Greenhouses are in need of new monitoring tools, as they size grow bigger and bigger but still using old labour intensive methods ways of caring for the crop. HiPerGreen is set out to create a new tool, which can drive onto the pre-existing heating pipes to provide a birds eye perspective for image analysis purposes. However, clear images are necessary for consistent usable data. This presentation resumes the steps taken during the reporting: the optimisation of a rail based system towards clear images. This is done through analysis of resulting images, understanding vibrations and oscillations, and finally presents results based on prototyping. Moreover, a re-design of the electronics and hardware was also introduce to facilitate prototyping. The results are promising, laying within the requirements.
DOCUMENT
Plant photosynthesis and biomass production are associated with the amount of intercepted light, especially the light distribution inside the canopy. Three virtual canopies (n = 80, 3.25 plants/m2) were constructed based on average leaf size of the digitized plant structures: ‘small leaf’ (98.1 cm2), ‘medium leaf’ (163.0 cm2) and ‘big leaf’ (241.6 cm2). The ratios of diffuse light were set in three gradients (27.8%, 48.7%, 89.6%). The simulations of light interception were conducted under different ratios of diffuse light, before and after the normalization of incident radiation. With 226.1% more diffuse light, the result of light interception could increase by 34.4%. However, the 56.8% of reduced radiation caused by the increased proportion of diffuse light inhibited the advantage of diffuse light in terms of a 26.8% reduction in light interception. The big-leaf canopy had more mutual shading effects, but its larger leaf area intercepted 56.2% more light than the small-leaf canopy under the same light conditions. The small-leaf canopy showed higher efficiency in light penetration and higher light interception per unit of leaf area. The study implied the 3D structural model, an effective tool for quantitative analysis of the interaction between light and plant canopy structure.
MULTIFILE
We present a novel architecture for an AI system that allows a priori knowledge to combine with deep learning. In traditional neural networks, all available data is pooled at the input layer. Our alternative neural network is constructed so that partial representations (invariants) are learned in the intermediate layers, which can then be combined with a priori knowledge or with other predictive analyses of the same data. This leads to smaller training datasets due to more efficient learning. In addition, because this architecture allows inclusion of a priori knowledge and interpretable predictive models, the interpretability of the entire system increases while the data can still be used in a black box neural network. Our system makes use of networks of neurons rather than single neurons to enable the representation of approximations (invariants) of the output.
LINK
Manual labour is an important cornerstone in manufacturing and considering human factors and ergonomics is a crucial field of action from both social and economic perspective. Diverse approaches are available in research and practice, ranging from guidelines, ergonomic assessment sheets over to digitally supported workplace design or hardware oriented support technologies like exoskeletons. However, in the end those technologies, methods and tools put the working task in focus and just aim to make manufacturing “less bad” with reducing ergonomic loads as much as possible. The proposed project “Human Centered Smart Factories: design for wellbeing for future manufacturing” wants to overcome this conventional paradigm and considers a more proactive and future oriented perspective. The underlying vision of the project is a workplace design for wellbeing that makes labor intensive manufacturing not just less bad but aims to provide positive contributions to physiological and mental health of workers. This shall be achieved through a human centered technology approach and utilizing advanced opportunities of smart industry technologies and methods within a cyber physical system setup. Finally, the goal is to develop smart, shape-changing workstations that self-adapt to the unique and personal, physical and cognitive needs of a worker. The workstations are responsive, they interact in real time, and promote dynamic activities and varying physical exertion through understanding the context of work. Consequently, the project follows a clear interdisciplinary approach and brings together disciplines like production engineering, human interaction design, creative design techniques and social impact assessment. Developments take place in an industrial scale test bed at the University of Twente but also within an industrial manufacturing factory. Through the human centered design of adaptive workplaces, the project contributes to a more inclusive and healthier society. This has also positive effects from both national (e.g. relieve of health system) as well as individual company perspective (e.g. less costs due to worker illness, higher motivation and productivity). Even more, the proposal offers new business opportunities through selling products and/or services related to the developed approach. To tap those potentials, an appropriate utilization of the results is a key concern . The involved manufacturing company van Raam will be the prototypical implementation partner and serve as critical proof of concept partner. Given their openness, connections and broad range of processes they are also an ideal role model for further manufacturing companies. ErgoS and Ergo Design are involved as methodological/technological partners that deal with industrial engineering and ergonomic design of workplace on a daily base. Thus, they are crucial to critically reflect wider applicability and innovativeness of the developed solutions. Both companies also serve as multiplicator while utilizing promising technologies and methods in their work. Universities and universities of applied sciences utilize results through scientific publications and as base for further research. They also ensure the transfer to education as an important leverage to inspire and train future engineers towards wellbeing design of workplaces.
Aanleiding De binnendijkse aquacultuur (viskweek) is een sector met grote economische potentie. De vislarven en schelpdieren die in deze sector gekweekt worden, zijn een belangrijk product voor de (inter)nationale markt. Binnendijks produceren geeft meer grip op de kwaliteit en hoeveelheid en biedt milieuvoordelen. Aangezien er binnendijks onvoldoende natuurlijk voedsel is voor de productie van de schelpdieren en vislarven, is het voor de aquacultuurbedrijven van groot belang dat ze zelf jaarrond beschikken over voedsel - microalgen - van de juiste kwaliteit. De bedrijven kunnen echter met de huidige algenproductiesystemen geen stabiele, kwalitatief hoogwaardige algenkweek tegen aanvaardbare kostprijs realiseren. Doelstelling Doel van het project is het ontwikkelen van kennis over de relatie tussen omgevingsfactoren, stuurvariabelen (licht, temperatuur, medium, oogstregime en menging) en de uiteindelijke opbrengsten (kwantiteit, kostprijs en kwaliteit) bij de kweek van microalgen voor aquacultuurtoepassingen. Deze factoren en variabelen worden onderzocht bij drie soorten algen in drie soorten productiesystemen. Het onderzoek bestaat uit twee onderdelen. Eerst onderzoekt het projectteam de kwantiteit, ofwel de productiviteit van algen en de doorwerking naar de kostprijs. Daarna komt de kwaliteit van algen en de beïnvloeding daarvan door de stuurvariabelen aan bod. Het onderzoeksteam voert manipulatieve experimenten uit op pilotschaal en monitort op productieschaal de algenkweek. Zo wordt de relatie tussen de stuurvariabelen en de kwaliteit en kwantiteit van de algenkweek in kaart gebracht. Gelijktijdig wordt onderzocht hoe men modelmatig voorspellingen kan doen over de kwantiteit en kostprijs. Beoogde resultaten Het programma beoogt twee uitkomsten: 1) handelingsprotocollen waarmee aquacultuurbedrijven de stuurvariabelen kunnen beheersen en hun algenkweekproces kunnen inrichten en beheren; 2) een 'decision support model' dat kostprijs en opbrengst van algenkweek berekent op basis van gebruikte systemen, procesvoering en algensoort. Via de Delta Expertise Site (wiki) komen onderzoeksresultaten beschikbaar voor de beroepspraktijk, onderwijs en onderzoek. De deelnemende hogescholen integreren de verworven kennis en producten in onderwijsmodules, cursussen, twee minoren, gastcolleges door professionals en in afstudeerstages bij bedrijven uit het projectnetwerk. Tijdens het onderzoek vindt al gedeeltelijk implementatie plaats bij de betrokken bedrijven (uitvoering experimenten op locatie). Voor de samenwerkingspartners worden er daarnaast projectbijeenkomsten meetcampagnes, masterclasses en workshops georganiseerd. Verdere kennisuitwisseling en -verspreiding verloopt via wetenschappelijke publicaties, artikelen in vaktijdschriften, nieuwsbrieven, presentaties in bedrijfsnetwerken en bij kennisinstellingen, een Massive Open Online Course, een studiereis naar China (Shanghai Ocean University), een definitief onderzoeksrapport en een slotconferentie.
