Aircraft Power-Up Anomaly Detection for Predictive Maintenance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Modern aircraft systems face inefficiencies in maintenance due to unscheduled faults, where components are replaced unnecessarily during scheduled maintenance, and delays occur due to the lack of immediate availability of parts or technicians during fault conditions.

Innovation Solution

An anomaly detection system that captures sensor data during power-up events, calculates delta values, assigns them to quantization bins, normalizes counts, and compares these to anomaly detection thresholds to predict operational anomalies before faults occur, enabling more effective and efficient maintenance scheduling.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If scheduled maintenance is performed according to a schedule, then fault conditions are avoided, but operational availability decreases due to unnecessary component replacements

Engineering Contradiction:
Improvefault avoidanceVSAvoidoperational availability
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system performs preliminary analysis of sensor data during power-up events to detect anomalies before they cause faults. By calculating delta values, quantizing them into bins, and comparing normalized counts against thresholds, the system identifies components that need attention before failure occurs, enabling maintenance to be performed only when necessary rather than following a fixed schedule

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system transforms raw sensor data into meaningful parameters through a series of processing steps: calculating delta values (differences between consecutive samples), quantizing these deltas into discrete bins, and computing normalized counts. These transformed parameters are then compared against thresholds to determine anomaly status, allowing the system to adapt maintenance decisions based on actual component behavior rather than predetermined schedules

Inventive Principle:
Principle #35Parameter changes

2Reliability

If unscheduled maintenance is performed to remedy fault conditions, then operational availability is maintained, but significant delays occur due to unavailability of parts or technicians

Engineering Contradiction:
Improveoperational availabilityVSAvoidmaintenance delay
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary detection of anomalies during routine power-up events, identifying components that will soon fail. This advance notice allows operators to schedule maintenance at convenient times when parts and technicians are available, eliminating the delays associated with unscheduled emergency maintenance while still maintaining operational availability

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors sensor data and provides feedback about component health status. By comparing normalized delta counts against thresholds, the system generates anomaly indicators that feed into maintenance scheduling decisions, creating a closed-loop system that adapts maintenance timing based on actual component conditions rather than reacting to failures

Inventive Principle:
Principle #23Feedback

3Reliability

If components are replaced during scheduled maintenance, then fault conditions are avoided, but efficiency decreases due to replacement of components operating normally

Engineering Contradiction:
Improvefault avoidanceVSAvoidmaintenance efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system applies local quality assessment by evaluating each component's sensor data independently through delta calculation and quantization. Each component receives individual anomaly scoring based on its specific behavior patterns, allowing maintenance decisions to be made on a component-by-component basis rather than replacing all components during scheduled maintenance

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system transforms raw sensor readings into anomaly indicators through parameter transformations: delta values capture rate of change, quantization bins categorize the magnitude of changes, and normalized counts provide comparable metrics across different components. These transformed parameters enable precise identification of which components actually need replacement

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3893071B1Anomaly prediction and detection for aircraft equipment
Publication Date: 2024.05.01 THE BOEING CO
  • EP3893071B1 patent drawingFigure 1
  • EP3893071B1 patent drawingFigure 2
  • EP3893071B1 patent drawingFigure 3

AI summary

A method includes obtaining sensor data captured by a sensor of an aircraft during a power up event. The sensor data includes multiple parameter values, each corresponding to a sample period. The method further includes determining a set of delta values, each indicating a difference between parameter values for consecutive sample periods of the sensor data. The method further includes determining a set of quantized delta values by assigning the delta values to quantization bins based on magnitudes of the delta values. The method further includes determining a normalized count of delta values for each quantization bin. The method further includes comparing the normalized counts of delta values to anomaly detection thresholds. The method further includes generating, based on the comparisons, output indicating whether the sensor data is indicative of an operational anomaly.