The $1 trillion dollar question
Follow Us

Inspecting, testing, and certifying equipment and machinery is an essential, if underappreciated, part of the industries that make our current—and future—standard of living possible.  The world we enjoy today feels distant from the industrial revolution; and indeed, centuries have passed since the first machine-driven industries were born. But maintaining where we are today, and enabling future productivity and advancement, safely, hinges on shared industry standards and the dedication and constant vigilance of machinery and equipment experts to ensure proper inspection, certification, and testing is taking place. 

Machinery and equipment inspection is not a check-the-box activity. Inspections help identify minor issues when they are easy to fix to prevent the costs and dangers associated with breakdowns that require major repairs or equipment failure.

Despite current best efforts though, the reality is that machinery and equipment still fail. A recent study looking at just the world’s 72 largest manufacturers found that almost $1T is lost each year to machine failures.

That astronomical figure is just the tip of the iceberg, which begs the question—what can be done to reduce the incidence of equipment and machine failure? That’s a big question.

Let’s break it into something smaller and zoom in on one piece of the equipment inspection process: nameplate data extraction.

Why no one loves nameplate data extraction

Every equipment or machine inspection, test, or certification, requires identifying specific information about the specific machine or piece of equipment. This identifying information is found on the nameplate.

Extracting the right information, such as serial and model number, is typically done from a photograph of the nameplate, taken at the time of inspection. The process of reading each photograph to identify the correct numbers, then correctly entering them into the system, is time-consuming, error-prone, manual, and mundane work.

And it’s work being done by highly-skilled inspectors and engineers, taking them away from the real work at hand: the inspections, tests, and certification assessments and reports. 

Did someone say automation?

Let’s double-back for a moment to the topic of the industrial revolution. For something as mundane and repetitive as nameplate extraction, what about automation and the promise of the 4th industrial revolution?

In the words of the IAP, ‘the Fourth Industrial Revolution is more than a technological leap forward”, rather it is a new era where communication between all materials and people is redefining the possibilities of industry and manufacturing. 

The potential of this great technological leap forward stands in stark contrast to our case of nameplate data extraction, which represents part of a critical process to ensure equipment and machine safety, and yet remains out of reach of basic business process automation. Why? 

Nameplate data exists in images—photographs taken at the time of inspection. That means nameplate data is unstructured, which creates a blocker for off-the-shelf process automation like robotic process automation (RPA), which relies on structured data. 

OK, so let’s apply AI

Extracting data from images is a perfect use case for artificial intelligence (AI). But that doesn’t mean it’s an accessible solution. Manufacturing and industry enthusiastically initiated AI projects to realize the potential of digital transformation only to find themselves reassessing the feasibility of applying AI, primarily due to underestimating the time and resources required to create the data infrastructure that underpins AI models.   

For our case of nameplate extraction, we can see the challenges to building an automated process, starting with building a dataset that requires manual transcription and labeling nameplate image data by highly-skilled staff. And if and when you reach the point where your data is ready, sourcing talent or outsourcing the AI build project means a massive investment in both time and costs. 

Before


The start of an AI revolution / Meet the AI assembly line: human + AI

And now for the good news: there is an “off-the-shelf” AI solution for nameplate data extraction. Super.image [link] represents the future of unstructured data processing by applying the “assembly line” principle to AI. 

To build your training dataset, SuperAI [link] allows humans and AI to work in tandem. Upload images (you can even drag and drop image files), define the data fields you need to identify, and let SuperAI do the work. You can involve your experts at this teaching stage to supervise labeling the training data set to ensure the quality you need.  That’s it. Next, Super.Image takes over, making nameplate data extraction a 2-step automated process, ready to go in a matter of hours.

After


Super. Image makes automating nameplate data extraction easy, reducing process complexity and time by orders of magnitude, while increasing data accuracy, resulting in operational cost savings up to 97%. See for yourself what Super.Image can do in a personalized demo


Manish Rai
VP of Marketing
Featured Posts