The purpose of this research project is the design and optimization of complex chemical engineering problems, by employing evolutionary algorithms (EAs). EAs are optimization techniques which mimic the principles of genetics and natural selection. Given their population-based approach, EAs are well suited for solving multiobjective optimization problems (MOOPs) to determine Pareto-optimal solutions. The Pareto front refers to the set of non-dominated solutions which highlight trade-offs among the different objectives. A broad range of applications have been studied, all of which are drawn from the chemical engineering field. The design of an industrial packed bed styrene reactor is initially studied with the goal of maximizing the productivity, yield and selectivity of styrene. The dual population evolutionary algorithm (DPEA) was used to circumscribe the Pareto domain of two and three objective optimization case studies for three different configurations of the reactor: adiabatic, steam-injected and isothermal. The Pareto domains were then ranked using the net flow method (NFM), a ranking algorithm that incorporates the knowledge and preferences of an expert into the optimization routine. Next, a multiobjective optimization of the heat transfer area and pumping power of a shell-and-tube heat exchanger is considered to provide the designer with multiple Pareto-optimal solutions which capture the trade-off between the two objectives. The optimization was performed using the fast and elitist non-dominated sorting genetic algorithm (NSGA-II) on two case studies from the open literature. The algorithm was also used to determine the impact of using discrete standard values of the tube length, diameter and thickness rather than using continuous values to obtain the optimal heat transfer area and pumping power. In addition, a new hybrid algorithm called the FP-NSGA-II, is developed in this thesis by combining a front prediction algorithm with the fast and elitist non-dominated sorting genetic algorithm-II (NSGA-II). Due to the significant computational time of evaluating objective functions in real life engineering problems, the aim of this hybrid approach is to better approximate the Pareto front of difficult constrained and unconstrained problems while keeping the computational cost similar to NSGA-II. The new algorithm is tested on benchmark problems from the literature and on a heat exchanger network problem.

In past years, great attention has been paid to evolutionary algorithms and they have been utilized in wide range of industries including data mining field, which nowadays presents a highly demanded product for many commercial institutions. Both mentioned topics are combined in this work. Main thesis subject is testing of new Reverse-Miner module, which can generate data with hidden properties using evolutionary algorithms while using also other modules of LISp-Miner system, commonly used for the purposes of data mining. Main goal lies in generation of two databases by the module in such way so they would meet explicitly set requirements. Other goals are also set within the thesis in the form of understanding the domain necessary for subsequent modeling. The result of the practical part of the thesis is represented not only by two successfully generated databases, but also by description of steps, methods and techniques used. The common recommendations for data preparation by module Reverse-Miner are later summarized, based on experience with modeling. Previous thesis outputs are furthermore contemplating the conclusion of analysis of technical means used for generation and they also provide several suggestions for possible future extensions.

O problema reconstrução filogenética têm como objetivo determinar as relações evolutivas das espécies, usualmente representadas em estruturas de árvores. No entanto, esse problema tem se mostrado muito difícil uma vez que o espaço de busca das possíveis árvores é muito grande. Diversos métodos de reconstrução filogenética têm sido propostos. Vários desses métodos definem um critério de otimalidade para avaliar as possíveis soluções do problema. Porém, a aplicação de diferentes critérios resulta em árvores diferentes, inconsistentes entre sim. Nesse contexto, uma abordagem multi-objetivo para a reconstrução filogenética pode ser útil produzindo um conjunto de árvores consideradas adequadas por mais de um critério. Nesta tese é proposto um algoritmo evolutivo multi-objetivo, denominado PhyloMOEA, para o problema de reconstrução filogenética. O PhyloMOEA emprega os critérios de parcimônia e verossimilhança que são dois dos métodos de reconstru ção filogenética mais empregados. Nos experimentos, o PhyloMOEA foi testado utilizando quatro bancos de seqüências freqüentemente empregados na literatura. Para cada banco de teste, o PhyloMOEA encontrou as soluções da fronteira de Pareto que representam um compromisso entre os critérios considerados. As árvores da fronteira de Pareto foram validadas estatisticamente utilizando o teste SH. Os resultados mostraram que o PhyloMOEA encontrou um número de soluções intermediárias que são consistentes com as soluções obtidas por análises de máxima parcimônia e máxima verossimilhança realizados separadamente. Além disso, os graus de suporte dos clados pertencentes às árvores encontradas pelo PhyloMOEA foram comparadas com a probabilidade posterior dos clados calculados pelo programa Mr.Bayes aplicados aos quatro bancos de teste. Os resultados indicaram que há uma relação entre ambos os valores para vários grupos de clados. Em resumo, o PhyloMOEA é capaz de encontrar uma diversidade de soluções intermediárias que são estatisticamente tão boas quanto as melhores soluções de máxima parcimônia e máxima verossimilhança. Tais soluções apresentam um compromisso entre os dois objetivos / The phylogeny reconstruction problem consists of determining the evolutionary relationships (usually represented as a tree) among species. This is a very complex problem since the tree search space is huge. Several phylogenetic reconstruction methods have been proposed. Many of them defines an optimality criterion for evaluation of possible solutions. However, different criteria may lead to distinct phylogenies, which often conflict with each other. In this context, a multi-objective approach for phylogeny reconstruction can be useful since it could produce a set of optimal trees according to mdifficultultiple criteria. In this thesis, a multi-objective evolutionary algorithm for phylogenetic reconstruction, called PhyloMOEA, is proposed. PhyloMOEA uses the parsimony and likelihood criteria, which are two of the most used phylogenetic reconstruction methods. PhyloMOEA was tested using four datasets of nucleotide sequences found in the literature. For each dataset, the proposed algorithm found a Pareto front representing a trade-off between the used criteria. Trees in the Pareto front were statistically validated using the SH-test, which has shown that a number of intermediate solutions from PhyloMOEA are consistent with solutions found by phylogenetic methods using one criterion. Moreover, clade support values from trees found by PhyloMOEA was compared to clade posterior probabilities obtained by Mr.Bayes. Results indicate a correlation between these probabilities for several clades. In summary, PhyloMOEA is able to find diverse intermediate solutions, which are not statistically worse than the best solutions for the maximum parsimony and maximum likelihood criteria. Moreover, intermediate solutions represent a trade-off between these criteria

Técnicas de agrupamento de dados usualmente assumem que o conjunto de dados é de tamanho fixo e pode ser alocado na memória. Neste contexto, um desafio consiste em aplicar técnicas de agrupamento em bases de dados de tamanho ilimitado, com dados gerados continuamente e em ambientes dinâmicos. Dados gerados nessas condições originam o que se convencionou chamar de Fluxo Contínuo de Dados (FCD). Em aplicações de FCD, operações de acesso aos dados são restritas a apenas uma leitura ou a um pequeno número de acessos aos dados, com limitações de memória e de tempo de processamento. Além disso, a distribuição dos dados gerados por essas fontes pode ser não estacionária, ou seja, podem ocorrer mudanças ao longo do tempo, denominadas de mudanças de conceito. Nesse sentido, algumas técnicas de agrupamento em FCD foram propostas na literatura. Muitas dessas técnicas são baseadas no algoritmo das k-Médias. Uma das limitações do algoritmo das k-Médias consiste na definição prévia do número de grupos. Ao se assumir que o número de grupos é desconhecido a priori e que deveria ser estimado a partir dos dados, percorrer o grande espaço de soluções possíveis (tanto em relação ao número de grupos, k, quanto em relação às partições possíveis para um determinado k) torna desafiadora a tarefa de agrupamento de dados - ainda mais sob a limitação de tempo e armazenamento imposta em aplicações de FCD. Neste contexto, essa tese tem como principais contribuições: (i) adaptar algoritmos que têm sido usados com sucesso em aplicações de Fluxo Contínuo de Dados (FCD) nas quais k é conhecido para cenários em que se deseja estimar o número de grupos; (ii) propor novos algoritmos para agrupamento que estimem k automaticamente a partir do FCD; (iii) avaliar sistematicamente, e de maneira quantitativa, os algoritmos propostos de acordo com as características específicas dos cenários de FCD. Foram desenvolvidos 14 algoritmos de agrupamento para FCD capazes de estimar o número de grupos a partir dos dados. Tais algoritmos foram avaliados em seis bases de dados artificiais e duas bases de dados reais amplamente utilizada na literatura. Os algoritmos desenvolvidos podem auxiliar em diversas áreas da Mineração em FCD. Os algoritmos evolutivos desenvolvidos mostraram a melhor relação de custo-benefício entre eficiência computacional e qualidade das partições obtidas. / Several algorithms for clustering data streams based on k-Means have been proposed in the literature. However, most of them assume that the number of clusters, k, is known a priori by the user and can be kept fixed throughout the data analysis process. Besides the dificulty in choosing k, data stream clustering imposes several challenges to be dealt with, such as addressing non-stationary, unbounded data that arrives in an online fashion. In data stream applications, the dataset must be accessed in order and that can be read only once or a small number of times. In this context, the main contributions of this thesis are: (i) adapt algorithms that have been used successfully in data stream applications where k is known to be able to estimate the number of clusters from data; (ii) propose new algorithms for clustering to estimate k automatically from the data stream; (iii) evaluate the proposed algorithms according to diferent scenarios. Fourteen clustering data stream algorithms were developed which are able to estimate the number of clusters from data. They were evaluated in six artificial datasets and two real-world datasets widely used in the literature. The developed algorithms are useful for several data mining tasks. The developed evolutionary algorithms have shown the best trade-off between computational efficiency and data partition quality.

Problemas de projeto de redes (PPRs) são muito importantes uma vez que envolvem uma série de aplicações em áreas da engenharia e ciências. Para solucionar as limitações de algoritmos convencionais para PPRs que envolvem redes complexas do mundo real (em geral modeladas por grafos completos ou mesmo esparsos de larga-escala), heurísticas, como os algoritmos evolutivos (EAs), têm sido investigadas. Trabalhos recentes têm mostrado que estruturas de dados adequadas podem melhorar significativamente o desempenho de EAs para PPRs. Uma dessas estruturas de dados é a representação nó-profundidade (NDE, do inglês Node-depth Encoding). Em geral, a aplicação de EAs com a NDE tem apresentado resultados relevantes para PPRs de larga-escala. Este trabalho investiga o desenvolvimento de uma nova representação, baseada na NDE, chamada representação nó-profundidade-grau (NDDE, do inglês Node-depth-degree Encoding). A NDDE é composta por melhorias nos operadores existentes da NDE e pelo desenvolvimento de novos operadores de reprodução possibilitando a recombinação de soluções. Nesse sentido, desenvolveu-se um operador de recombinação capaz de lidar com grafos não-completos e completos, chamado EHR (do inglês, Evolutionary History Recombination Operator). Foram também desenvolvidos operadores de recombinação que lidam somente com grafos completos, chamados de NOX e NPBX. Tais melhorias tem como objetivo manter relativamente baixa a complexidade computacional dos operadores para aumentar o desempenho de EAs para PPRs de larga-escala. A análise de propriedades de representações mostrou que a NDDE possui redundância, assim, foram propostos mecanismos para evitá-la. Essa análise mostrou também que o EHR possui baixa complexidade de tempo e não possui tendência, além de revelar que o NOX e o NPBX possuem uma tendência para árvores com topologia de estrela. A aplicação de EAs usando a NDDE para PPRs clássicos envolvendo grafos completos, tais como árvore geradora de comunicação ótima, árvore geradora mínima com restrição de grau e uma árvore máxima, mostrou que, quanto maior o tamanho das instâncias do PPR, melhor é o desempenho relativo da técnica em comparação com os resultados obtidos com outros EAs para PPRs da literatura. Além desses problemas, um EA utilizando a NDE com o operador EHR foi aplicado ao PPR do mundo real de reconfiguração de sistemas de distribuição de energia elétrica (envolvendo grafos esparsos). Os resultados mostram que o EHR possibilita reduzir significativamente o tempo de convergência do EA / Network design problems (NDPs) are very important since they involve several applications from areas of Engineering and Sciences. In order to solve the limitations of traditional algorithms for NDPs that involve real world complex networks (in general, modeled by large-scale complete or sparse graphs), heuristics, such as evolutionary algorithms (EAs), have been investigated. Recent researches have shown that appropriate data structures can improve EA performance when applied to NDPs. One of these data structures is the Node-depth Encoding (NDE). In general, the performance of EAs with NDE has presented relevant results for large-scale NDPs. This thesis investigates the development of a new representation, based on NDE, called Node-depth-degree Encoding (NDDE). The NDDE is composed for improvements of the NDE operators and the development of new reproduction operators that enable the recombination of solutions. In this way, we developed a recombination operator to work with both non-complete and complete graphs, called EHR (Evolutionary History Recombination Operator). We also developed two other operators to work only with complete graphs, named NOX and NPBX. These improvements have the advantage of retaining the computational complexity of the operators relatively low in order to improve the EA performance. The analysis of representation properties have shown that NDDE is a redundant representation and, for this reason, we proposed some strategies to avoid it. This analysis also showed that EHR has low running time and it does not have bias, moreover, it revealed that NOX and NPBX have bias to trees like stars. The application of an EA using the NDDE to classic NDPs, such as, optimal communication spanning tree, degree-constraint minimum spanning tree and one-max tree, showed that the larger the instance is, the better the performance will be in comparison whit other EAs applied to NDPs in the literatura. An EA using the NDE with EHR was applied to a real-world NDP of reconfiguration of energy distribution systems. The results showed that EHR significantly decrease the convergence time of the EA

L'augmentation de la contribution des énergies renouvelables (solaire ou éolien) et une évolution majeure du parc électrique français et s'inscrit dans le cadre de la transition énergétique. Il est prévu que la part de ces énergies dans le mix passe de 6% actuellement à 30% d'ici à 2030. Cette augmentation en revanche laisse entrevoir d'importants déséquilibres entre l'offre et la demande, et les autres moyens de production, l'énergie nucléaire en tête, devront donc s'adapter. Ce travail vise à augmenter la disponibilité de suivi de charge des centrales, en améliorant leur pilotage durant tout le cycle d'exploitation. Parmi l'ensemble des réacteurs du parc nucléaire français, les réacteurs à eau pressurisées d'une puissance électrique de $1300$ MW sont choisis en raison de leur capacité de suivi de charge déjà accrue. Dans un premier temps, un modèle multi-physique et de type simulateur de la centrale est développé, permettant de prendre en arguments les paramètres principaux des barres de commande, et permettant de déterminer en quelques dizaines de minutes de calcul, les critères d'intérêt dont le premier est en lien avec le diagramme de pilotage et le second avec le volume d'effluents. Le problème d'optimisation est alors résolu grâce à des algorithmes évolutionnaires parallèles asynchronesde type maître-esclave, et les mode de pilotage obtenus sont commentés. / The increase of the renewable energies contribution (as wind farms, solar energy) is a major issue in the actual context of energetic transition. The part of intermittent renewable energies is indeed forecast to be around 30% of the total production in 2030, against 6% today. On the other hand, their intermittent production may lead to an important imbalance between production and consumption. Consequently, the other ways of power production must adapt to those variations, especially nuclear energy which is the most important in France. This work aims at increasing the availability of thepower plants to load-follow, by optimizing their manageability all along their operation cycle. Among the French nuclear fleet, the pressurized water reactors(PWR) producing $1300$ electrical MW and operated in the "G" mode are considered as they show the higher capability to load-follow. In a first step, a multi-physics PWR model is designed taking as inputs the main parameters of the control rods, and computing in few minutes the criteria of interest whichare linked to the control diagram and to the effluents volume. The optimization problem which consists in minimizing those two values of interest is then solved thanks to a parallel asynchronous master-worker evolutionary algorithm. Finally, the efficient operating modes are discussed.

This paper researches the impact of different settings on an Infinite Impulse Response-filter (IIR-filter) used on a NIBE heat pump in combination with photovoltaic panels (PV-panel). The IIR-filter is applied to the level of the PV-panel’s power and its output is used by the heat pump’s control to harvest as much solar power as possible for supplying the heat pump with electricity. In some of the experiments weather data is used in the form of a forecast regarding the incoming cloudiness in the area, called “cloud coverage”. My objective is to find out which setting performs the best, and whether an evolutionary algorithm can find an optimal setting. The evolutionary algorithms I try are Genetic Algorithm, Simulated Annealing and the Hill Climbing algorithm. Historical data is collected from one of NIBE’s active heat pumps running in a field test. The data is processed and experimented on using an algorithm that analyzes how close a certain setting of values for the coefficient used in the filter and sensitivity of the cloud coverage forecast performs compared to an ideal reference. By using an evolutionary algorithm a better solution to the usage of solar energy can be found, compared to the non-evolutionary algorithm, by using a combination of different values for the coefficient in the filter, and also the cloud coverage forecast, which decides when we should change to another value for the filter coefficient.

This work focuses on automatization of neural network design via the so-called neuroevolution, which employs evolutionary algorithms to construct artificial neural networks or optimise their parameters. The goal of the project is to design and implement an evolutionary algorithm which can be used in the process of designing and optimizing topologies of convolutional neural networks. The effectiveness of the proposed framework was experimentally evaluated on tasks of image classification on datasets MNIST and CIFAR10 and compared with relevant solutions. The results showed that neuroevolution has a potential to successfully find accurate and effective convolutional neural network architectures.

The aim of this Master's thesis is to describe basic technics of evolutionary computing, convolutional neural networks (CNN), and automated design of neural networks using neuroevolution ( NAS - Neural Architecture Search ). NAS techniques are currently being researched more and more, as they speed up and simplify the lengthy and complicated process of designing artificial neural networks. These techniques are also able to search for unconventional architectures that would not be found by classic methods. The work also contains the design and implementation of software capable of automated development of convolutional neural networks using the open-source library TensorFlow. The program uses a multiobjective NSGA-II algorithm for designing accurate and compact CNNs.

This thesis deals with the placement of irregular shapes on a fixed width plane, which is a problem whose solution can be used, for example, when placing sewing patterns on fabric so that its length is as small as possible. A continuity of shapes depending on ma- terial patterns are also taken into account. The thesis uses evolutionary algorithms with heuristic functions that assign positions to individual shapes depending on the individual being developed by the relevant evolution. Patterned fabrics are treated differently using special heuristic functions types that are able to adjust the layout. 1