Logo of Acerta
Book a demo

Case Study

Reducing Hydrogen Fuel Cell Test Times by 46%

Objectives

Accelerate fuel cell production by reducing test times and avoiding costly test station expansion using machine learning.

Challenge

Lengthy test cycles, underused data, and high capital costs made it difficult for Ballard to scale production and meet growing demand efficiently.

Key Results

  • 46% reduction in average test time per unit
  • 83% increase in testing throughput
  • Over $6M projected savings in capital and operating costs
Hydrogen Fuel Cell Stacks Light Vehicles

46%

Reduction in test time

83%

Increase in test throughput

$6M

Estimated savings over 3 years

Background

Ballard Power Systems, based in Burnaby, BC, Canada, is a global leader in hydrogen fuel cell technology, specializing in Proton Exchange Membrane Fuel Cells (PEMFC) for heavy-duty applications such as buses, trains, and marine vessels. As part of their growth strategy, Ballard aimed to scale production volume by 488% over three years to meet increasing demand and compete effectively against battery-electric alternatives.

Problem

In scaling production volumes, Ballard encountered these key challenges:

  • Lengthy Factory Acceptance Testing (FAT): Each fuel cell stack underwent rigorous FAT lasting between 2.5 to 8 hours to ensure consistent performance and reliability. These long test cycles limited production throughput, consumed significant amounts of costly hydrogen, and strained test station capacity.
  • Underutilized Data Potential: Although large volumes of high-frequency time-series data (voltage, current, temperature, etc.) were generated during testing, current tools limited the ability for Ballard to extract actionable insights. Traditional methods based on averaging techniques at the end of the test cycle didn’t allow for significant early predictions of the test outcomes or other improvements.
  • High Cost of Scaling: To support their planned increase in production targets, Ballard would have needed to invest in additional automated test stations, each costing approximately $1M. Physical factory space constraints further complicated expansion plans.

Solution

Ballard partnered with Acerta to extract the latent value in their testing data and avoid costly capital expenditures. Acerta developed, validated, and deployed a custom machine learning model tailored to Ballard’s specific test sequences, integrated within Acerta’s LinePulse platform. The solution included:

  • Time-Series Data Ingestion: The model ingests rich, high-frequency data captured during the FAT process, including voltage, current, stack-level performance parameters, and environmental conditions.
  • Early Pass/Fail Predictions: By analyzing patterns and trends within the first 15 minutes of each test, the model accurately predicts whether a stack will pass or fail the rest of the test in 46% of cases. This allows operators to either continue the test if further verification is required, or terminate it early, saving time and resources.
  • Seamless Integration: The model operates within the LinePulse platform, complementing existing modules for real-time SPC monitoring, automated root cause analysis, and predictive quality, ensuring comprehensive production oversight.
  • Flexibility and Scalability: Ballard’s test engineers retain full control over model thresholds, balancing prediction coverage and accuracy to fit evolving production needs.

Results

  • 46% reduction in fuel cell test times: The predictive model shortened average FAT durations from 2.5-8 hours to as little as 15 minutes for a significant share of stacks, enabling Ballard to drastically improve production efficiency.
  • 83% increase in throughput: The improved test process eliminated the need for additional test stations, allowing Ballard to meet their aggressive growth targets using their existing infrastructure.
  • Projected $6M+ in savings: Reduced hydrogen consumption, decreased labor hours, and avoidance of ~$6M in capital costs over three years, including the potential avoidance of purchasing additional $1M test stations.
  • Environmental Benefits: Shorter test cycles reduced hydrogen usage per stack, lowering both energy consumption and the environmental impact of Ballard’s manufacturing process.

This increase in efficiency allows us to scale production

"Acerta’s machine learning model allowed us to cut our fuel cell stack testing time by 46% without sacrificing quality. This increase in efficiency allows us to scale production while lowering our hydrogen and labour costs, and avoiding additional capital investments.”
Andreas Putz
Principal Engineer: Data Science

Case Studies

Proven Impact