Accelerating R&D and Production of Fast-Paced Li-Ion Battery Cell Manufacturer
CLIENT - SOLID-STATE BATTERY CELLS
Our client is an innovative and fast-paced Li-ion battery cell manufacturer focused on battery performance, safety, and sustainability.
They came to Machinery Analytics with the goal of accelerating their R&D. We started by automating the analysis of SEM images of their cell microstructure.
Over the last year of working with us, they have gone from 10 to 1,000 images taken and analyzed per month.
This case study aims to demonstrate our capabilities and the impact we have made on the client's R&D and production processes. We have allowed them to thoroughly analyze their cell microstructure, see its effect on product quality, and to instantly visualize important metrics and production KPIs.
Cell microstructure is key to determining battery performance. Before we came along, our client had a single scientist looking at SEM images of cell microstructure, and providing only qualitative feedback on morphology. We have automated that process, allowing quantitative assessment of large numbers of images, saving time and improving image insights.
AUTOMATED FEATURE ANALYSIS
Automated identification & measurement of material surface features
Because of our industry knowledge and work with previous clients, we quickly created custom, accurate algorithms to
identify three features of interest in the client's cell microstructure.
*note that as we cannot share client images, the image is an example
Quantified image features
Then, we quantified the image features to make sense of the data.
This allows the R&D team to better understand their product and its composition.
They can now use the data to quickly spot abnormalities in the cell's microstructure.
As an example, the graphs on the left show how often each feature size occurs. Feature 2's size occurrences seem to vary, indicating to the R&D team to further inspect this issue.
After quantifying each feature, we can now look at how different features relate to each other and production parameters.
Our software's dashboard has also allowed our client to look at different trends in their data, such as between different features and production lots.
SEE TRENDS BETWEEN FEATURES & CORRELATE FEATURE METRICS TO PERFORMANCE
The plot on the right is showing feature size for different production batches (or lots).
By being able to visualize plots like this, the client's production team is able to immediately, and accurately see changes from lot to lot, as well as between different features.
The platform can measure different feature parameters, such as mean, standard deviation, area, length, etc. Clients can customize these parameters to look at what matters most.
Our software also has the following capabilities:
filtering by feature parameters and types, lots, dates, and image types
setting control limits and ranges
ability to see all relevant information once you click on a data point
Our next step with the client is to integrate time-series data from testing and instruments into our platform. This will allow them to immediately correlate production process changes to performance outcomes.
Provided Actionable Insights
Improved Product Quality
Are you facing similar obstacles in your organization?
At Machinery Analytics , we believe that skilled professionals should always have the best tools for the job. If you're ready to save time, money, and to accelerate development, contact us for a demo or to book a call!