A blog by Oleg Shilovitsky
Information & Comments about Engineering and Manufacturing Software

Will machine learning eliminate part numbers?

Will machine learning eliminate part numbers?
Oleg
Oleg
29 February, 2016 | 4 min for reading

machine-learning

Part Number is a fundamental element of any identification mechanism in product development and manufacturing. The debates about intelligent and non-intelligent part numbers are unstoppable like a wildfire. Back in time when the most updated bill of materials was on the cork board in shop-floor, people memorized part numbers. I believe new data management technologies can provide more part number intelligence to help selects parts and components. The brutal reality of engineering and manufacturing – both intelligent and dumb numbers are needed.

Is there a better way? What can be a potential alternative to complicated part numbering schemas and endless debates about how to classify parts? I think we have a chance…

The power of cloud computing paradigm can open new ways to identify information. Yesterday news from Google about PlaNet development are fascinating. Google is on a heavy mission to recognize the location on the earth based on the picture. Navigate to the following MIT technology review article to read more – Google Unveils Neural Network with “Superhuman” Ability to Determine the Location of Almost Any Image.

Here’s a tricky task. Pick a photograph from the Web at random. Now try to work out where it was taken using only the image itself. If the image shows a famous building or landmark, such as the Eiffel Tower or Niagara Falls, the task is straightforward. But the job becomes significantly harder when the image lacks specific location cues or is taken indoors or shows a pet or food or some other detail.

Today, that changes thanks to the work of Tobias Weyand, a computer vision specialist at Google, and a couple of pals. These guys have trained a deep-learning machine to work out the location of almost any photo using only the pixels it contains.

google-pla-net

You can play www.geoguessr.com. Give it a try—it’s a lot of fun and more tricky than it sounds.

What’s next in computing article by Chris Dixon speaks about maturing of multiple technology over the course of last decade and moving into product development phase that can take advantages of these technologies. You might find few interesting examples there. It brings several amazing examples of technological achievements that were available only in Hollywood movies.

My favorite example is real-time object classifier developed by TeraDeep.

TERADEEP develops Deep Learning Software and Hardware solutions to accelerate the runtime of Convolutional Neural Networks and Recurrent Neural Networks resulting in more scalable solutions for datacenter applications.

The following two examples can give clear connection between past science fiction and reality of technologies today.

tera-deep-classifier

Terminator Movie

Terminatormovie

It made me think about problem of identification turning into the problem of object recognition. You might think about it as a next step after VR technologies. But at the same time it has a potential to replace VRs with  more advanced technologies.

I can see some signs of machine learning development happening with the work done by CAD vendors today. Here is one example I captured from DEVELOP3D article sponsored by Autodesk – Design & machine learning. It speaks about organizing graphical content.

autodesk-design-graph

Here is the passage explaining the problem design graph is supposed to solve.

Organizing design data is a significant challenge, according to Haley. “After all, design data is inherently graphical. It’s not text. And it’s hard to search for something that’s not text.” 

So how should you organise it? Haley and his team at Autodesk are working on a solution. Over the past four years, they’ve used machine learning to create a system that can categorise design data without human assistance and build design taxonomies, so when you need a certain design, you can find it.

The product, called Design Graph, will become available to the public for the first time later this year as part of Autodesk’s A360 cloud-based design and collaboration platform.

What is my conclusion? For very long time, meta-data was the ultimate way to mark every digital or real time object for the future recognition. Part numbers in the design is just one example. There are many others. We are coming close to the opportunity to eliminate meta-data identification and shift to the era of product recognition. Just my thought…

Best, Oleg

Picture credit MIT article, Chris Dixon blog and DEVELOP3D

Image courtesy of jesadaphorn at FreeDigitalPhotos.net

Disclaimer: I’m co-founder and CEO of OpenBOM developing a digital network-based platform that manages product data and connects manufacturers and their supply chain networksMy opinion can be unintentionally biased.

Recent Posts

Also on BeyondPLM

4 6
17 March, 2011

I’m watching closely everything that happens around with Open Source. The world of Open Source is changing all the time....

11 December, 2009

I got a comment on my blog yesterday stating “back to basics”. Why do we discuss advanced stuff at the...

22 March, 2016

Engineering.com article Winners and Losers When Industry Giant Bosch Consolidates CAD and PLM shed some lights on the recent announcement of...

5 May, 2019

My attention was caught by CIO article – The digital transformation debate: It’s about people AND technology. In many voices...

12 April, 2017

AI and Machine Learning are trending these days. It is revolutionizing the world of computers and make possible to discover...

18 August, 2009

Another prompt today. Oracle is devoting two full days and 70 sessions at the upcoming OpenWorld conference to its Primavera...

2 June, 2009

I think that I’m not exaggerating by saying that every conversation about “collaboration” last week started from  the Google Wave...

6 March, 2019

User interface or how we more often call it these days “user experience” (UX) is tough. Enterprise systems, PLM and CAD...

18 July, 2019

Have you heard about low-code development platforms? You better pay attention to low-code, since this cool buzzword and actually tools...

Blogroll

To the top