Turkish wheel manufacturer reduces cost & material wastage using ML
Client
The client is a leading wheel manufacturer in Turkey. They are
major suppliers to world's biggest automobile manufacturers.
Project Context
The client wanted to reduce manufacturing costs by increasing quality
controls. The firm incurred additional manufacturing costs as 8% wheels
manufactured ended up not meeting quality standards which then had to be
scrapped.
Challenges
The firm incurred
manufacturing cost as 8%
wheels manufactured ended
up not meeting quality
standards which then had to
be scrapped.
The objective was to reduce
manufacturing cost by
increasing quality controls.
Solution
Using thousands of variables
collected and stored in an
AWS data lake, SquareShift
built and implemented a set
of real-time prescriptive
dashboards to gain insights
into line performance.
Project Objectives
Reduce raw material wastage by using prescriptive recommendations.
Detect scarps early in the process and save processing time and
money
Solution Delivery
Using thousands of variables collected and stored in an AWS data lake,
we built and implemented a set of real-time descriptive dashboards to
gain insights into line performance, analyze patterns over time, and
comprehend process drifts.
SquareShift created machine learning (ML) algorithms to forecast
faulty wheels early in the process and developed prescriptive models to
suggest process variables that would lower the number of damaged
wheels.
A data lake with real-time dashboards for descriptive and prescriptive
analytics was used to collect and store process variables.
Testimonial
With SquareShift’s ML insights, we’ve significantly reduced waste and increased throughput across the production line
