Integrated LinePulse: Tracing Failure Dependencies Across Factories

Share On:
LinePulse UI
Remi Marchand    By Remi Marchand
Share On:

By Remi Marchand

Today we are proud to announce a major update to Acerta’s LinePulse

Since its inception back in August 2017, LinePulse has been helping clients predict the root cause of issues at their End-of-Line operations, resulting in improved KPIs and significant cost savings. While this model has solved many of our clients’ needs in the past, we’ve recently noticed that our customers are becoming increasingly interested in the relationships between their data at multiple operations and even multiple factories.

Although Acerta is not new to this kind of thinking (we have analyzed data relationships from a wide range of sources to help our clients conduct predictive maintenance), it was clear that our existing LinePulse product needed significant updates to accommodate this use case.

Logging into the new LinePulse, you will first see a representation of your entire assembly line. A quick glance at this “Line Graph” will show you information pertaining to the health of your assembly line; the color of the operation indicates whether that operation is healthy (ie. performing as expected) or not*, and pass/fail statistics can be viewed by hovering over a single operation. We expect that this view of your assembly line with feel natural and familiar and that, by extension, so will Acerta’s AI-driven findings that we overlay on top of the graph (the curved, red dotted lines).

These findings are called “result edges” and they represent the relationships that Acerta has discovered between upstream (or source) operations and a downstream (or target) operation. The target operation is chosen from the set of End-of-Line operations in collaboration with the client, then every operation upstream of the target becomes a candidate source operation. Next, our machine learning algorithms identify the top 3 source candidates contributing to the failure at the target and these get displayed in our LinePulse dashboard with weights that indicate their relative importance.

Clicking on an individual result edge opens up a view of the significant signals identified as part of this result. For each of the signals, you will see a visualization that represents the values of the signal as measured at the source operation but with their status at the target operation (represented by green for pass and red for fail, respectively). We expect this should allow our clients to more quickly identify problematic operations that they may have otherwise labelled as okay.

LinePulse Signals

With these additional features, LinePulse is able to demonstrate the correlation between the performances of different operations across the entire assembly line, thus helping you identify the root causes of EOL failures. By tracing performance anomalies and making use of this data, we expect all of our clients to profit from a return on their investment in digitalization and connectivity, without being overwhelmed with growing volume and complexity of their data.

*(i.e., exceeded thresholds set by the customer)


Software Internship Advice from Acerta: What We Learned as Interns

Sadly, all good software engineering internships must come to an end. [...]Read More... Read More

Acerta   By Acerta

Artificial Intelligence & Industry 4.0: 5 Manufacturing Applications for AI

From predicting product and equipment failures to building better robots, Industrial AI is on the rise. [...]Read More... Read More

Ian Wright   By Ian Wright

The Automotive Data Challenge: Enter the Colosseum

Industry 4.0 is the dream of having your finger on the pulse of your production line at all times. But...... Read More

Jean-Christophe Petkovich   By Jean-Christophe Petkovich

Migrating from AWS to Azure: What We Learned

Cloud migration can be intimidating, but there are ways to smooth the transition. [...]Read More... Read More

Matthew Van Boxtel and Alex Liu   By Matthew Van Boxtel and Alex Liu

AI in the Automotive Industry: An Insider Perspective

Contrary to popular belief, the most exciting application of artificial intelligence in the automotive industry isn’t autonomous vehicles—it’s manufacturing. [...]Read...... Read More

Luke Richard   By Luke Richard