Penn State Beginning $1.5 Million Smart Manufacturing Project


In the article Researchers to Begin $1.5 Million Project for Manufacturing Industry, the author explains how a teams from Penn State, Case Western Reserve University, GE Global Research Center, and Microsoft are collaborating on a smart manufacturing research project.  The project aims to help machines internally recognize signs and wear and fault conditions through the use of cloud-based wireless sensing and prognostic system for monitoring machinery health conditions.  The overall goal is for the machines themselves to make intelligent decisions about fault detection and proactive maintenance scheduling, hence smart machines.  The use of the IoTs, cloud computing big data analytics, and machine learning allows this smart ecosystem to exist.

The project brings experts from across academia and industry together.  On the academic side there are experts from the fields of industrial and manufacturing engineering and mechanical and aerospace engineering.  On the industry side there are experts from GE’s industrial internet of things global research center and senior managers from Microsoft.  Penn State will be hosting the project, but the project is 50% funded by Digital Manufacturing and Design Innovation Institute (DMDII).  DMDII, which was founded in 2014, is funded by the US department of Defense along with number of other entities with the purpose of digitally transforming American manufacturing.

The plan is to begin in February of 2017 and run the project for 18 months.  The actual workings of the project will be done in FAME (Factory for Advanced Manufacturing Education) which is a 10,000-square- foot integrated high-bay laboratory for teaching and research.  Senior Research Associate Wu stated the overall purpose of the project as “The overall goal of this research is to establish a generic framework for real-time process monitoring, diagnosis and prognosis for smart manufacturing using cloud computing and big data analytics.”  It’s easy to see that with lofty goals as described above, this smart manufacturing project could help transform the industry.  Only time will tell how successful the project becomes, and possibly even more important, how the results are viewed and accepted by the greater manufacturing industry.


Do you believe the team will be successful at creating a generic framework that can be used by a majority of the manufacturing industry?

Do you think the project will stay within budget and finish on time?

What are your thoughts on the fact the Department of Defense is funding part of this project?


Big Data is Allowing the Tail to Wag the Dog


In the article Is Data the New King of Manufacturing Technology?, the author wishes to establish a relationship that fits the phrase “the tail is wagging the dog.”  In broad terms, it is a relationship where a secondary offshoot actually becomes the main operation or begins to run the main operation.  In this case, manufacturing information technology is the dog and the tail is big data analytics.  Big data analytics is quickly becoming enterprise platform of the future, and those that which to stay at the cutting edge of manufacturing need jump in so they don’t get left behind.

In the manufacturing world, data has been collected since at least the 1980s, but in most cases, the data collected was just a byproduct of the process itself.  The data was stored and mostly unused.   As business intelligence tools began to transform the landscape in the 1990s, managers and process owners began to realize more could be understood from all the data collected.  This evolution has led us to the big data analytics of today – the answer to the question of how any part of the process can be improved via analyzation of data.  The Industrial Internet of Things (IIoT) has evolved to be able to capture data from any sensor, equipment, or even phone and send this data to a platform, such as the cloud, to be analyzed and have insights developed.

This data analytics tools, and the profits companies are experiencing given their usage, has accelerated the entire industry forward.  Manufactures are connected on all their platforms and have the ability to trade their assets on a global scale – thus satisfying demand quickly.  This data ecosystem has allowed for personalized processes for creating and delivering products because manufacturers know more about their customers.  With the power of big data analytics, a manufacturer can mine vast amounts of production and customer data to improve and even redesign processes.


Do you believe all this data collection will create more jobs?

Remembering that correlation does not always equal causality, do you believe that some trends will emerge within manufacture’s data that do not actually exist?

With more industries relying on data, do you believe the human aspect of understanding processes may be left behind?

Sensing Change

In a recent article on the website, Shanghai Daily, smart manufacturing and its impact on industry is discussed. Internet-connected sensors, a major facet of the emerging internet of things, is allowing for more efficient machines, lower costs, and more accuracy. Maintenance sensors are now able to monitor machines and robots through sound and provide quick and accurate diagnostics. New scanners are able to read color codes and store large amounts of information. Large industrial upgrades to enormous machines, are now identified by small sensors. In what other ways may these sensors be put to use? How can color coding be used in other functions? Will color coding replace bar and QR codes?

Is 3D Printing Really the Future?

All over the media we are reading about how 3D printing is going to change the manufacturing industry completely. Is this fact a guarantee? The article “The Limits of 3D Printing” ( give a converse view to this new technology. Per the article, “…the economics of 3D printing now and for the foreseeable future make it an unfeasible way to produce the vast majority of parts manufactured today”. Because of this assumption, the author proposes that we “…look to new areas where it can exploit its unique capabilities to complement traditional manufacturing processes”. Building off of this statement, the article also addresses the theory that with 3D printing, global supply chains will become a thing of the past by stating that “this vision does not stack up to economic reality”. One of the widely accepted benefits of 3D printing is that product customization is much easier. Despite this fact, the article states that “… 99% of all manufactured parts are standard and do not require customization”. Due to this fact, “… when customization isn’t important, 3D printing is not competitive”. How much of these ideas are fact? Is 3D printing the future, or just a complement we will utilize for customization? For now, only time will tell.

Specifically Defining Big Data in Manufacturing

In the article What Is Big Data Analytics in Manufacturing?, the author defines Big Data in a manufacturing sense and also examines how big data has evolved in a manufacturing environment.  Interestingly, some of us think of Big Data as exactly as it sounds, a very large amount of data, say a petabyte of data as collected from sensors on an engine.  Big Data Analytics, in this mind frame, would then be the analyzation of this data using mathematical and statistical techniques.  But the author makes a key point – running reports on large data sets does not qualify as Big Data analytics in manufacturing.  If what I’ve just explained does not qualify as Big Data Analytics, then what does?

The article defines Big Data as follows, and I quote,

“Big Data Analytics in manufacturing is about using a common data model to combine structured business system data like inventory transactions and financial transactions with structured operational system data like alarms, process parameters, and quality events, with unstructured internal and external data like customer, supplier, Web, and machine data to uncover new insights through advanced analytical tools.”  This definition is certainly covers all the bases one could think of when it comes to understanding Big Data Analytics in manufacturing.

The transition of older technologies to a Big Data platform is happening right now.  One previous technology for collecting manufacturing data that is currently transforming to Big Data is enterprise manufacturing intelligence (EMI).  The author notes that two of the three ways this transition can happen for EMI is the ability to use structured and unstructured data as well as new analytical tools such as image, video, and geospatial data.

As big data usage in manufacturing continues to mature, it will become part of the IIoT Platform for delivering both legacy applications and Next-Gen systems.  Data will eventually be able to be taken from anywhere and delivered to anywhere while is usability will be simplified so that floor personal can use it.  In a connected, smart manufacturing environment, there is the possibility that any data collected can become useful to the process, personal, and ultimately, the bottom line.


Are most readers familiar with older technologies like EMI?

What do you think of the definition of Big Data as presented by the author?

Has anyone seen the industrial IoTs at work and if so, does this article portray a realistic picture of how manufacturing is changing?

Understanding Smart Manufacturing

In the article What is Smart Manufacturing? the author delves into what exactly smart manufacturing is, as defined by the new technology that has allowed it to come into being.  Smart manufacturing has enabled us to use continuously collected and flowing data to continuously improve processes thus taking some the human error element out of manufacturing.  It’s not to say that the smartest piece in the manufacturing puzzle isn’t still a human because it most certainly is.  It is more a realization that machines can now collect and interpret data themselves (as we have programmed them) so that they almost “think” on their own.

The author points out that some believe we are now in the 4th industrial revolution.  This industrial revolution involves big data, predictive analytics, and the artificial intelligence created using these concepts.  In essence, the data tells us what to do.  Instead of a maintenance cycle that works based on past failures, think of a maintenance cycle that continuously collects data thus giving us indicators before a failure.  Furthermore, the data can let us know what failed as well which increases efficiency.  This connection is known as the IIoT – the Industrial Internet of Things.  The emergence of cheap connected devices, coupled with the availability and affordability of mass computing power, has been the biggest driver of Smart Manufacturing.

Visibility is a big driver in understanding ROI in smart manufacturing.  The processes can alert users via messages on their phones; displays on a monitor, or a number of other ways.  Communication between machine and humans becomes simple.  When the data tells you what to do, decisions normally become easier thus reducing human error, increasing efficiencies in manufacturing processes, and finally saving money.


Will smart manufacturing eventually become so good that actual human jobs are lost?

What safeguards are in place so we know that sensors on manufacturing processes are not relaying operators the wrong data?

As I mentioned in a previous blog, do you believe there is a downside to collecting too much data?


Big Data is Not The Magic Bullet for Smart Manufacturing Improvement

In the article My New Year Wish – Less Hype for Big Data Analytics, More Buzz for Smart Manufacturing, the author examines how smart manufacturing is utilizing big data, but just not to the extent we all thought.  In fact, vast amounts of data are being collected in many new manufacturing processes, but very little of it actually gets used.  The value in new smart manufacturing processes isn’t all the data, it’s the connectivity between systems.  That is, no value is found by trying to mine a stream of sensor data emanating from machines in the plant in the hope of finding some pearl of wisdom.  The real value is streamlining business processes from desktops to machines, across department walls, across tiers of manufacturing operations management, and across tiers of suppliers.

Interestingly, the author cites an article that states that 70% of the data collected during manufacturing processes goes unused.  If this big data was so important, why is so much of being discarded?  One has to believe if there was usage to be found, it would be found by experts in these processes.  Instead of mindless and useless streams of data, emphasis needs to be placed on manufacturing process improvement enabled by integration standards that connect machines, processes, and systems.  Of course some data collection and analyzation is part of this improvement, but gigantic amounts of data are not necessary.

One has to wonder if Big Data is more a buzzword then a useful concept.  There is no denying that manufacturing processes can become more efficient through a more thorough understanding of the process via data collection, but perhaps we’ve overstated how much data we need.  Properly prioritizing the importance of big data usage within innovation is key, and we need to stop looking at the technology itself as the innovation.


Do you think the author has a minority point when it comes to Big Data?

Will there come a time in the near future where we actually begin to collect less data, or will the reasoning of better safe than sorry prevail?

Do you think there is actually any use to all the data that gets discarded?