Predictive Sensor System for Aircraft Engine Maintenance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems fail to accurately predict and identify specific aircraft engines that will be unexpectedly grounded for maintenance, leading to inefficiencies and increased costs due to inadequate analysis of sensor data and limited user-friendly presentation of prediction results.
Innovation Solution
A predictive sensor system with a network of sensors that track engine performance and a graphical user interface (GUI) to efficiently route aircraft for maintenance, using machine learning models to identify 'at-risk' engines and provide actionable alerts for preventative action.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional analytical models are used to predict maintenance events, then the system can process sensor data, but the analysis requires excessive time and memory resources
Solution Approach 1:
The patent replaces conventional analytical models with machine learning models that are specifically optimized for processing sensor data from aircraft engines. The machine learning models are trained on historical sensor data to recognize patterns indicating maintenance events, enabling faster and more accurate predictions without requiring excessive computational resources.
Solution Approach 2:
The patent transforms the approach by changing from traditional statistical analysis parameters to machine learning parameters such as neural network weights and decision tree structures. This parameter transformation allows the system to process sensor data more efficiently while maintaining or improving prediction accuracy for maintenance events.
2Reliability
If conventional analytical models are used to predict maintenance events, then the system can generate predictions, but the amount of memory required is excessive
Solution Approach 1:
The patent substitutes memory-intensive conventional analytical models with streamlined machine learning models that use optimized data structures and algorithms. The machine learning models process sensor data through trained parameters rather than requiring extensive storage of intermediate calculation results, significantly reducing memory requirements while maintaining prediction capability.
3Loss of information
If the system presents detailed sensor data for thousands of sensors monitoring hundreds of engines, then complete information is provided, but the interface becomes tedious and not user-friendly
Solution Approach 1:
The patent extracts only the most relevant information from the vast sensor data set and presents it through the graphical user interface. Instead of displaying all sensor readings, the system identifies and highlights engines with predicted maintenance events and shows only the critical sensor data and maintenance recommendations, making the interface user-friendly while preserving essential information.
Solution Approach 2:
The patent segments the overwhelming sensor data into manageable groups and categories within the GUI. The interface organizes information by engine, by maintenance priority, and by sensor type, allowing users to navigate and access detailed data systematically without being overwhelmed by the total volume of information.
4Reliability
If previous systems predict the number of engines requiring unexpected grounding, then aggregate maintenance planning is possible, but specific engines cannot be identified for targeted maintenance
Solution Approach 1:
The patent replaces aggregate prediction models with machine learning models that analyze sensor data at the individual engine level. The models process unique sensor patterns from each engine to identify specific engines likely to experience maintenance events, providing both accurate predictions and precise engine identification for targeted maintenance planning.
Data Source
AI summary
A system according to which a network of physical sensors are configured to detect and track the performance of aircraft engines. The physical sensors are placed in specific locations to detect an exhaust gas temperature, vibration, speed, oil pressure, and fuel flow for each aircraft engine. The performance of each aircraft engine is then viewed in combination with oil consumption associated with that aircraft engine and the routine maintenance program associated with that aircraft engine to route the aircraft and move the aircraft, in accordance with the routing, to a specific location. The sensors efficiently track the performance and physical condition of the engines. Moreover, a listing of identified “at-risk” engines is displayed on a screen of a GUI in a manner that allows for easy navigation and display. Data point(s) that triggered the identification of each “at-risk” engine are easily accessible and viewable.