Aircraft Engine Monitoring Model for Fleet-Scale Parallel Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Aircraft engine engineers lack the expertise in distributed computing to analyze large volumes of flight data from a fleet of engines, as they are specialists in thermodynamics and mechanics rather than distributed programming, making it difficult to implement effective monitoring systems.
Innovation Solution
A computer environment system that allows engineers to develop and deploy their own indicator extraction algorithms without knowledge of server cluster architecture or distributed calculations, using a system with an application interface, extraction module, learning module, and visualization tools to process and analyze flight data in parallel, and build a monitoring model for predictive maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If engineers develop monitoring codes using their specialized knowledge in thermodynamics and mechanics, then the monitoring algorithms are domain-specific and accurate, but the engineers cannot deploy these codes on distributed computing systems due to lack of distributed programming skills
Solution Approach 1:
The patent introduces an intermediary layer (the system architecture with code compilation, deployment, and execution modules) that translates domain-specific monitoring codes into distributed computing tasks. This intermediary enables engineers to write codes in their specialized languages without needing to learn distributed programming, while the system handles the translation and deployment automatically.
Solution Approach 2:
The system segments the monitoring process into distinct modules: code development, code compilation, code deployment, and code execution. This segmentation allows engineers to focus solely on the code development phase using their domain expertise, while other phases are automated or handled by specialists, resolving the contradiction between domain specificity and deployment capability.
2Productivity
If flight data from the fleet is processed systematically on a distributed computing medium, then large volumes of data can be analyzed in parallel, but the system requires specialized skills in distributed programming that engine engineers do not possess
Solution Approach 1:
The system enables self-service by allowing engine engineers to develop and deploy monitoring codes independently without requiring distributed programming expertise. The automated compilation and deployment mechanisms handle the complexity of distributed computing, making the system accessible to domain specialists while maintaining high data processing capacity.
Solution Approach 2:
The system creates a universal platform that accepts monitoring codes written in various domain-specific languages and automatically adapts them for execution on distributed computing media. This multi-functional approach allows the same system to handle both the complexity of distributed processing and the simplicity of domain-specific code development.
3Ease of manufacture
If generic platforms like Datalku are used for code development, then development tools are available, but these platforms are not specialized in aircraft engine monitoring and cannot produce operational solutions
Solution Approach 1:
The system applies local quality by providing specialized functionality for aircraft engine monitoring within the distributed computing platform. Rather than using a generic platform, the system incorporates domain-specific knowledge, data structures, and processing algorithms tailored to engine monitoring, ensuring both ease of development and operational reliability.
Solution Approach 2:
The system merges the advantages of generic development platforms with domain-specific expertise by integrating specialized aircraft engine monitoring capabilities into the distributed computing environment. This combination maintains the ease of code development while ensuring the reliability needed for operational solutions.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The invention relates to a computing environment system for monitoring aircraft engines, said system being connected to a cluster of servers, said system comprising: - an application interface (13) configured so as to receive user codes (19) that are developed independently from a distributed deployment system specifying the calculation of a set of indicators relating to an aircraft engine (3) for deployment on a fleet (12) of aircraft engines; - an extraction module (15) configured so as to extract said indicators by deploying parallel calculations on temporal flight data from the fleet of aircraft engines and stored in a database (9) distributed over said cluster (5) of servers (7); - a learning module (17) configured so as to use said indicators to construct, without supervision, from said indicators, a monitoring model (21) representative of the indicators by implementing predetermined learning functions.