynamically activated only when thermal anomalies are detected, optimizing the balance between data coverage and energy consumption

Inventive Principle:
Principle #15Dynamics

3Speed

If high-frequency data collection is performed, then real-time monitoring capability is improved, but data storage requirements and processing time increase

Engineering Contradiction:
Improveanomaly detection speedVSAvoiddata volume
Core Design Contradiction:
SpeedVSQuantity of substance

Solution Approach 1:

The patent extracts only significant thermal events from the continuous data stream rather than storing all high-frequency readings. The neuromorphic sensor inherently filters out redundant data by outputting only events that exceed threshold changes, reducing data volume while maintaining real-time anomaly detection capability

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent inverts the traditional approach by not collecting all data and then analyzing it, but rather by directly detecting and reporting only significant anomalies in real-time. The thermal neuromorphic sensor is designed to inherently identify abnormal thermal patterns and trigger targeted data collection, reversing the conventional data collection and analysis workflow

Inventive Principle:
Principle #13The other way round (Inversion)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach minimizes data processing and storage requirements during nominal conditions, allowing for quick and efficient anomaly detection and troubleshooting by focusing resources on potential fault conditions in real-time or near-real-time.

Implementation Method 1

a thermal neuromorphic sensor coupled to the aircraft engine... receive first data from the thermal neuromorphic sensor, the first data including a thermal data characteristic associated with the aircraft engine

Methodology Applied
Scientific EffectThermal radiation: Thermal Radiation

Data Source

PatentEP4488782A1Aircraft engine data acquisition using thermal neuromorphic sensors
Publication Date: 2025.01.08 RTX CORP
  • EP4488782A1 patent drawingFigure 1
  • EP4488782A1 patent drawingFigure 2
  • EP4488782A1 patent drawingFigure 3

AI summary

Embodiments of the present disclosure generally relate to aircraft engines (20) and, more particularly to data acquisition for aircraft engines (20) using thermal neuromorphic sensors (206). In some embodiments, an event associated with the aircraft engine (20) may be identified based on a change in a thermal data characteristic measured from a thermal neuromorphic sensor (206). In response to identifying the event associated with the aircraft engine (20), one or more other sensors (206) coupled to the aircraft engine (20) may be activated and data received from the activated sensors (206) stored in memory (212). Other embodiments may be disclosed or claimed.