Distributed Fault Management for Fuel Cell Systems

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Fuel cell systems are vulnerable to partial failures and lack adaptive cognitive features to manage faults effectively, requiring human intervention and lacking adaptive learning capabilities to address real-time, unanticipated events.

Innovation Solution

A distributed fault management system using at least one sensor and two fault management computing devices, where the first device generates a resolution command signal for a fault condition and transmits it to a second device to implement a similar resolution for similar fault conditions, leveraging artificial intelligence and machine learning to dynamically and adaptively manage faults across multiple fuel cell systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If distributed fault management with AI/ML is implemented, then adaptability and automatic fault resolution improve, but device complexity increases

Engineering Contradiction:

Improveadaptive fault management capabilityVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The fault management system is segmented into distributed computing devices, each capable of independent AI/ML-based fault analysis. Each computing device processes fault data locally and can share resolution strategies with other devices in the network, dividing the complex adaptive management task into manageable distributed units.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

A communication network acts as an intermediary between distributed fault management computing devices, enabling them to share fault data, resolutions, and learned patterns without requiring direct complex interconnections. This mediator simplifies the overall system architecture while maintaining adaptive capabilities.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If human intervention is required for fault correction, then measurement precision and fault detection accuracy can be maintained, but loss of time and productivity decrease

Engineering Contradiction:

Improvefault detection accuracyVSAvoidfault resolution time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary fault analysis and generates resolution strategies automatically using AI/ML algorithms before human intervention is needed. By pre-processing fault data and generating corrective actions in advance, the system maintains high detection accuracy while significantly reducing the time required for actual fault resolution.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The fault management system implements continuous feedback loops where detected faults, human corrections, and resolution outcomes are fed back into the AI/ML models. This feedback mechanism allows the system to learn from human expertise while maintaining operational autonomy, improving both accuracy and response time over time.

Inventive Principle:

Principle #23Feedback

3Reliability

If adaptive learning features are added to fuel cell systems, then reliability and automatic fault resolution improve, but device complexity and manufacturing difficulty increase

Engineering Contradiction:

Improvesystem reliabilityVSAvoidmanufacturing complexity

Core Design Contradiction:

ReliabilityVSEase of manufacture

Solution Approach 1:

The fault management computing devices are designed as universal platforms that can be deployed across multiple fuel cell systems. Each device incorporates AI/ML capabilities for fault detection, analysis, and resolution, as well as communication functions for sharing learned patterns. This multi-functionality reduces per-system complexity while improving overall reliability through distributed intelligence.

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Productivity

If fault resolutions are shared across distributed systems, then productivity and fault prevention improve, but loss of information and communication requirements increase

Engineering Contradiction:

Improvefault resolution efficiencyVSAvoiddata communication overhead

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The system extracts only the essential fault patterns, diagnostic findings, and resolution strategies from complex fault data, transmitting only this distilled information across the network. By separating critical actionable information from raw data, the system improves fault resolution efficiency while minimizing communication overhead and information loss.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS11508980B2Systems and methods for distributed fault management in fuel cell systems

Publication Date: 2022.11.22 GE VERNOVA INFRASTRUCTURE TECHNOLOGY LLC

AI summary

A distributed fault management system includes at least one sensor associated with a fuel cell system and at least one first fault management computing device coupled to the at least one sensor. The at least one first fault management computing device is configured to receive data associated with a first fault condition. The at least one first fault management computing device is further configured to generate a resolution to the first fault condition and transmit at least one resolution command signal to at least one second fault management computing device. The at least one resolution command signal configures the at least one second fault management computing device to use the resolution to resolve a second fault condition in a similar manner.