experience research. design. digital strategy.
homa-appliances-_XDK4naBbgw-unsplash.jpg

Stanley Black and Decker: machine learning and manufacturing

machine learning and manufacturing

Machine learning & artificial Intelligence with Stanley Black and DEcker

 

The Project

Manufacturing environments are complicated places where milliseconds matter. The machines used to make the products we enjoy range in age from brand new to 80 years-old. Attaching a network of sensors to these machines creates a window into the process that can eliminate slowdown and stoppages by using early warnings and intelligent maintenance reminders. The end goal is the virtual elimination of waste in the manufacturing process.

The Challenge

Through a rigorous research process we identified personas, their jobs, and opportunities in need of support. In my role as UX Lead I was asked to distill those findings into a series of applications that allowed for the monitoring of complex processes that has as it’s goal saving time, money, and frustration in the manufacturing process.

The Satisfaction

 Critical breakthroughs in understanding the wide array of people in an ecosystem always bears fruit. With that foundation the team was able to design multiple systems that allowed for more efficient management and control of the manufacturing process. The tools we designed reduced downtime in the test plant 25% in the first deployment. It also boosted on-time maintenance events by 75%.

actionable personas

Deep conversations about individual goals, incentives, and environments make design easier.

ML Model training

Worked with team to define key data elements and key opportunities for enhancement.

industrial UI

This environment required an at-a-glance view by an array of folks with different skills and interests in the manufacturing process.