What Can Big Data Do for Manufacturing?

Sight Machine 2.0 aims to give manufacturers user-driven analytics.

Like ‘Industry 4.0,’ ‘big data’ is one of those terms that sounds so broad as to be vacuous.

(Have you noticed how everyone seems to be selling “solutions” these days?)

But in reality, the concepts underlying Industry 4.0 and big data lie far from the territory of empty marketing buzzwords.

More specifically, the term ‘big data’ refers to data sets that cannot be dealt with via traditional data processing, often involving predictive or user-driven analytics. Understood in this light, big data’s value for manufacturing becomes much more tangible. As an example, consider Sight Machine 2.0.

Industrial-Strength Analytics

Sight Machine Inc. recently introduced a major upgrade of its end-to-end big data platform that is purpose-built for manufacturing. Sight Machine 2.0 has been developed and stress-tested for large-scale deployment across lines, plants and extended supply chains. According to the company, it uses analytics and artificial intelligence to help manufacturers improve quality, productivity and visibility.

(Image courtesy of Sight Machine.)

(Image courtesy of Sight Machine.)

Sight Machine is designed to create a digital twin of a manufacturing plant, combining process and product data into a set of analytical models that mirror machines, lines, plants and supply chains. This enables users to answer a variety of questions, such as:

  • Why has machine downtime risen 22 percent this month?
  • Why is our new line in Indiana 18 percent less productive than an identical line in Michigan?
  • Which production step is responsible for introducing this defect?
  • Why is my scrap cost running 10 percent higher this month?

According to the company, among the major new features in Sight Machine 2.0 are the Global Ops View for real-time visibility across the enterprise, Contextualized Dashboards that can be tailored to the needs of a user or function and the Downtime Classifier, which uses machine learning to determine the reasons for downtime.

“Sight Machine’s Downtime Classifier is a novel use of machine learning and should address what has been a long-time challenge for manufacturers: accurately and efficiently recording machine downtime,” said Matthew Littlefield, president and principal analyst at LNS Research. “This use case should drive quick ROI through better root cause analysis in operations.”

(Image courtesy of Sight Machine.)

(Image courtesy of Sight Machine.)

Sight Machine is already processing billions of data points per week to optimize production at a global network of contract manufacturing facilities. Enterprise customers are also able to add hundreds of machines onto the platform for processing manufacturing data.

For more information, visit the Sight Machine website.

Written by

Ian Wright

Ian is a senior editor at engineering.com, covering additive manufacturing and 3D printing, artificial intelligence, and advanced manufacturing. Ian holds bachelors and masters degrees in philosophy from McMaster University and spent six years pursuing a doctoral degree at York University before withdrawing in good standing.