Reusable Fault Model Components for System Prognostics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Creating prognostics solutions for complex systems is time-consuming and costly due to the need for developing algorithms at various stages and levels, making existing solutions less adopted by the industry, as they are not customizable and widely applicable.
Innovation Solution
The development of reusable fault model components and algorithms that can be incorporated into a fault model, allowing for customization and wide applicability across various components, with the ability to predict system degradation and remaining life using real-time data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If prognostics solutions are developed for complex systems using custom algorithms at various stages and levels, then prediction accuracy is improved, but development time and cost increase significantly
Solution Approach 1:
The patent segments the complex prognostics system into reusable fault model components that can be independently developed, validated, and assembled. Each component represents a modular unit that can be developed once and reused across multiple systems, reducing redundant development work while maintaining prediction accuracy through component-specific algorithms.
Solution Approach 2:
The patent creates universal fault model components that can be applied across different complex systems and industries. These components are designed to be adaptable to various operating environments, manufacturing defects, and age-related factors, allowing a single component to serve multiple functions and systems, thereby reducing overall development time and cost.
2Measurement precision
If prognostics solutions are developed for complex systems with custom algorithms, then system-specific accuracy is improved, but maintenance complexity increases
Solution Approach 1:
By segmenting the prognostics solution into standardized fault model components, the patent simplifies maintenance activities. Each component can be independently maintained, updated, or replaced without affecting the entire system, reducing maintenance complexity while preserving system-specific accuracy through component configuration.
Solution Approach 2:
The universal fault model components are designed with standardized interfaces and maintenance procedures that can be applied across different systems. This universality reduces the need for system-specific maintenance expertise and simplifies the maintenance process while maintaining accuracy through component adaptability to different operating conditions.
3Measurement precision
If prognostics solutions are developed for each specific system configuration, then prediction accuracy is improved, but adaptability to different systems decreases
Solution Approach 1:
The patent creates fault model components with universal applicability that can be deployed across different complex systems and industries. These components are designed to adapt to various operating environments, manufacturing defects, and age-related factors through configuration rather than custom development, enabling wide applicability while maintaining prediction accuracy through component-specific parameter tuning.
Solution Approach 2:
The patent utilizes parameter changes to adapt universal fault model components to different system configurations. By modifying parameters such as operating conditions, manufacturing defect characteristics, and age-related degradation rates, the same component can accurately predict failures across diverse systems without requiring custom algorithm development for each system.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for creating and using a fault model representative of a system, the fault model comprising one or more fault model components is provided. The method creates a reusable fault model component; associates one or more algorithms to the reusable fault model component, the one or more algorithms describing behavior of the reusable fault model component; incorporates the reusable fault model component and the one or more algorithms into the fault model; tunes the reusable fault model component, using available data associated with the fault model; and predicts occurrence of degradation of the system, based on the tuning.