ENBIS Spring Meeting 2019 in Barcelona

13 – 14 June 2019 Abstract submission: 15 January – 20 May 2019

My abstracts


The following abstracts have been accepted for this event:

  • A population balance model for the recycling of waste electrical and electronic equipment

    Authors: Antonio Pievatolo (CNR-IMATI), Ettore Lanzarone (CNR-IMATI), Marcello Colledani (Politecnico di Milano), Marco Diani (Politecnico di Milano)
    Primary area of focus / application: Modelling
    Secondary area of focus / application: Design and analysis of experiments
    Keywords: Mass conservation, Machine characterization, Design of experiments, Markov modelling
    Submitted at 20-May-2019 10:55 by Antonio Pievatolo
    13-Jun-2019 16:30 A population balance model for the recycling of waste electrical and electronic equipment
    Sustainable circular economy is introducing new industrial challenges, including recycling of waste electrical and electronic equipment (WEEE). In particular, we consider mechanical comminution of parts such as printed circuits boards, which produces mixtures of highly liberated particles. However, the complexity this process requires adequate models to control and optimize its behaviour in the context of the overall recycling system, which is composed by several stations: comminution, particle classification and separation. For comminution, the so-called Population Balance Model (PBM) has been proposed, which is however limited to the mining industry. Here we examine its applicability in the WEEE recycling industry. In particular, we consider a Markov model formulation of the PBM on the state space of the dimensional distribution of particles that can be quickly estimated and put into production, so as to be able to choose the best settings of the shredding machine for the subsequent separation stage.
  • Statistical Engineering Case Study: Using fast robust statistical methods to efficiently build a computer vision model for modern, high-throughput product inspection.

    Authors: Bart De Ketelaere (1 Division Mechatronics, Biostatistics and Sensors (MeBioS), KU Leuven), Mia Hubert (Statistics Section, KU Leuven), Peter Rousseeuw (Statistics Section, KU Leuven), Iwein Vranckx (Statistics Section, KU Leuven)
    Primary area of focus / application: Other:
    Keywords: Computer vision, Calibration
    Submitted at 3-Jun-2019 16:40 by Bart De Ketelaere
    13-Jun-2019 11:30 Using fast robust statistical methods to efficiently build a computer vision model for modern, high-throughput product inspection.
    Computer vision is often used in inspection processes to discriminate between good and bad product, or to separate many fractions that constitute a material stream (e.g. in food or plastics inspection). In order to build a statistical model that can be used to perform the inspection task, there are mainly two practical options that are used. In the first option, the product is manually sorted into the different pure fractions and images of those pure fractions are then used to build a calibration model. In the second option, the mixture of fractions is presented to the camera system as such, and a human operator then labels the different fractions in the acquired images.

    Both modi operandi have their important drawbacks. The first way of working faces the disadvantage that a substantial effort is required to manually sort a representative and large enough sample for building the model. In the second approach, the required effort is somewhat lower, but the manual, on-screen labeling of images is prone to errors, so that wrongly labelled data corrupt the obtained database to build a model, potentially leading to inferior classification results. Moreover, modern imaging systems operate in many more wavelength regions as the classical RGB (e.g. by including the NIR region of the electromagnetic spectrum, or by using hyperspectral imaging systems) so that labelling images on screen is becoming cumbersome.

    Because of these drawbacks, an approach that is applicable to modern vision systems that produce hard-to-interpret images and avoids the time consuming manual inspection step whilst being robust to mislabeling (or even makes manual labeling obsolete) would have a clear advantage.

    In order to be insensitive to mislabeling and noisy data, robust statistical methods could be an appealing choice. However, their computational complexity makes them unsuitable for high-throughput applications such as those in image analysis where millions of samples need to be classified in a fraction of time.

    In this case study, we will present a novel approach that is based on newly developed robust yet fast statistical methods that adapt existing techniques so that they work fast on modern computer architectures. By applying these fast and robust techniques, no manual inspection nor image labeling is required, drastically improving the calibration procedure and the classification efficiency of an inspection process.
  • Statistical Engineering Examples

    Authors: Murat Kulahci (Technical University of Denmark)
    Primary area of focus / application: Other:
    Secondary area of focus / application: Other:
    Keywords: Industry 4.0, Analytics
    Submitted at 3-Jun-2019 16:44 by Murat Kulahci
    13-Jun-2019 11:00 Statistical Engineering Examples
    There has been a growing push towards digitalization through developments in Industry 4.0 and IoT. Digitalization of production information comes with a lot of issues and constitutes only one component of the whole picture. The days for statisticians to sit in their desk and crunch numbers in their isolated world seem to be over. Being part of the new production environment also requires us to learn, develop and use not just analytical but also IT, operational and planning tools. The problems this new era brought forth are too complex and truly muti-disciplinary. Hence the solutions we are expected to provide should take this into account as well. In this talk, we will try to elaborate on this aspect of some of the data analytics work we have been engaged in and provide some examples where we needed varying tools, and communicate and collaborate with other key members from production to provide a “workable” solution.