<img height="1" width="1" style="display:none" src="https://q.quora.com/_/ad/aa0df465f5e145b99c2e3c66e3450b19/pixel?tag=ViewContent&amp;noscript=1">

Ford Motor Company


About the Process

Sheet metal stamping is core function in the automotive manufacturing industry. Historically, identifying the most optimal stamping process for a given part design has been a trial and error and time-consuming task that relies heavily on the stamping engineer’s tribal knowledge and skill level. To address this issue, Ford Mexico began documenting successful metal stamping production runs over a 5-year period. The goal was to capture in-house critical knowledge and best-practices then use that to rapidly train new personnel. 

Their Challenge

Growing design complexity of Ford's designs and non-conventional material types made the stamping process arduous leading to longer cycle times and more scrap material. The goal in this process was to reduce the amount of scrap material, which represented nearly 26% of the total cost to product a stamped part. To do this, they needed to start with compiling data over the 5-year period  in order to gain insights to how they can make their process more efficient.

Our Solution

Leveraging the data Ford collected for over 3,000 stamping processes identified as being
representative of future requirements, Ford’s stamping domain experts and Altair’s solution
architects collaborated to develop an accurate, reliable machine learning model with
Knowledge Studio.

Knowledge Studio offers 15 different machine learning models allowing users to explore,
select and train the model that best fits their data. Using subsets of the data, the team ran
a series of tests to determine which was most effective. With an accuracy rate of over 90%,
the decision tree model produced the most consistent results. In the process, a surprising
– and valuable – discovery was made. In terms of selecting the optimal stamping process,
the most important factors are the overall dimensions and thickness of the finished part.
Alone, these factors are not enough to make a final decision, however, when combined
with all the other datapoints, Knowledge Studio’s machine learning algorithm provided
Ford with results that are close to 100% accurate


The machine learning predictive power of Knowledge Studio proved to be highly accurate and
successful in largely automating stamping process selection. By minimizing manual process validations and rework, more time was available for stamping process engineers to address the most difficult and complex part designs further maximizing production efficiency.

Overall, the projected throughput increased by a factor of three and, increased FTT rates
resulting in reduced rework time – all accomplished without increasing personnel resources. In addition, the Knowledge Studio machine learning model was effective in capturing Ford’s in-house tribal knowledge to support a faster learning-curve for training of new personnel.


TOP: Wasted (or scrap) material represents roughly 26% of the total cost to produce a stamped part. Reducing wasted material
and increasing FTT rates directly benefits bottom line profitability.
BOTTOM: Knowledge Studio streamlined the selection of the best stamping process for metal formed parts.