Stanley Black & Decker scales AI solution with flexible industrial data infrastructure
What You Need to Know
Stanley's AI solution predicts potential failures and improves operational efficiency
Solution meets stringent IT requirements from customers
Supports up to 5000 fastening robots per plant
Introduction
Stanley Black & Decker is a leading supplier of automotive fastening solutions such as riveting and spot welding. To improve operational efficiency and predict potential equipment failures, Stanley's data team built an AI solution that collects data from plant floor equipment and uses AI to generate world-class predictive maintenance results.
One of the key challenges Stanley faced when scaling its AI solution was scaling its edge data pipelines. Since data is collected directly from automotive assembly lines, Stanley had to meet the stringent IT requirements from its customers, work with various different network protocols, overcome unreliable and frequently-changing data schemas, and support up to 5000 fastening robots per plant.
Problem
Stanley needed a flexible and scalable edge data infrastructure that could meet the unique requirements of its automotive customers. The solution needed to be able to collect, clean, validate, transform, and engineer data from a variety of sources, including fastening robots, sensors, and other industrial equipment. It also needed to be able to support a variety of network protocols and handle unreliable and frequently-changing data schemas.
Solution - Industrial Data as a Service
Stanley partnered with Prescient to build a flexible and scalable edge data infrastructure. Prescient's distributed low-code data software and Industrial DaaS solution is specifically designed to collect, clean, validate, transform, and engineer data from edge devices. Prescient also has extensive experience working with edge data and on-premise IT requirements.
Results
Prescient's IDaaS solution enabled Stanley to install production-grade edge data pipelines at new sites within one week. Prescient's solution also offers the flexibility to support nearly any network protocol or data schema, which is well-suited for automotive customers who have very different network and data requirements.
Conclusion
Stanley Black & Decker's case study demonstrates the importance of having a flexible and scalable edge data infrastructure when deploying AI solutions at scale. Prescient's solution enabled Stanley to meet the unique requirements of its automotive customers and scale its AI solution rapidly.
If you are facing similar challenges to Stanley Black & Decker, schedule a demo now to learn more about how Prescient can help you build a flexible and scalable edge data infrastructure for your AI solutions.
Amir Kashani, Director of AI and Digital Product Development at Stanley Black & Decker