Tag Archive for: TrendMiner

You are here: / / TrendMiner

Posts

Presenting E2COMATION Results at the BTW 2025

/0 Comments/in , , , , /by

I’m glad to have had the opportunity to present our paper at BTW 2025 last week. In the paper, we could outline one of our main contributions in the finishing European research project E2COMATION, how we could enable plant workers to perform their own (visual) analytics on shopfloor data for smart manufacturing. With my colleagues Harald, Mohamed, and Kanishk, it was a special experience to participate in the conference.

The BTW conference is the most important database conference in the German-speaking area. Every two years since 1985, it has served as a central forum for the exchange of information between scientists, practitioners, and users on topics of database and information system technology. Focus topics are data integration and extraction, provenance management, data protection, scalable big data analytics, hardware technologies on a small scale up to cloud computing as well as new application areas and architectural approaches for the support of machine learning in the context of artificial intelligence.

More information about our paper, titled “Enabling Smart Manufacturing with Visual Analytics for Plant Workers”
Abstract: Smart manufacturing is increasingly making use of visual analytics to optimize production or to identify early problem signs. However, current solutions and approaches require professionals, especially from the data science area, to make use of it, which is not affordable for most production companies. In this paper, we describe first a best practice to sensorize plants from the wood and beverage industry to enable smart manufacturing in general. Second, we describe a new approach that aims at providing easy-to-use visual analytics functionalities that are designed to be used directly by plant workers. Plant workers usually have encompassing experience in the production and the plant, but lack of computer experience and corresponding mathematical knowledge for data analysis. Through lowering the barriers for plant workers in performing data analysis of the IoT sensors with simplified and almost automated analysis functions would give them the ability to gain insights into the production and achieve similar production optimizations and problem preventions as data science experts could. The main contributions of this article are on the one hand the best practice of how production lines of the wood and beverage industry could be made ready for smart manufacturing, but also an approach that enables non-data scientists, especially plant workers, to perform sufficient analysis about optimal production settings and early problem cause identification.
DOI: 10.18420/BTW2025-33

2nd Project Review in E2COMATION

/in , , , , /by

Last week we had our 2nd project review in the now three-year ongoing European research project E2COMATION. As usual in such projects, the last view month required a lot of attention to complete the last work actions, deliverables, and of course the administrative reporting. And now it was to show the achievements to the EU project officer and the reviewers.

After the preparation day, we had a full day to show all our achievements and answer questions. As might be noted, in such a big project with big industrial actors as use-cases there were a lot of challenges to be solved and also alternative strategies and solutions to be elaborated.

As Software AG we are responsible for the two tasks. The first was about real-time analytics together with our solution APAMA, which my colleague presented. The second part was presenting the self-analytics results for what we use TrendMiner and this was on me. The goal of this task is to give production workers, who are not data scientists, the ability to analyze IoT data from the shopfloor and identify problems, solutions, and optimizations. Together with some principle architectural information I also gave a demo to show how the solution is practically used in the use cases.

E2COMATION Year-end Race

/in , , , , /by

The final steps in the race to the end of the year in the E2COMATION project are underway and the major milestones have been reached. Time to take a deep breath and review the results of the project.

I started working on the E2COMATION project about 1.5 years ago and since then there have been many challenges to overcome, first and foremost a common understanding of how all the technologies paired with the know-how behind them must ultimately work together. It started with the first executable individual small demos, then extended demos, then the first live connections, and now there are finished prototypes in the project. It is always exciting to see how the work, especially in the final phases, increasingly comes together to form an overall picture and how the functional possibilities increase exponentially.

I am particularly pleased to see how much Software AG‘s technologies, especially APAMA and Trendminer, create great benefits here. This is always getting very clear when application partners use the technologies and approach you with specific feature questions. You can see that the technologies are in practical use and now it is time to turn the technology functions into production results. Which is also the outlook for the coming year in the project.

I would like to take this opportunity to wish the entire E2COMATION team a peaceful Christmas season and a happy New Year.

3rd Year E2COMATION Project Meeting in Milan

/in , , , , /by

Last week we had our 3rd year E2COMATION project meeting in Milano. The focus laid on finalizing the implementation in the four use cases. Meanwhile, the SAG’s self-analytics solution Trendminer is used in the three use-cases KEAS, MAHOU, and ROYO to have a sensorial overview of what’s happened at the production, but also to identify possible opportunities to optimize the production and to identify anomalies, which might be solved, corrected or at least send warnings automatically with the SAG’s real-time analytics solution APAMA.

As a significant milestone, Trendminer is already fully connected and configured to consume the KEAS plant data, where we already have started discussing and preparing analysis views for certain behaviors that require some optimization and cause analysis. It is impressive to see how a graphical tool like Trendminer with simplified user-friendly analytical functions could help to understand certain behaviors at the plant and in the IoT date and find potential optimization strategies together with the domain experts of the company.

E2COMATION Self-Analytics Platform with TrendMiner

/in , , , , /by

As a response to our E2COMATION project’s masterclass workshop at hub.berlin last week, I wanted to share some shown features of TrendMiner to analyze IoT data for Smart Manufacturing. As a tool that is also designed for non-data scientists, it gives a lot of analytics capabilities to production experts and engineers and simplifies the use of production data on a practical level.

For more information about TrendMiner analytics platform, please visit: https://www.trendminer.com.
For more information about the E2COMATION project, please visit: https://e2comation.eu.

Showing TrendMiner at E2COMATION Consortium Meeting

/in /by

Yesterday we could show at our E2COMATION meeting in Milano to the KEAS use-case the results of the very first live data integration into TrendMiner to enable analysis in perspective in energy saving and optimization. After being part of the Software AG research team for almost half a year, this is not only a personal milestone but also a solid project milestone since we can now overserve the entire production plant regarding energy consumption.
 
With TrendMiner, the self-analytics platform, employees at KEAS should be able to identify potentials to identify among others energy savings and process optimizations. So, the solution intends to empower process engineers, plant managers, and other non-data scientists to optimize operations all the time, anytime, using a new generation of model-free self-service industrial analytics, as a means to analyze operational performance without data modeling, as well as to recognize cause-effect-relationships and root causes, and create early warnings for.

Presentation at E2COMATION Consortium Meeting
Group Photo of the E2COMATION Consortium at the Y2 Meeting