Data is the new oil!

For many years, oil was the main economic driver. This has now changed thanks to the ecological transition. Oil is now just one of many elements that are important for ensuring economic success. The digital transformation has turned data into the new oil. Data from machines, production processes, ERP. A deluge of data. 

emnos helps you process and understand this data to create a solid foundation for making effective decisions that will determine the economic success of your business.

Shampoos or screws. Data is data!

We have over 15 years of experience in processing, analyzing and providing recommendations for action. This gives emnos a unique understanding of how to harness the potential of data for the commercial success of your business. In collaboration with the specialists at ROBUR, we develop bespoke solutions based on our high-performance cloud platform.

What does successful data utilization mean for industry?

• Improved efficiency
• Higher machine availability
• New business models

Our approach: AI+EQ

Our AI+EQ approach is what makes us different. We start with our scalable & cloud-based industrial analytics & AI solutions, which have a high degree of data security. We combine these with the human touch – EQ – our data and industry experts from throughout the ROBUR group. Working with data for more than 15 years has taught us: Without human expertise, machines alone cannot create sustainable added value! It is the combination of state-of-the-art AI technology with the experience of data engineers and mechanical engineers that enables real insights to be gained from data. And these insights contribute directly to the success of our customers.

Some examples of our work:

The customer’s problem

A producer of concrete slabs got in touch with emnos as their systems had been suffering a considerable number of unexplained faults and outages for some time. These problems particularly affected one process within the machine resulting in high expenditure for repairs and spare parts and accordingly extensive downtimes.

emnos received and analysed a data pool consisting of minute-by-minute measurements from a multitude of sensors, times and descriptions of fault messages and interventions performed by maintenance technicians over of a period of 3 years.

The challenges

The customer’s description of their problem was fairly indeterminate, being not much more than “our machines keep breaking down”, “our technicians are snowed under” and “something’s always going wrong with this process.”

No data-driven investigation into the cause of the problems had been conducted up to that point. emnos had no specialist knowledge of the system.

Our solution

Data Insights

Basic analyses, such as looking at the occurrence of fault messages over time, allowed initial patterns to be identified. Contrary to the customer’s expectations, most faults occurred in the middle of the week and not at the end of the week. 

This led us to discover that it was not only the machine affecting the frequency of faults, the type of concrete slab being produced also had a significant impact. This had previously not been considered as a factor.

Anomalies drew attention to one particular process. In-depth investigation of this process identified the exact sub-process that was causing the majority of the faults. Furthermore, we identified data acquisition gaps that made a more in-depth root cause analysis impossible.

The high workload of the maintenance technicians could be explained much more clearly by analysing frequent sequences of interventions – recurring patterns of maintenance steps carried out in sequence. In this way, we identified specific optimisation potential with regard to automation and standardisation of operation and also highlighted areas in which improved training for maintenance technicians would be of benefit.

The customer’s problem

A provider of district heating using geothermal energy wanted to understand how their customers (private and commercial) were consuming the heat supplied. 

Their customers react differently and with different reaction times in response to changes in the outdoor temperature. By looking into the response patterns of their customers, the provider was better able to plan the use of expensive secondary energy sources for periods of peak load (e.g. in winter), predict and anticipate customer demand and to plan their capacity requirements for future network expansion in greater detail. 

The challenges

No data-based diagnoses had previously been performed. This meant that the first challenge was to structure and check the data. Until this point, the data had been collected in wide range of different formats. 

In some cases, system modifications had resulted in changes to the output format of measurements. The actual analysis had to find out by how much and for how long the temperature had to vary to cause a change in customers’ consumption behaviour as well as the timeframe during which this occurred. We also had to account for that fact that customer behaviour always varies greatly depending on the day and time.

During the night, almost no changes can be seen and weekends, weekdays and public holidays also produce very different patterns of consumption.  

Our solution

The basic data auditing routines used by emnos identified all anomalies in the data and removed them to produce a clean dataset. This allowed us to determine significant temperature changes in terms of size and duration.

Using the emnos analysis platform, we investigated all possible scenarios for delayed customer reactions linked to these temperature changes (how long before there was a response, how long did the response take). We determined the scenarios with the highest correlation between size of temperature change and the change in heat consumption.  

The provider can now use these findings to estimate the expected effects of predicated local temperature changes on customer demand. They can also mitigate the impact of peak demand periods by supplying customers who display the most extreme reactions with additional heat ahead of time Furthermore, the findings of this analysis can be used to plan future district heating systems. 

emnos Digital Maintenance Platform

A key success factor for digitalisation is the scalability of the chosen solution. This is especially true when it comes to data: all relevant information must be available at the right time and delivered in a user-friendly way. Only then will people be delighted to work with data. And it is the only way to create sustainable added value from data.  

The emnos Digital Maintenance Platform is a cloud-based, highly scalable solution for a wide range of different requirements in the industrial sector. Data protection plays a key role in our solutions alongside a wide variety of AI-based analytical models and state-of-the-art UX/UI. We have more than 15 years of experience working with personal data and all of our systems meet the latest data protection and privacy requirements. GDPR conformity and various security certifications have long been a core part of our business.