This might seem the easiest step, but often it is a question of finding the best way to collect the data. This can be direct from the IIoT devices or via the means of gateways or via standard communication platforms like OPC (Open Platform Communications) or OPC UA. If the data is available via a database, the data can also be collected from those sources.

When data comes from one source or multiple sources, it might be that the data is not directly usable in its original form. Sometimes data is delivered in a format that must be transformed to be usable, other times the data is delivered as individual records of a string of data patterns and so on. Due to the nature of the data and the different data sources, it might be that data must be normalized. It might also be that some data needs to be enriched to be usable. This step in the process is the data transformation stage. The content stays the same, formats are adapted, and data is readied for storage and usage.

Storing the data can be done in the cloud or on-site, depending on the capabilities permitting the transfer of the data to the cloud. Depending on the nature of the data, we prefer to store most data in time series databases. As the name implies, a time series database (TSDB) makes it possible to add, process, and track massive quantities of real-time data with lightning speed and precision efficiently and continuously. A time series database stores data as pairs of time(s) and value(s). By storing data this way, it makes it easy to analyze time series, or a sequence of points recorded in order over time.

The internet of things (IoT) concept and its associated sensors that constantly collect and stream data underlie several modern workloads such as powering industrial applications, predicting sales demand, analyzing temperature readings, and providing medical information from wearable devices. As you can imagine, the data produced is staggering... and a time series database is more adapted to this kind of data.

Data analysis happens more and more using data models and Artificial Intelligence. Data analytics and artificial intelligence make it possible to link data to gain insights on processes, grow the business, and optimize the speed and quality of production. Data are necessary to feed algorithms, but you need to be able to transform any data you collect into useful information, otherwise it is more likely to just waste resources and add even more complexity. A useful process to draw causal inference from big data could be divided into the following stages:

• Find interesting patterns in the data
• Explain those patterns (possibly using experimental manipulation to understand the link between cause and effects)
• Use those patterns and explanations.

Using those stages, we build models that can provide the necessary insight in the delivered data and provide the information required to do the job.

Once the result is known, we visualize it. We use different kinds of dashboards to present the information in a format that is ready to use in an industrial environment. This can go from simple dashboards to complex presentations of the information to use.

Once you know how to do it, you either need to find a platform that can help you build your case, or you can look for a partner that can assist you through the process. With a background in monitoring and collections of large data sets, we believe that we have the necessary knowledge and expertise to help you in the following domains:

• Collect your data (from heterogeneous sources)
• Normalize your data
• Store your data either on-site or in the cloud
• Analyze your data using statistical and AI models
• Visualize your information

• We build your custom AI models
• We train, maintain, and improve our AI models
• We provide monitoring, alerting, and reporting

• Integrated monitoring of OT/IT infrastructure and applications
• Own time-based visualization platform and agent technology for real time data capture, automatic discovery, alerting & notifications, and local actions