SAG_Аnalytics_880x440px_Mar21All too often in Internet of Things (IoT) discussions, the topic keeps coming back to value - but how do you get value from the IoT?

Organizations frequently start an IoT project without a clear idea of what the primary goal should be, or even whether substantial value lies ahead. Envisaging these benefits ahead of time might just help shape decisions about your plans and usage of IoT.

The true value is not in the IoT connected devices and sensors, but in the data they collate. You need accurate, relevant data to drive every business decision. And the value of that data comes from analytics. Analytics provide insights for innovation, new business models and efficiencies. They provide the ability to make better decisions.

This is often overlooked as companies set out and focus mainly on the technology aspect of connecting devices to a platform. It’s something that businesses begin to realize at a certain stage of maturity, once they are six months or so into running a project and have historical data which can be analyzed.

Analytics can be divided into three broad categories: historical analytics, which help you understand what has happened; real-time streaming analytics, which help you understand what has is happening now; and predictive analytics, which make it possible to understand what is likely to happen in the future. (Visual analytics are another interesting category, which can apply to all three, which I will cover in a future post.)

Let’s look at the value that different companies have gained from each of these different examples – it might give you some ideas and shape your plans on how your data might start to provide value.

Streaming analytics for instant actions on real-time data

Streaming analytics is often a starting point in using data to gain business value. Streaming analytics takes live data that is coming in from different sources of IoT “things,” analyzes it the instant it is measured and can take an action based on that analysis.

  • This might be sending a text to an engineer to alert them to an equipment failure, or it might be monitoring the temperature on a machine and stopping it before overheating.
  • Another good example is in parks’ waste management; streaming analytics can detect when a bin is too full and needs emptying. This saves time – workers don’t have to check all the bins – and avoids mess.
  • In fleet management, streaming analytics can highlight not only the location of vehicles and identify any off-course vehicles, but also report back on the condition of what is being transported.

Improved production process efficiencies with historical data trends

Historical data can provide insights into why an incident happened and how often, helping to improve efficiencies in production processes. Analytics software helps indicate possible root causes, so similar behavior can be avoided in the future.

  • As an example, one company had difficulty controlling a continuous process for producing a chemical used in manufacturing. The process tended to swing between operating points, and trimming the control based on lab analysis led to energy and production loss. This customer spent months trying to establish a good data model to solve this problem. In the end, it was solved within hours using TrendMiner historical analytics product. The result? Improved production efficiencies, saving around €2 million per year and a reduction in energy consumption for the purification cycle. 

Predictive analytics through long-term and real-time data

  • An engineering company that develops and tests systems like combustion engines, batteries and fuel cells wants to provide its customers with better performance insights. The company combines real-time streaming with historical IoT data. It puts its operational data into a data lake and gives the company’s data scientists access to the historical data sets. Based on the analysis, the company recommends how its customers can improve operational performance and save money.
  • For its marine customers for example, the company can recommend routes that have less turbulence, faster travel and use less fuel. This provides a whole new competitive advantage in their solution, that puts them on front of others who can’t provide such insights – which can substantially support the sale process, as well as improve customer retention.

Automotive production-line improvements using historical data

  • Another company builds machines that adds fluids to cars on the production line. The solution runs on an industrial PC in the factory—in the hands of production planning staff. The company hooks up the machines to all parts of the car that need brake fluid, oil and washer fluid, runs pressure tests, and then uses the data to plan for future car production. Insight into the average time it takes to fill a model with similar capacity helps in planning production time and fluid requirements. It can reduce waste, downtime and bring about fewer errors, all benefitting the business in many ways.

Whether it’s using real-time data to analyze and act upon live data from sensors and devices, historical data or a combination of the two, data analytics in IoT will bring about impactful benefits to your business.

Make better decisions. Click below to learn how you can use analytics to innovate and gain insights from your data – and get real value from IoT.

Get value from IoT



    Most Popular Blog Posts