About the Hackathon

Look forward to a varied weekend full of challenges, networking and exciting insights into our work. Together with our staff, the Fraunhofer Project Center (FPC) at the University of Twente and our partners from the International Center for Networked, Adaptive Production, you will face the challenges of Industrie 4.0 in a real manufacturing environment and use your coding knowledge, technical skill and team spirit to solve them.







Task 1: Machine Learning Model Interpretation​

Machine Learning (ML)-based models are often black-box. To use ML model in industrial setting it should be fair and reliable. Metrics like accuracy-score or r2-score makes it reliable, but one cannot say anything about the fairness of the model. Model fairness and interpretability are critical for data scientists as well as production engineer to explain their models and understand the value and accuracy of their findings. ​

The objective of this task is to interpret a trained ML model using CXPlain and SHAP library.​

You will be given a tabular dataset for a classification task. Using the given dataset, a ML model should be trained to predict the target value. Using this trained model, feature importance for the input features should be calculated with the help of CXPlain and SHAP Model interpretation library and compared quantitatively. ​


  • Train ML-based model on the given dataset for a classification task. Report the balanced accuracy on test-split.​
  • Explore CXPlain library. Code will be provided.​
  • Find feature importance for the input features using CXPlain & SHAP​.
  • Find feature importance uncertainty, confidence interval using CXPlain​.
  • Report comparison for computation time for CXPlain and SHAP library​.
  • Report other findings​

    Things included:

  • Dataset​
  • CXPlain and SHAP library Code​
  • Code to get you started with the task​
  • Dataset​
  • Programming Language to use: Python​
  • Task 2: Dynamic Anomaly Detection of Vibration Data

    Vibration sensors are frequently used in smart factory applications. Standard thresholds for alarms are usually are configurations derived from the ISO10816 standard. This is a good starting point, but it does not reflect real sensor applications and installations, especially when supervising several sensors at several similar machines.

    In reality the mounting position and orientation of sensors at different machines is not identical. In reality “natural” vibrations of two or more “identical” machines are not identical. In reality many vibration influencing variables are ”machine individual”, e.g. on cutting machines there is influence of the actual cutter condition, the “age” of the coolant, the overlay of pick-and-place movements to the “individual” vibration signal of the “individual” machine.

    The task therefore is to develop, verify and deploy an algorithm, that is able to individually generate thresholds through learning data from the first week after the installation of the machine. So-to-say delivering a machine individual zero-line for alarm-threshold out of the time-series vibration data.


  • Develop an algorithm to dynamically set alarm-thresholds for the individual sensor data stream (RMS, value X,Y,Z, FFT values) using the first week of data as training data.
  • Extend the algorithm to continuously retrain itself with incoming data.
  • The ML model should be able to detect anomalies in the individual sensor data stream (RMS, value X,Y,Z, FFT values).
  • Verify the algorithm with respect to recall, precision, F1 score and balanced accuracy.
  • Test the algorithm to a set of 10 similar machines with different vibration characteristics with installed sensors.
  • Task 3: Automatic 3D Model Creation for Industrial AR/MR Application

    Augmented Reality (AR) and Mixed Reality (MR) are increasingly used in manufacturing environments, for example to support manual work with visualizations of work instructions. With the increasing spread and utilization of AR and MR applications in manufacturing, a need arises to create 3D models which accurately depict the characteristics of real life objects. If, for instance, assembly instructions for an engine are to be provided to assembly workers, a precise model of the engine might be useful in order to visualize assembly steps with a high accuracy. However, the creation of accurate 3D models is a time consuming task so that an automation of this work step would add significant value.

    The objective of this task is to find a way to automate the creation of a 3D model of a real reference object which in this case is a ordinary PC keyboard.

    User input can be photographs, videos, camera scanning process of the reference keyboard. The output should be a textured 3D mesh of the reference object in GLTF format in its correct physical size.

    The requirements are:

  • You are allowed to use any resources available to you.
  • The 3D model creation procedure should be as automated as possible.
  • (Bonus) Other objects with different dimensions and/or reflective surfaces can be also correctly reconstructed.
  • (Bonus) The mesh can be organized into groups, according to the physical reference object‘s internal structure.
  • The organizers

    International Center for Networked, Adaptive Production (ICNAP)
    International Center for Networked, Adaptive Production (ICNAP)Aachen (Germany)

    To find out which new approaches in information technology can lead the way towards Industrie 4.0 and which requirements must be met, is the aim of the three Aachen-based Fraunhofer Institutes for Production Technology IPT, for Laser Technology ILT and for Molecular Biology and Applies Ecology IME, who are cooperating with renowned industrial partners in the International Center for Networked, Adaptive Production (ICNAP). The hackathon is organized by the ICNAP in cooperation with the Fraunhofer Project Center at the University of Twente.

    Fraunhofer Project Center at the University of Twente
    Fraunhofer Project Center at the University of TwenteEnschede (The Netherlands)

    The Fraunhofer Project Center at the University of Twente (FPC@UT) aims to be the go-to for applied research in the focus core competencies within application of Advanced Manufacturing. Working together with industry, FPC@UT builds synergies to achieve high-tech excellence within the fourth industrial revolution and to train the high-tech talents of tomorrow. Fraunhofer Project Center acts as the bridge across Germany and the Netherlands as leading providers of science and technology-based solutions in today’s most vital fields, addressing smart industry’s current pressing product and production issues.

    Who are our partners?


    You need help? We have got it covered.

    • Who can participate?

      You can participate if you study computer science, engineering, communication design or take similar course, want to prove your skills and are at least 18 years old at the start of the hackathon.

    • When and where will the hackathon take place?

      The hackathon will take place from April 23, 2021 (8 p.m. CET) – April 25, 2021 (2 p.m. CET) online.

    • How much does it cost to participate in the hackathon?

      Your participation is completely free of charge.

    • How big can a team be?

      There should be a minimum of 2 and a maximum of 5 participants in a team.

    • Can I register without a team?

      Yes, of course! We will also form teams on site.

    • What do I have to bring?

      In any case, you will need your computer and charger. You are also happy about headphones and a power bank for your mobile phone. The other participants will certainly be happy if you bring change of clothes and something to freshen up – unfortunately there are no showers. We don't have sleeping mats and sleeping bags for you and you can bring them with you if you need them. You don't need to bring food and drinks – we'll get them for you.

    • What about the rights to my intellectual property?

      You definitely own the code! You submit the code for evaluation and allocation. You do not transfer any rights to the ICNAP.

    • Can I win anything?

      Yes, the best teams can look forward to winnings that we will announce here soon.

    • What if I have more questions?

      More detailed information will be sent to you before the event. If you have a question that is burning under your nails, you can contact us at community@icnap.de