“The four main parts of any IIoT system are smart assets, data communications infrastructure, analytics and applications to interpret the data and act on it, and people.
Smart assets include machines or other assets with sensors, processors, memory, and communications capabilities. In some cases, these assets may have associated virtual entities or support software-defined configuration and performance; smart assets generate more data and share information across the value chain ; some smart assets will eventually be self-aware or operate autonomously. Over the Internet, data communications between these assets and other entities will often leverage network technologies such as LTE, ZigBee wireless networking, IEEE 802.15-4, and cloud-based computing infrastructure whose storage can meet big data needs. Powerful analytics and related software will enhance asset optimization as well as system optimization. Predictive analytics will be deployed to reduce unplanned downtime. The latest available information generated by these tools will lead to new applications supporting new, transformative business models. Companies will no longer offer physical products for sale, but will increasingly offer products “as a service.” People will participate through access to more data, better analytical tools, and better information, and will increasingly make decisions based on the analysis generated by these resources. Quantitative decision-making will become more common, and “smart” information will be available when and where people need it. But people will also continue to become better connected to each other and to machines and systems through social and mobile tools and applications. “
Obviously, people are the most important part of the four parts of the IIoT system:
Smart Assets: The amount of data we get today from sensors, motors, instruments, etc. is increasing the amount of data we were generating when I started using them 20 years ago. We must learn how to leverage all this data, find useful information and use the intelligence we gain to improve our bottom line.
Data infrastructure: Just a decade ago, networking PLCs or other control systems was uncommon in many industries. Today, that is no longer the case, so we all must be prepared to deal with the deluge of data coming from smart assets.
Analysis: This is where data turns into knowledge. I believe analytics and its applications will revolutionize manufacturing, and those who don’t embrace analytics will be left behind. As I said before, context is key to data, and analysis certainly requires context to be effective. However, only people know what context is critical to enable analytics and make it useful. Analysis does not create itself, people create it.
People: This is the most critical component of all. Even with the emergence of machine learning and cloud-based predictive analytics packages with machine learning content, such as Microsoft Azure Machine Learning, IPLeanware’s Braincube, etc., people still need to fully understand the data to write the algorithms for the above tools. People still need to figure out which metrics have the greatest impact on the business. People still need to shape the data to get meaning from the tools.
One also needs to address the issues shown by the above tools. For example, what we need is not software that actually solves the problem, but people who ask the “why”. Who had even heard of the term “data scientist” in manufacturing or utilities a few years ago? Data science has been around for a long time, but in the past five years, the amount of work in this field has exploded, in Work has exploded in industries that had never considered such a thing. Data scientists are working on problems that didn’t exist just a few years ago. Likewise, people are the most critical component of IIoT.
The right problem solvers with the right data can be a magical combination, and many organizations are so focused on the first three components (intelligent assets, data infrastructure, and especially analytics) that they can minimize the fourth, And the most important component – people. Another assumption some organizations make is that if the same data or information is put in front of multiple people, each person can theoretically have the same impact on the organization with what they see. However, based on their interpretation of information, skills , and experience, this is incorrect. We don’t make these assumptions – we know that getting the right information in front of the right person, at the right time, can make a difference.
Keywords in this article: Industrial Ethernet data transmission terminal
Spanish 
English 
Russian 
German 
Italian 
Portuguese 
French 
Dutch