Cognite Data Fusion®
Transcript of the video on how Cognite Data Fusion provides simple access to the complex industrial data
As part of the 4.0 Solutions community, I wanted to do my part in helping raise awareness of the most impressive companies in Industry 4.0. So, I created a word-for-word transcript of this video by Cognite Data Fusion, which explains how they provide simple access to complex industrial data.
It took a while to eliminate all the errors in the automated transcript. But it is my hope that others interested in learning about Highbyte now find and consume this content more easily.
If you are keen to learn more what Cognite is doing, I recommend you visit the Cognite website, where you can get all your questions answered!
The source video is here:
Transcript
Most data platforms today, still, they only gather the data. So, they take the data, put it into a data lake, or maybe into a data warehouse, but they don’t really connect it so that it is usable. That means that still 80% of the time for a data scientist is spent on cleaning the data, connecting the data, and not doing valuable work, not doing actual data analysis. So, we need a new type of software that helps get this data into production for production solutions a lot quicker, also to scale it, so we get actual value from it across the organization.
Data Silos
Data is sitting in silos. It is sitting in different parts of the enterprise. It’s also sitting outside the enterprise. When real-time data is fed into data lakes or applications, it sits there and becomes static. So, the opportunity in digitalization is to harvest data on a real-time basis. Contextualization is making data speak human, and that means that we put the data into context. If you wanted to go to a restaurant, you can go on an online map site, you can find out when the opening hours are, that was captured from the homepage. Then you can see where it is, from a mapping solution, and you can see reviews from other types of people. We don’t really have this for industry.
Cognite Data Fusion
Our software, Cognite Data Fusion, is built to solve this fundamental data problem for industry. Cognite Fusion builds knowledge graphs for industrial companies, whether in oil and gas, manufacturing, or powering utilities. We use artificial intelligence to connect all of the different data sources, so that you can see all of your data in one place. We harvest data from different industrial silos, be it engineering, be it operations, or ERP data. Then we process it, we contextualize it, and we drive insights for our customers that makes them more operationally efficient.
More Data, More Power
The beauty of all this is that the more data you put in, the more powerful it becomes. When you add current sensor values, when you add emissions data, you can start to optimize the performance and make your solutions more sustainable. You can build and deploy solutions 10 to 20 times faster, and it also means that more people, the people who aren’t data scientists, can also build data-driven solutions and get more value out of their data.
Industrial Data Ops
Industrial data ops is a new way of managing data in the industrial sector. Basically, there are three steps. The first is to make your data available. You need to identify where it is, how to get it, how to store it for later use. To do this, we use extractors to get all types of industrial data types, from time series to documents to visual data, from different source systems, whether it’s operational, IT, or engineering systems.”
The second is making your data useful. We take all the data that’s been captured, and we use AI-powered contextualization to create relationships between the different data sets and keep track of it as a flexible knowledge graph. The third is making your data valuable. The flexible data graph provides a solid foundation for making digital twins agile, adaptable, and efficient. And on top of that, available to all the hearts and minds across the company, enabling all business users with insights to make better decisions, and the ability to become a solution creator themselves, all in a scalable way.
Flexible Data Graph
That’s also where we really saw the power of Cognite tech. It was that as soon as we got the data out, it was immediately available for the key people in that organization. And it’s like, ‘Wow, that’s amazing! We can actually see what’s happening in our plant at the level of granularity that we’ve not been able to do.’ And then suddenly, we see amazing things happening with uptime, with resource utilization, with capacity utilization, without us having actually even dealt with a use case other than just getting data in the hands of the right people.
A Digital Twin is a digital representation of something that exists in the physical world. Typically, that is taking data like two different data sets, it might be a 3D model, it might be sensor values, and then putting those together. The benefit of this is that you can see how your machines are operating, and you can see them in the way you’re used to as a person.
So, Cognite Data Fusion accelerates the building of a digital twin. So, we will take this data, grab it from the source systems, populate the digital twin automatically using machine-based learning, and also artificial intelligence.
Improved Operations
It’s important to note that the digital twin is not the end goal. We use the digital twin to improve operations. So, we cut time for planning, we reduce maintenance because we see trends, we also can make the operation more efficient, and then, of course, as you use less energy, we can also make it more sustainable.
Access to Data
The key thing that is different about Cognite is that it really doesn’t care where the data is coming from. So, it provides you with an access to data independent of data source. That technology is really cutting edge.
I can’t really see that there are any competitors out there right now, able to provide what Cognite is providing.
Industrial companies face what seems like contradicting goals: they have to produce more, whether it’s energy or goods, but at the same time, cut emissions and waste. The truth is, that it’s possible for industrial companies to achieve both. Taking control over industrial data will enable legacy industries to become more sustainable, and emerging industries, such as renewables, to scale and become more profitable.
Conclusion
Companies have to assure that every industrial asset can reach its fully digitally optimized potential on efficiency, profitability and sustainability.
The next five to ten years are the most defining. The same way the industrial revolution changed the entire infrastructure of how goods were manufactured, procured, and delivered to consumers, I believe that is the revolution underway today. And it really manifests itself when you will see more socially, more ethically responsible production and availability of goods for our consumers. And for that, digitalization is imperative. Smart utilization of data is required to do that. And I’m really optimistic about what happens on that front over the next five to ten years.
