Fuel Cell Stack Voltage Diagnostics for Bad Channel Separation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current fuel cell stack diagnostic systems face challenges in distinguishing between bad channels and weak cells, which affects the accuracy of health assessment and operational efficiency, especially in next-generation fuel cell systems operating at varying pressure and temperature conditions.

Innovation Solution

A method involving a controller that collects and processes operating data to identify bad channels and weak cells by analyzing voltage differences, statistical distributions, and behavioral signatures, while accounting for fuel cell aging and system variability, and provides proactive health assessments and alerts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If voltage monitoring is used to detect fuel cell stack health, then diagnostic information can be obtained, but it is difficult to distinguish between bad channels and weak cells

Engineering Contradiction:
Improvevoltage detection accuracyVSAvoiddiagnostic information accuracy
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The diagnostic method segments the fuel cell stack into individual cells and further segments the diagnostic analysis into multiple stages: initial voltage monitoring, statistical analysis of voltage distribution, transient condition testing, and behavioral signature analysis. This segmentation allows differentiation between measurement errors (bad channels) and actual cell degradation (weak cells) by examining patterns across multiple dimensions rather than relying on single voltage readings.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system implements continuous feedback loops where voltage measurements from all cells are collected, analyzed statistically, and used to update the diagnostic model. The controller monitors voltage distributions, compares against expected patterns, and refines its identification of bad channels versus weak cells over time. This feedback mechanism improves diagnostic accuracy by learning from accumulated operational data and adjusting interpretations accordingly.

Inventive Principle:
Principle #23Feedback

2Productivity

If complex control systems are designed for air handling and fuel management, then system performance can be optimized, but device complexity increases

Engineering Contradiction:
Improvesystem performanceVSAvoidcontrol system complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The controller is designed as a multi-functional device that simultaneously performs air handling control, fuel management, voltage monitoring, statistical analysis, and diagnostic functions. Rather than requiring separate dedicated systems for each function, the same controller hardware and software platform handles multiple tasks, reducing overall system complexity while maintaining optimized performance across all subsystems.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The diagnostic functions are merged with the existing control system rather than being implemented as separate add-on systems. The voltage monitoring, statistical analysis, and health assessment capabilities are integrated into the same controller that manages air and fuel systems, creating a unified platform that reduces component count and simplifies system architecture while delivering enhanced functionality.

Inventive Principle:
Principle #5Merging (Combining)

3Measurement precision

If higher fidelity diagnostics are implemented, then health assessment accuracy improves, but measurement and processing requirements increase

Engineering Contradiction:
Improvehealth assessment accuracyVSAvoiddata processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary statistical analysis and baseline establishment during normal operation before diagnostic issues arise. Voltage distributions are continuously characterized, and expected patterns are established during healthy operation. This preliminary action creates reference data that simplifies later diagnostic decisions, allowing the system to detect deviations from normal behavior without requiring complex real-time analysis during critical assessments.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The diagnostic system implements a tiered approach where basic voltage monitoring is continuously performed on all cells, but more intensive statistical analysis and transient testing are applied selectively based on initial screening results. Not all cells undergo the full diagnostic sequence; only those showing signs of potential issues receive more intensive analysis, reducing overall processing complexity while maintaining high detection accuracy for problematic cells.

Inventive Principle:
Principle #16Partial or excessive action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enhances the accuracy of fuel cell stack health assessment, enabling timely interventions and improving operational performance by distinguishing between bad channels and weak cells, thus extending the lifespan and efficiency of fuel cell systems.

Implementation Method 1

A fuel cell or fuel cell stack may generate electricity in the form of direct current (DC) from electro-chemical reactions that take place in the fuel cell or fuel cell stack

Methodology Applied
Scientific EffectElectrochemical reaction:

Data Source

PatentUS20230327154A1Assessing health of a fuel stack using fuel cell voltage diagnostics
Publication Date: 2023.10.12 CUMMINS INC
  • US20230327154A1 patent drawing
  • US20230327154A1 patent drawing
  • US20230327154A1 patent drawing

AI summary

The present disclosure generally relates to systems and methods for assessing the health of a fuel cell stack including collecting fuel cell stack operating data by a controller including stack voltage data and cell voltage monitoring data and determining the trust in the collected data, processing stack voltage data and cell voltage monitoring data by the controller to identify bad channels and weak cells amongst fuel cells included in the fuel cell stack, tracking the state of health of the fuel cell stack by the controller, and assessing the health of the fuel cell stack by the controller.