Now showing 1 - 10 of 12
  • Publication
    Informed Machine Learning - A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems
    Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process which leads to the notion of informed machine learning. In this paper, we present a structured overview of various approaches in this field. We provide a definition and propose a concept for informed machine learning which illustrates its building blocks and distinguishes it from conventional machine learning. We introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Based on this taxonomy, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning.
  • Publication
    Cleaning strategies and cost modelling of experimental membrane-based desalination plants
    In Project WASTEC, an experimental Reverse Osmosis (RO) desalination system was developed. It serves as a platform for testing new technologies. For this system, we solved two problems, which are described in this paper. Firstly, we developed and investigated strategies for scheduling chemical enhanced backwashing and chemical cleaning and secondly, due to the experimental nature of the project, several new technological developments with respect to materials and methods were integrated into the system and requires tools for evaluating the economic viability of the new technologies. In this task, the economics of membrane-based desalination will be investigated. Baseline systems of reverse osmosis and pretreatment systems (microfiltration and ultrafiltration) will be economically examined and compared for their investments and operational costs. Sensitivity of the different plant and membrane parameters to the cost will be studied. Results show that with respect to costs, for a 200m3/hr design capacity plant, a volume of water is produced by a MF process at a cost of $0.494 and at a cost of $0.486 by an ultrafiltration process microfiltration. The reverse osmosis process cannot be compared directly, but it required $ 0.49 / m3 for a plant with 56 m3/hour design capacity. The values are in line with the costs reported in literature for membrane-based filtration.
  • Publication
    Experimental Evaluation of a Novel Sensor-Based Sorting Approach Featuring Predictive Real-Time Multiobject Tracking
    ( 2021) ;
    Pfaff, Florian
    ;
    Pieper, Christoph
    ;
    ;
    Noack, Benjamin
    ;
    Kruggel-Emden, Harald
    ;
    ;
    Hanebeck, Uwe D.
    ;
    Wirtz, Siegmar
    ;
    Scherer, Viktor
    ;
    Sensor-based sorting is a machine vision application that has found industrial application in various fields. An accept-or-reject task is executed by separating a material stream into two fractions. Current systems use line-scanning sensors, which is convenient as the material is perceived during transportation. However, line-scanning sensors yield a single observation of each object and no information about their movement. Due to a delay between localization and separation, assumptions regarding the location and point in time for separation need to be made based on the prior localization. Hence, it is necessary to ensure that all objects are transported at uniform velocities. This is often a complex and costly solution. In this paper, we propose a new method for reliably separating particles at non-uniform velocities. The problem is transferred from a mechanical to an algorithmic level. Our novel advanced image processing approach includes equipping the sorter with an area-scan camera in combination with a real-time multiobject tracking system, which enables predictions of the location of individual objects for separation. For the experimental validation of our approach, we present a modular sorting system, which allows comparing sorting results using a line-scan and area-scan camera. Results show that our approach performs reliable separation and hence increases sorting efficiency.
  • Publication
    SmartSpectrometer - Embedded Optical Spectroscopy for Applications in Agriculture and Industry
    The ongoing digitization of industry and agriculture can benefit significantly from optical spectroscopy. In many cases, optical spectroscopy enables the estimation of properties such as substance concentrations and compositions. Spectral data can be acquired and evaluated in real time, and the results can be integrated directly into process and automation units, saving resources and costs. Multivariate data analysis is needed to integrate optical spectrometers as sensors. Therefore, a spectrometer with integrated artificial intelligence (AI) called SmartSpectrometer and its interface is presented. The advantages of the SmartSpectrometer are exemplified by its integration into a harvesting vehicle, where quality is determined by predicting sugar and acid in grapes in the field.
  • Publication
    Optimal, blind-search modal wavefront correction in atmospheric turbulence. Part I: Simulations
    Modal control is an established tool in adaptive optics. It allows not only for the reduction in the controllable degrees of freedom, but also for filtering out unseen modes and optimizing gain on a mode-by-mode basis. When Zernike polynomials are employed as the modal basis for correcting atmospheric turbulence, their cross-correlations translate to correction errors. We propose optimal modal decomposition for gradient-descent-based wavefront sensorless adaptive optics, which is free of this problem. We adopt statistically independent Karhunen-Loève functions for iterative blind correction and analyze performance of the algorithm in static as well as in dynamic simulated turbulence conditions.
  • Publication
    Quantum ghost imaging using asynchronous detection
    We present first results of a novel type of setup for quantum ghost imaging based on asynchronous single photon timing using single photon avalanche diode (SPAD) detectors. This scheme enables photon pairing with arbitrary path length difference and does, therefore, obviate the dependence on optical delay lines of current quantum ghost imaging setups [Nat. Commun. 6, 5913 (2015) [CrossRef]]. It is also, to our knowledge, the first quantum ghost imaging setup to allow three-dimensional imaging.
  • Publication
    Ultra-flat supercontinuum from 1.95 to 2.65 µm in a nanosecond pulsed Thulium-doped fiber laser
    ( 2020) ;
    Jaouën, Yves
    ;
    Tench, Robert E.
    ;
    Delavaux, Jean-Marc
    We report on mid-IR supercontinuum generation in an all-silica nanosecond pulsed fiber laser. The laser topology is a master oscillator power amplifier which consists of a two stage Thulium-doped fiber amplifier seeded with a directly modulated semiconductor laser at 1952 nm. The supercontinuum performance is investigated for repetition rate frequencies between 35 kHz and 100 kHz and pulse widths between 6 ns and 21 ns. Supercontinuum average output powers greater than 1.5 W and spectra ranging from 1.95 µm to 2.65 µm are demonstrated.
  • Publication
    From Visual Spectrum to Millimeter Wave: A Broad Spectrum of Solutions for Food Inspection
    The consequences of food adulteration can be far reaching. In the past, inexpensive adulterants were used to inflate different products, leading to severe health issues. Contamination of food has many causes and can be physical(plant stems in tea), chemical (melamine in infant formula), or biological (bacterial contamination). Employing suitable sensor systems along the production process is a requirement for food safety. In this article, different approaches to food inspection are illustrated, and exemplary scenarios outline the potential of different sensor systems along the spectrum.
  • Publication
    Adaptable Shack-Hartmann wavefront sensor with diffractive lenslet arrays to mitigate the effects of scintillation
    Adaptive optics systems are used to compensate for distortions of the wavefront of light induced by turbulence in the atmosphere. Shack-Hartmann wavefront sensors are used to measure this wavefront distortion before correction. However, in turbulence conditions where strong scintillation (intensity fluctuation) is present, these sensors show considerably worse performance. This is partly because the lenslet arrays of the sensor are designed without regard to scintillation and are not adaptable to changes in turbulence strength. Therefore, we have developed an adaptable Shack-Hartmann wavefront sensor that can flexibly exchange its lenslet array by relying on diffractive lenses displayed on a spatial light modulator instead of utilizing a physical microlens array. This paper presents the principle of the sensor, the design of a deterministic turbulence simulation test-bed, and an analysis how different lenslet arrays perform in scintillation conditions. Our experiments with different turbulence conditions showed that it is advantageous to increase the lenslet size when scintillation is present. The residual phase variance for an array with 24 lenslets was up to 71% lower than for a 112 lenslet array. This shows that the measurement error of focal spots has a strong influence on the performance of a Shack-Hartmann wavefront sensor and that in many cases it makes sense to increase the lenslet size. With our adaptable wavefront sensor such changes in lenslet configurations can be done very quickly and flexibly.
  • Publication
    55 W actively Q-switched single oscillator Tm3+, Ho3+-codoped silica polarization maintaining 2.09 µm fiber laser
    ( 2019)
    Dalloz, Nicolas
    ;
    Robin, Thierry
    ;
    Cadier, Benoît
    ;
    ; ;
    Hildenbrand-Dhollande, Anne
    A bidirectional 793 nm diode-pumped actively Q-switched Tm3+, Ho3+-codoped silica polarization-maintaining (PM) double-clad (DC) fiber laser is reported. With this fiber laser, 55 W of average output power with 100 ns pulse width at 200 kHz repetition rate and 2.09 µm wavelength is obtained. The pump power injection with end-caps fusion-spliced on fiber tips provides good power stability (< 1.1%) and beam quality factors (M2 < 1.7). The fiber laser output beam polarization factor is 97.5%. At 55 W, no thermal-induced damage is observed on any optical element, and power scaling of the laser is only pump-power-limited in the range of the total available pump power (180 W).