Prognostic Reasoning for Complex System Fault Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional complex system analysis systems are inadequate for identifying and diagnosing complex adverse events such as incipient faults, slow progressing events, intermittent or recurring faults, and cascading faults, as they rely on simple binary evidence which is insufficient for sophisticated event analysis.
Innovation Solution
The system generates complex evidence through advanced diagnostic and prognostic monitors that produce condition indicators, health indicators, and prognostic indicators, using a system fault model to define statistical relationships between binary evidence, complex evidence, and underlying failure modes, enabling advanced diagnostic and prognostic reasoning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If simple binary evidence is used for system analysis, then the system complexity is reduced and ease of operation is improved, but the measurement precision and ability to detect complex adverse events deteriorates
Solution Approach 1:
The evidence is segmented into multiple types (binary evidence, complex evidence, condition indicators, health indicators, prognostic indicators) that can be processed differently. This allows the system to maintain simple binary processing for basic operations while using more sophisticated evidence types for complex event detection, thus resolving the contradiction between ease of operation and measurement precision.
Solution Approach 2:
The patent introduces additional dimensions of evidence representation beyond simple binary values. By adding complex evidence with multiple properties (condition indicators, health indicators, prognostic indicators), the system enhances measurement precision without completely overhauling the operational framework, as binary evidence continues to be used for basic operations.
2Reliability
If complex evidence with sophisticated mathematical properties is generated, then the ability to identify complex adverse events is improved, but the device complexity and computational requirements increase
Solution Approach 1:
The monitoring system is segmented into different levels: simple diagnostic and prognostic monitors that generate binary evidence, and advanced diagnostic and prognostic monitors that generate complex evidence. This segmentation allows the system to achieve high reliability for complex event detection while keeping the overall device complexity manageable by only applying advanced processing where needed.
Solution Approach 2:
The system implements a universal evidence processing framework that can handle both binary and complex evidence types through a common system fault model and probabilistic reasoning engine. This multi-functionality allows the same core architecture to support both simple and complex analysis, reducing the need for separate specialized systems and thereby controlling device complexity.
3Measurement precision
If advanced diagnostic and prognostic monitors are implemented, then the diagnostic and prognostic capabilities are improved, but the loss of computational resources and processing time increases
Solution Approach 1:
The system applies advanced processing partially - only for complex adverse events that require it. For routine monitoring, simple binary evidence processing is sufficient and is used to minimize computational overhead and processing time. Advanced diagnostic and prognostic monitors are activated selectively based on system state and event complexity, thus achieving high measurement precision when needed while minimizing time loss during normal operation.
Data Source
AI summary
Methods and apparatus are provided for analyzing a complex system that includes a number of subsystems. Each subsystem comprises at least one sensor designed to generate sensor data. Sensor data from at least one of the sensors is processed to generate binary evidence of a sensed event, and complex evidence of a sensed event. The complex evidence has more sophisticated mathematical properties than the binary evidence. The complex evidence comprises one or more of: a condition indicator (CI), a health indicator (HI), and a prognostic indicator (PI). A system fault model (SFM) is provided that defines statistical relationships between binary evidence, complex evidence, and an underlying failure mode (FM) that is occurring in the complex system. The binary evidence and the complex evidence are processed to identify failure modes taking place within one or more of the subsystems. Based on the binary evidence and the complex evidence and the SFM, diagnostic conclusions can be generated regarding adverse events that are taking place within the complex system, and prognostic conclusions can be generated regarding adverse events that are predicted to take place within the complex system.