Die Topologieoptimierung ist die Suche einer optimalen Bauteilgeometrie in Abhängigkeit des Einsatzfalls. Für komplexe Probleme kann die Topologieoptimierung aufgrund eines hohen Detailgrades viel Zeit- und Rechenkapazität erfordern. Diese Nachteile der Topologieoptimierung sollen mittels Deep Learning reduziert werden, so dass eine Topologieoptimierung dem Konstrukteur als sekundenschnelle Hilfe dient. Das Deep Learning ist die Erweiterung künstlicher neuronaler Netzwerke, mit denen Muster oder Verhaltensregeln erlernt werden können. So soll die bislang numerisch berechnete Topologieoptimierung mit dem Deep Learning Ansatz gelöst werden. Hierzu werden Ansätze, Berechnungsschema und erste Schlussfolgerungen vorgestellt und diskutiert.

Récemment, la pyro-gazéification de déchets ménagers solides (DMS) a suscité une plus grande attention, en raison de ses bénéfices potentiels en matière d’émissions polluantes et d’efficacité énergique. Afin de développer un système de traitement de ces déchets, durable et intégré, ce manuscrit s’intéresse plus spécifiquement au développement de la technique de pyro-gazéification des DMS, à la fois sur l’aspect technologique (expérimentations) et sur son évaluation globale (modélisation). Pour cette étude, quatre composants principaux représentatifs des DMS (déchet alimentaire, papier, bois et plastique) ont été pyro-gazéifiés dans un lit fluidisé sous atmosphère N2, CO2 ou vapeur d’eau. Les expériences ont été menées avec les composés seuls ou en mélanges afin de comprendre les interactions mises en jeu et leurs impacts sur la qualité du syngas produit. La présence de plastique améliore significativement la quantité et la qualité du syngas (concentration de H2). La qualité du syngas est améliorée plus particulièrement en présence de vapeur d’eau, ou, dans une moindre mesure, en présence de CO2. Les résultats obtenus ont été ensuite intégrés dans un modèle prédictif de pyro-gazéification basé sur un réseau de neurones artificiels (ANN). Ce modèle prédictif s’avère efficace pour prédire les performances de pyro-gazéification des DMS, quelle que soit leur composition (provenance géographique). Pour améliorer la qualité du syngas et abaisser la température du traitement, la gazéification catalytique in-situ, en présence de CaO, a été menée. L’impact du débit de vapeur d’eau, du ratio massique d’oxyde de calcium, ainsi que de la température de réaction a été étudié en regard de la production (quantité et pourcentage molaire dans le gaz) d’hydrogène. La présence de CaO a permis d’abaisser de 100 oC la température de gazéification, à qualité de syngas équivalente. Pour envisager une application industrielle, l’activité du catalyseur a aussi été évaluée du point de vue de sa désactivation et régénération. Ainsi, les températures de carbonatation et de calcination de 650 oC et 800 oC permettent de prévenir la désactivation du catalyseur, tandis que l’hydratation sous vapeur d’eau permet la régénération. Ensuite, une étude a été dédiée à l’évaluation et à l’optimisation de la technologie de pyro-gazéification par la méthode d’analyse de cycle de vie (ACV). Le système de gazéification permet d’améliorer les indicateurs de performances environnementales comparativement à l’incinération conventionnelle. De plus, des systèmes combinant à la fois la transformation des déchets en vecteur énergétique et la mise en œuvre de ce vecteur ont été modélisés. La pyro-gazéification combinée à une turbine à gaz permettrait de maximiser l’efficacité énergétique et de diminuer l’impact environnemental du traitement. Ainsi, les résultats permettent d’optimiser les voies actuelles de valorisation énergétique, et de d’optimiser les techniques de pyro-gazéification. / Due to the potential benefits in achieving lower environmental emissions and higher energy efficiency, municipal solid waste (MSW) pyro-gasification has gained increasing attentions in the last years. To develop such an integrated and sustainable MSW treatment system, this dissertation mainly focuses on developing MSW pyro-gasification technique, including both experimental-based technological investigation and assessment modeling. Four of the most typical MSW components (wood, paper, food waste and plastic) are pyro-gasified in a fluidized bed reactor under N2, steam or CO2 atmosphere. Single-component and multi-components mixture have been investigated to characterize interactions regarding the high-quality syngas production. The presence of plastic in MSW positively impacts the volume of gas produced as well as its H2 content. Steam clearly increased the syngas quality rather than the CO2 atmosphere. The data acquired have been further applied to establish an artificial neural network (ANN)-based pyro-gasification prediction model. Although MSW composition varies significantly due to geographic differences, the model is robust enough to predict MSW pyro-gasification performance with different waste sources. To further enhance syngas properties and reduce gasification temperature as optimization of pyro-gasification process, MSW steam catalytic gasification is studied using calcium oxide (CaO) as an in-situ catalyst. The influence of CaO addition, steam flowrate and reaction temperature on H2-rich gas production is also investigated. The catalytic gasification using CaO allows a decrease of more than 100 oC in the reaction operating temperature in order to reach the same syngas properties, as compared with non-catalyst high-temperature gasification. Besides, the catalyst activity (de-activation and re-generation mechanisms) is also evaluated in order to facilitate an industrial application. 650 oC and 800 oC are proven to be the most suitable temperature for carbonation and calcination respectively, while steam hydration is shown to be an effective CaO re-generation method. Afterwards, a systematic and comprehensive life cycle assessment (LCA) study is conducted. Environmental benefits have been achieved by MSW gasification compared with conventional incineration technology. Besides, pyrolysis and gasification processes coupled with various energy utilization cycles are also modeled, with a gasification-gas turbine cycle system exhibits the highest energy conversion efficiency and lowest environmental burden. The results are applied to optimize the current waste-to-energy route, and to develop better pyro-gasification techniques.

No description available.

A number of recent studies have shown that the dimensionality of the neural activity in the cortex is low. However, what network structures are capable of producing such activity is not theoretically well understood. In this thesis, I discuss a few possible solutions to this problem, and demonstrate that a network with a multidimensional attractor can give rise to such low dimensional activity. The network is created using the Neural Engineering Framework, and exhibits several biologically plausible features, including a log-normal distribution of the synaptic weights. / Ett antal nyligen publicerade studier has visat att dimensionaliten för neural aktivitet är låg. Dock är det inte klarlagt vilka nätverksstrukturer som kan uppbringa denna typ av aktivitet. I denna uppsats diskuterar jag möjliga lösningsförslag, och demonstrerar att ett nätverk med en flerdimensionell attraktor ger upphov till lågdimensionell aktivitet. Nätverket skapas med hjälp av the Neural Engineering Framework, och uppvisar ett flertal biologiskt trovärdiga egenskaper. I synnerhet är fördelningen av synapsvikter log-normalt fördelad.

Databases of user generated data can quickly become unmanageable. Klarna faced this issue, with a database of around 700,000 customer reviews. Ideally, the database would be cleaned of uninteresting reviews and the remaining reviews categorized. Without knowing what categories might emerge, the idea was to use an unsupervised clustering algorithm to find categories. This thesis describes the work carried out to solve this problem, and proposes a solution for Klarna that involves artificial neural networks rather than unsupervised clustering. The implementation done by us is able to categorize reviews as either interesting or uninteresting. We propose a workflow that would create means to categorize reviews not only in these two categories, but in multiple. The method revolved around experimentation with clustering algorithms and neural networks. Previous research shows that texts can be clustered, however, the datasets used seem to be vastly different from the Klarna dataset. The Klarna dataset consists of short reviews and contain a large amount of uninteresting reviews. Using unsupervised clustering yielded unsatisfactory results, as no discernible categories could be found. In some cases, the technique created clusters of uninteresting reviews. These clusters were used as training data for an artificial neural network, together with manually labeled interesting reviews. The results from this artificial neural network was satisfactory; it can with an accuracy of around 86% say whether a review is interesting or not. This was achieved using the aforementioned clusters and five feedback loops, where the model’s wrongfully predicted reviews from an evaluation dataset was fed back to it as training data. We argue that the main reason behind why unsupervised clustering failed is that the length of the reviews are too short. In comparison, other researchers have successfully clustered text data with an average length in the hundreds. These items pack much more features than the short reviews in the Klarna dataset. We show that an artificial neural network is able to detect these features despite the short length, through its intrinsic design. Further research in feature extraction of short text strings could provide means to cluster this kind of data. If features can be extracted, the clustering can thus be done on the features rather than the actual words. Our artificial neural network shows that the arbitrary features interesting and uninteresting can be extracted, so we are hopeful that future researchers will find ways of extracting more features from short text strings. In theory, this should mean that text of all lengths can be clustered unsupervised. / Databaser med användargenererad data kan snabbt bli ohanterbara. Klarna stod inför detta problem, med en databas innehållande cirka 700 000 recensioner från kunder. De såg helst att databasen skulle rensas från ointressanta recensioner och att de kvarvarande kategoriseras. Eftersom att kategorierna var okända initialt, var tanken att använda en oövervakad grupperingsalgoritm. Denna rapport beskriver det arbete som utfördes för att lösa detta problem, och föreslår en lösning till Klarna som involverar artificiella neurala nätverk istället för oövervakad gruppering. Implementationen skapad av oss är kapabel till att kategorisera recensioner som intressanta eller ointressanta. Vi föreslår ett arbetsflöde som skulle skapa möjlighet att kategorisera recensioner inte bara i dessa två kategorier, utan i flera. Metoden kretsar kring experimentering med grupperingsalgoritmer och artificiella neurala nätverk. Tidigare forskning visar att texter kan grupperas oövervakat, dock med ingångsdata som väsentligt skiljer sig från Klarnas data. Recensionerna i Klarnas data är generellt sett korta och en stor andel av dem kan ses som ointressanta. Oövervakad grupperingen gav otillräckliga resultat, då inga skönjbara kategorier stod att finna. I vissa fall skapades grupperingar av ointressanta recensioner. Dessa användes som träningsdata för ett artificiellt neuralt nätverk. Till träningsdatan lades intressanta recensioner som tagits fram manuellt. Resultaten från detta var positivt; med en träffsäkerhet om cirka 86% avgörs om en recension är intressant eller inte. Detta uppnåddes genom den tidigare skapade träningsdatan samt fem återkopplingsprocesser, där modellens felaktiga prediktioner av evalueringsdata matades in som träningsdata. Vår uppfattning är att den korta längden på recensionerna gör att den oövervakade grupperingen inte fungerar. Andra forskare har lyckats gruppera textdata med snittlängder om hundratals ord per text. Dessa texter rymmer fler meningsfulla enheter än de korta recensionerna i Klarnas data. Det finns lösningar som innefattar artificiella neurala nätverk å andra sidan kan upptäcka dessa meningsfulla enheter, tack vare sin grundläggande utformning. Vårt arbete visar att ett artificiellt neuralt nätverk kan upptäcka dessa meningsfulla enheter, trots den korta längden per recension. Extrahering av meningsfulla enheter ur korta texter är ett ¨ämne som behöver mer forskning för att underlätta problem som detta. Om meningsfulla enheter kan extraheras ur texter, kan grupperingen göras på dessa enheter istället för orden i sig. Vårt artificiella neurala nätverk visar att de arbiträra enheterna intressant och ointressant kan extraheras, vilket gör oss hoppfulla om att framtida forskare kan finna sätt att extrahera fler enheter ur korta texter. I teorin innebär detta att texter av alla längder kan grupperas oövervakat.

In this thesis, we use evolutionary robotics techniques to automatically design and synthesise<p>behaviour for groups of simulated and real robots. Our contribution will be on<p>the design of non-trivial individual and collective behaviour; decisions about solitary or<p>social behaviour will be temporal and they will be interdependent with communicative<p>acts. In particular, we study time-based decision-making in a social context: how the<p>experiences of robots unfold in time and how these experiences influence their interaction<p>with the rest of the group. We propose three experiments based on non-trivial real-world<p>cooperative scenarios. First, we study social cooperative categorisation; signalling and<p>communication evolve in a task where the cooperation among robots is not a priori required.<p>The communication and categorisation skills of the robots are co-evolved from<p>scratch, and the emerging time-dependent individual and social behaviour are successfully<p>tested on real robots. Second, we show on real hardware evidence of the success of evolved<p>neuro-controllers when controlling two autonomous robots that have to grip each other<p>(autonomously self-assemble). Our experiment constitutes the first fully evolved approach<p>on such a task that requires sophisticated and fine sensory-motor coordination, and it<p>highlights the minimal conditions to achieve assembly in autonomous robots by reducing<p>the assumptions a priori made by the experimenter to a functional minimum. Third, we<p>present the first work in the literature to deal with the design of homogeneous control<p>mechanisms for morphologically heterogeneous robots, that is, robots that do not share<p>the same hardware characteristics. We show how artificial evolution designs individual<p>behaviours and communication protocols that allow the cooperation between robots of<p>different types, by using dynamical neural networks that specialise on-line, depending on<p>the nature of the morphology of each robot. The experiments briefly described above<p>contribute to the advancement of the state of the art in evolving neuro-controllers for<p>collective robotics both from an application-oriented, engineering point of view, as well as<p>from a more theoretical point of view. / Doctorat en Sciences de l'ingénieur / info:eu-repo/semantics/nonPublished

The development of machine learning research has provided statistical innovations and further developments within the field of time series analysis. This study seeks to investigate two different approaches on artificial neural network models based on different learning techniques, and answering how well the neural network approach compares with a basic autoregressive approach, as well as how the artificial neural network models compare to each other. The models were compared and analyzed in regards to the univariate forecast accuracy on 20 randomly drawn time series from two different time frequencies from the M4 competition dataset. Forecasting was made dependent on one time lag (t-1) and forecasted three and six steps ahead respectively. The artificial neural network models outperformed the baseline Autoregressive model, showing notably lower mean average percentage error overall. The Multilayered perceptron models performed better than the Long short-term memory model overall, whereas the Long short-term memory model showed improvement on longer prediction time dimensions. As the training were done univariately  on a limited set of time steps, it is believed that the one layered-approach gave a good enough approximation on the data, whereas the added layer couldn’t fully utilize its strengths of processing power. Likewise, the Long short-term memory model couldn’t fully demonstrate the advantagements of recurrent learning. Using the same dataset, further studies could be made with another approach to data processing. Implementing an unsupervised approach of clustering the data before analysis, the same models could be tested with multivariate analysis on models trained on multiple time series simultaneously.

Hyperspectral imaging has become one of the most popular technologies in plant phenotyping because it can efficiently and accurately predict numerous plant physiological features such as plant biomass, leaf moisture content, and chlorophyll content. Various hyperspectral imaging systems have been deployed in both greenhouse and field phenotyping activities. However, the hyperspectral imaging quality is severely affected by the continuously changing environmental conditions such as cloud cover, temperature and wind speed that induce noise in plant spectral data. Eliminating these environmental effects to improve imaging quality is critically important. In this thesis, two approaches were taken to address the imaging noise issue in greenhouse and field separately. First, a computational simulation model was built to simulate the greenhouse microclimate changes (such as the temperature and radiation distributions) through a 24-hour cycle in a research greenhouse. The simulated results were used to optimize the movement of an automated conveyor in the greenhouse: the plants were shuffled with the conveyor system with optimized frequency and distance to provide uniform growing conditions such as temperature and lighting intensity for each individual plant. The results showed the variance of the plants’ phenotyping feature measurements decreased significantly (i.e., by up to 83% in plant canopy size) in this conveyor greenhouse. Secondly, the environmental effects (i.e., sun radiation) on <a>aerial </a>hyperspectral images in field plant phenotyping were investigated and modeled. <a>An artificial neural network (ANN) method was proposed to model the relationship between the image variation and environmental changes. Before the 2019 field test, a gantry system was designed and constructed to repeatedly collect time-series hyperspectral images with 2.5 minutes intervals of the corn plants under varying environmental conditions, which included sun radiation, solar zenith angle, diurnal time, humidity, temperature and wind speed. Over 8,000 hyperspectral images of </a>corn (<i>Zea mays </i>L.) were collected with synchronized environmental data throughout the 2019 growing season. The models trained with the proposed ANN method were able to accurately predict the variations in imaging results (i.e., 82.3% for NDVI) caused by the changing environments. Thus, the ANN method can be used by remote sensing professionals to adjust or correct raw imaging data for changing environments to improve plant characterization.

Indiana University-Purdue University Indianapolis (IUPUI) / This thesis proposes an artificial neural network (NN) model to predict fuel consumption in heavy vehicles. The model uses predictors derived from vehicle speed, mass, and road grade. These variables are readily available from telematics devices that are becoming an integral part of connected vehicles. The model predictors are aggregated over a fixed distance traveled (i.e., window) instead of fixed time interval. It was found that 1km windows is most appropriate for the vocations studied in this thesis. Two vocations were studied, refuse and delivery trucks. The proposed NN model was compared to two traditional models. The first is a parametric model similar to one found in the literature. The second is a linear regression model that uses the same features developed for the NN model. The confidence level of the models using these three methods were calculated in order to evaluate the models variances. It was found that the NN models produce lower point-wise error. However, the stability of the models are not as high as regression models. In order to improve the variance of the NN models, an ensemble based on the average of 5-fold models was created. Finally, the confidence level of each model is analyzed in order to understand how much error is expected from each model. The mean training error was used to correct the ensemble predictions for five K-Fold models. The ensemble K-fold model predictions are more reliable than the single NN and has lower confidence interval than both the parametric and regression models.

The work occupy by inverse analysis based on artificial neural network. This identification algorithm enable correct determine parameters of applied material model on creation of numerical model of construction so it's possible that the results of computerized simulation correspond with experiments. It look's like suitable approach especially in cases with complicated problems and complex models with many material parameters.