Shut-Off Valve Fault Detection from Opening-Closing Sensor Gaps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Diagnosing abnormal operation of aircraft valves is time-consuming and challenging with conventional methods, which are often specific to individual valve types and require manual intervention.
Innovation Solution
A data-driven, unsupervised algorithm analyzes sensor data using an n-second window to identify abnormal valve operation by computing differences in sensor values during valve opening and closing, allowing for flexible and portable detection across various aircraft systems without manual labeling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional diagnostic methods are used for valve operation, then specific valve types can be diagnosed, but the process is time-consuming and requires manual intervention
Solution Approach 1:
The patent replaces manual diagnostic methods with an automated data-driven unsupervised algorithm that analyzes sensor data to detect abnormal valve operation. The system automatically identifies sensor parameters, computes thresholds, and generates maintenance messages without human intervention, thereby reducing diagnosis time while maintaining accuracy.
Solution Approach 2:
The system enables self-diagnosis by automatically analyzing sensor data from multiple valves, identifying abnormal operations through computed thresholds, and generating maintenance messages autonomously. The unsupervised algorithm learns from historical data and independently detects anomalies without requiring manual labeling or expert intervention.
2Reliability
If conventional diagnostic approaches are used, then specific valve types can be targeted, but the system lacks flexibility and portability across different valve types
Solution Approach 1:
The patent creates a universal diagnostic system that can detect abnormal operations across all types of shut-off valves in an aircraft. The data-driven unsupervised algorithm is type-agnostic and adapts to different valve configurations by analyzing their respective sensor data, enabling a single system to serve multiple valve types without requiring type-specific customization.
Solution Approach 2:
The system dynamically identifies and adapts to different valve types by automatically selecting relevant sensor parameters and computing type-specific thresholds through unsupervised learning. The algorithm adjusts its analysis based on the characteristics of each valve type while maintaining a unified diagnostic framework, enabling flexible adaptation without manual reconfiguration.
3Measurement precision
If manual diagnostic intervention is used, then detailed analysis can be performed, but the process becomes complex and difficult to scale
Solution Approach 1:
The patent replaces complex manual diagnostic processes with an automated data-driven algorithm that performs detailed sensor data analysis. The unsupervised learning system automatically identifies patterns, computes thresholds, and detects anomalies without requiring manual intervention, thereby reducing system complexity while maintaining or improving analysis depth.
Solution Approach 2:
The system introduces an intermediate computational layer that automatically processes sensor data between the sensors and the diagnostic output. The unsupervised algorithm acts as a mediator that transforms raw sensor readings into meaningful diagnostic information, simplifying the overall system architecture while enabling detailed analysis through automated feature extraction and pattern recognition.
Data Source
AI summary
A computer-implemented method, system, and computer program product are provided. A plurality of maintenance messages (MMSGs) are identified. Each MMSG is associated with at least one shut-off valve. A sensor parameter is identified based on an analysis of sensor parameters associated with the shut-off valves of each MMSG. A threshold value for the sensor parameter is identified as being associated with abnormal operation of the respective shut-off valves. A sensor associated with a first shut-off valve captures values for the sensor parameter during a first and second predefined time period, the first and second predefined time periods associated with an opening and a closing of the first shut-off valve. Upon determining that a difference between the maximum values of the sensor values captured during the first and second predefined time periods exceeds the first threshold value, a determination is made that the first shut-off valve is operating abnormally.