Speed Neuro-fuzzy Estimator Applied To Sensorless Induction Motor Control

This work proposes the development of an Adaptive Neuro-fuzzy Inference System (ANFIS) estimator applied to speed control in a three-phase induction motor sensorless drive. Usually, ANFIS is used to replace the traditional PI controller in induction motor drives. The evaluation of the estimation capability of the ANFIS in a sensorless drive is one of the contributions of this work. The ANFIS speed estimator is validated in a magnetizing flux oriented control scheme, consisting in one more contribution. As an open-loop estimator, it is applied to moderate performance drives and it is not the proposal of this work to solve the low and zero speed estimation problems. Simulations to evaluate the performance of the estimator considering the vector drive system were done from the Matlab/Simulink(R) software. To determine the benefits of the proposed model, a practical system was implemented using a voltage source inverter (VSI) to drive the motor and the vector control including the ANFIS estimator, which is carried out by the Real Time Toolbox from Matlab/Simulink(R) software and a data acquisition card from National Instruments.

Sobre a aplicação de sistemas inteligentes para diagnóstico de falhas em máquinas de indução - uma visão geral

Muitas pesquisas estão sendo desenvolvidas buscando nos sistemas inteligentes soluções para diagnosticar falhas em máquinas elétricas. Estas falhas envolvem desde problemas elétricos, como curto-circuito numa das fases do estator, ate problemas mecânicos, como danos nos rolamentos. Dentre os sistemas inteligentes aplicados nesta área, destacam-se as redes neurais artificiais, os sistemas fuzzy, os algoritmos genéticos e os sistemas híbridos, como o neuro-fuzzy. Assim, o objetivo deste artigo é traçar um panorama geral sobre os trabalhos mais relevantes que se beneficiaram dos sistemas inteligentes nas diferentes etapas de análise e diagnóstico de falhas em motores elétricos, cuja principal contribuição está em disponibilizar diversos aspectos técnicos a fim de direcionar futuros trabalhos nesta área de aplicação.

Redes neurais artificiais na previsão da inflação: aplicação como ferramenta de apoio à análise de decisões financeiras em organizações de pequeno porte

As estimações das taxas de inflação são de fundamental importância para os gestores, pois as decisões de investimento estão intimamente ligadas a elas. Contudo, o comportamento inflacionário tende a ser não linear e até mesmo caótico, tornando difícil a sua correta estimação. Essa característica do fenômeno pode tornar imprecisos os modelos mais simples de previsão, acessíveis às pequenas organizações, uma vez que muitos deles necessitam de grandes manipulações de dados e/ou softwares especializados. O presente artigo tem por objetivo avaliar, por meio de análise formal estatística, a eficácia das redes neurais artificiais (RNA) na previsão da inflação, dentro da realidade de organizações de pequeno porte. As RNA são ferramentas adequadas para mensurar os fenômenos inflacionários, por se tratar de aproximações de funções polinomiais, capazes de lidar com fenômenos não lineares. Para esse processo, foram selecionados três modelos básicos de redes neurais artificiais Multi Layer Perceptron, passíveis de implementação a partir de planilhas eletrônicas de código aberto. Os três modelos foram testados a partir de um conjunto de variáveis independentes sugeridas por Bresser-Pereira e Nakano (1984), com defasagem de um, seis e doze meses. Para tal, foram utilizados testes de Wilcoxon, coeficiente de determinação R² e o percentual de erro médio dos modelos. O conjunto de dados foi dividido em dois, sendo um grupo usado para treinamento das redes neurais artificiais, enquanto outro grupo era utilizado para verificar a capacidade de predição dos modelos e sua capacidade de generalização. Com isso, o trabalho concluiu que determinados modelos de redes neurais artificiais têm uma razoável capacidade de predição da inflação no curto prazo e se constituem em uma alternativa razoável para esse tipo de mensuração.

Variance Reduction in Analytical Chemistry : New Numerical Methods in Chemometrics and Molecular Simulation

This thesis is based on five papers addressing variance reduction in different ways. The papers have in common that they all present new numerical methods. Paper I investigates quantitative structure-retention relationships from an image processing perspective, using an artificial neural network to preprocess three-dimensional structural descriptions of the studied steroid molecules. Paper II presents a new method for computing free energies. Free energy is the quantity that determines chemical equilibria and partition coefficients. The proposed method may be used for estimating, e.g., chromatographic retention without performing experiments. Two papers (III and IV) deal with correcting deviations from bilinearity by so-called peak alignment. Bilinearity is a theoretical assumption about the distribution of instrumental data that is often violated by measured data. Deviations from bilinearity lead to increased variance, both in the data and in inferences from the data, unless invariance to the deviations is built into the model, e.g., by the use of the method proposed in paper III and extended in paper IV. Paper V addresses a generic problem in classification; namely, how to measure the goodness of different data representations, so that the best classifier may be constructed. Variance reduction is one of the pillars on which analytical chemistry rests. This thesis considers two aspects on variance reduction: before and after experiments are performed. Before experimenting, theoretical predictions of experimental outcomes may be used to direct which experiments to perform, and how to perform them (papers I and II). After experiments are performed, the variance of inferences from the measured data are affected by the method of data analysis (papers III-V).

Strumenti per la valutazione dello stato conservativo e per la manutenzione programmata dei ponti della Provincia di Bologna

La tesi tratta di strumenti finalizzati alla valutazione dello stato conservativo e di supporto all'attività di manutenzione dei ponti, dai più generali Bridge Management Systems ai Sistemi di Valutazione Numerica della Condizione strutturale. Viene proposto uno strumento originale con cui classificare i ponti attraverso un Indice di Valutazione Complessiva e grazie ad esso stabilire le priorità d'intervento. Si tara lo strumento sul caso pratico di alcuni ponti della Provincia di Bologna. Su un ponte in particolare viene realizzato un approfondimento specifico sulla determinazione approssimata dei periodi propri delle strutture da ponte. Si effettua un confronto dei risultati di alcune modellazioni semplificate in riferimento a modellazioni dettagliate e risultati sperimentali.

Nonlinear/electromagnetic co-simulation of microwaves and millimeter-waves links

The Ph.D. thesis describes the simulations of different microwave links from the transmitter to the receiver intermediate-frequency ports, by means of a rigorous circuit-level nonlinear analysis approach coupled with the electromagnetic characterization of the transmitter and receiver front ends. This includes a full electromagnetic computation of the radiated far field which is used to establish the connection between transmitter and receiver. Digitally modulated radio-frequency drive is treated by a modulation-oriented harmonic-balance method based on Krylov-subspace model-order reduction to allow the handling of large-size front ends. Different examples of links have been presented: an End-to-End link simulated by making use of an artificial neural network model; the latter allows a fast computation of the link itself when driven by long sequences of the order of millions of samples. In this way a meaningful evaluation of such link performance aspects as the bit error rate becomes possible at the circuit level. Subsequently, a work focused on the co-simulation an entire link including a realistic simulation of the radio channel has been presented. The channel has been characterized by means of a deterministic approach, such as Ray Tracing technique. Then, a 2x2 multiple-input multiple-output antenna link has been simulated; in this work near-field and far-field coupling between radiating elements, as well as the environment factors, has been rigorously taken into account. Finally, within the scope to simulate an entire ultra-wideband link, the transmitting side of an ultrawideband link has been designed, and an interesting Front-End co-design technique application has been setup.

Machine learning methods for prediction of disulphide bonding states of cysteine residues in proteins

The goal of this thesis work is to develop a computational method based on machine learning techniques for predicting disulfide-bonding states of cysteine residues in proteins, which is a sub-problem of a bigger and yet unsolved problem of protein structure prediction. Improvement in the prediction of disulfide bonding states of cysteine residues will help in putting a constraint in the three dimensional (3D) space of the respective protein structure, and thus will eventually help in the prediction of 3D structure of proteins. Results of this work will have direct implications in site-directed mutational studies of proteins, proteins engineering and the problem of protein folding. We have used a combination of Artificial Neural Network (ANN) and Hidden Markov Model (HMM), the so-called Hidden Neural Network (HNN) as a machine learning technique to develop our prediction method. By using different global and local features of proteins (specifically profiles, parity of cysteine residues, average cysteine conservation, correlated mutation, sub-cellular localization, and signal peptide) as inputs and considering Eukaryotes and Prokaryotes separately we have reached to a remarkable accuracy of 94% on cysteine basis for both Eukaryotic and Prokaryotic datasets, and an accuracy of 90% and 93% on protein basis for Eukaryotic dataset and Prokaryotic dataset respectively. These accuracies are best so far ever reached by any existing prediction methods, and thus our prediction method has outperformed all the previously developed approaches and therefore is more reliable. Most interesting part of this thesis work is the differences in the prediction performances of Eukaryotes and Prokaryotes at the basic level of input coding when ‘profile’ information was given as input to our prediction method. And one of the reasons for this we discover is the difference in the amino acid composition of the local environment of bonded and free cysteine residues in Eukaryotes and Prokaryotes. Eukaryotic bonded cysteine examples have a ‘symmetric-cysteine-rich’ environment, where as Prokaryotic bonded examples lack it.

Zu Problemen der Flüssigszintillationsspektroskopie bei Transactiniden-Experimenten

Die vorliegende Arbeit beschäftigt sich vorwiegend mit Detektionsproblemen, die bei Experimenten zur Chemie der Transactiniden mit dem schnellen Flüssig-Flüssig-Extraktionssystem SISAK auftraten. Bei diesen Experimenten wird als Detektionsmethode die Flüssigszintillationsspektroskopie (LSC) eingesetzt. Es werden Szintillationspulse registriert, die für das verursachende Teilchen charakteristische Formen zeigen, die unterschieden werden müssen. Am Beispiel der Auswertung des SISAK-Experimentes zur Chemie des Rutherfordiums vom November 1998 wurde gezeigt, dass es mit den herkömmlichen Verfahren zur Pulsformdiskriminierung nicht möglich ist, die aus dem Zerfall der Transactiniden stammenden alpha-Ereignisse herauszufiltern. Ursache dafür ist ein hoher Untergrund, der in erster Linie von beta/gamma-Teilchen, Spaltfragmenten und pile ups verursacht wird. Durch die Verfügbarkeit von Transientenrecordern ergeben sich neue Möglichkeiten für eine digitale Pulsformdiskriminierung. In dieser Arbeit wird erstmals die Methode der digitalen Pulsformdiskriminierung mit künstlichen neuronalen Netzen (PSD-NN) vorgestellt. Es wurde im Zuge der Auswertung des SISAK-Experimentes vom Februar 2000 gezeigt, dass neuronale Netze in der Lage sind, Pulsformen automatisch richtig zu klassifizieren. Es ergeben sich nahezu untergrundfreie alpha-Flüssigszintillationsspektren. Es werden Vor- und Nachteile der neuen Methode diskutiert. Es ist dadurch möglich geworden, in SISAK-Experimenten Transactinidenatome anhand ihres Zerfalls eindeutig zu charakterisieren. Das SISAK-System kann somit bei Experimenten zum Studium des chemischen Verhaltens von Transactiniden in flüssiger Phase eingesetzt werden.____

A numerical methodology for the multi-objective optimization of the DI Diesel engine combustion

DI Diesel engine are widely used both for industrial and automotive applications due to their durability and fuel economy. Nonetheless, increasing environmental concerns force that type of engine to comply with increasingly demanding emission limits, so that, it has become mandatory to develop a robust design methodology of the DI Diesel combustion system focused on reduction of soot and NOx simultaneously while maintaining a reasonable fuel economy. In recent years, genetic algorithms and CFD three-dimensional combustion simulations have been successfully applied to that kind of problem. However, combining GAs optimization with actual CFD three-dimensional combustion simulations can be too onerous since a large number of calculations is usually needed for the genetic algorithm to converge, resulting in a high computational cost and, thus, limiting the suitability of this method for industrial processes. In order to make the optimization process less time-consuming, CFD simulations can be more conveniently used to generate a training set for the learning process of an artificial neural network which, once correctly trained, can be used to forecast the engine outputs as a function of the design parameters during a GA optimization performing a so-called virtual optimization. In the current work, a numerical methodology for the multi-objective virtual optimization of the combustion of an automotive DI Diesel engine, which relies on artificial neural networks and genetic algorithms, was developed.

Lernen mit einer Hybride aus Lernendem Klassifizierendem System und Selbstorganisierender Karte

Im Forschungsgebiet der Künstlichen Intelligenz, insbesondere im Bereich des maschinellen Lernens, hat sich eine ganze Reihe von Verfahren etabliert, die von biologischen Vorbildern inspiriert sind. Die prominentesten Vertreter derartiger Verfahren sind zum einen Evolutionäre Algorithmen, zum anderen Künstliche Neuronale Netze. Die vorliegende Arbeit befasst sich mit der Entwicklung eines Systems zum maschinellen Lernen, das Charakteristika beider Paradigmen in sich vereint: Das Hybride Lernende Klassifizierende System (HCS) wird basierend auf dem reellwertig kodierten eXtended Learning Classifier System (XCS), das als Lernmechanismus einen Genetischen Algorithmus enthält, und dem Wachsenden Neuralen Gas (GNG) entwickelt. Wie das XCS evolviert auch das HCS mit Hilfe eines Genetischen Algorithmus eine Population von Klassifizierern - das sind Regeln der Form [WENN Bedingung DANN Aktion], wobei die Bedingung angibt, in welchem Bereich des Zustandsraumes eines Lernproblems ein Klassifizierer anwendbar ist. Beim XCS spezifiziert die Bedingung in der Regel einen achsenparallelen Hyperquader, was oftmals keine angemessene Unterteilung des Zustandsraumes erlaubt. Beim HCS hingegen werden die Bedingungen der Klassifizierer durch Gewichtsvektoren beschrieben, wie die Neuronen des GNG sie besitzen. Jeder Klassifizierer ist anwendbar in seiner Zelle der durch die Population des HCS induzierten Voronoizerlegung des Zustandsraumes, dieser kann also flexibler unterteilt werden als beim XCS. Die Verwendung von Gewichtsvektoren ermöglicht ferner, einen vom Neuronenadaptationsverfahren des GNG abgeleiteten Mechanismus als zweites Lernverfahren neben dem Genetischen Algorithmus einzusetzen. Während das Lernen beim XCS rein evolutionär erfolgt, also nur durch Erzeugen neuer Klassifizierer, ermöglicht dies dem HCS, bereits vorhandene Klassifizierer anzupassen und zu verbessern. Zur Evaluation des HCS werden mit diesem verschiedene Lern-Experimente durchgeführt. Die Leistungsfähigkeit des Ansatzes wird in einer Reihe von Lernproblemen aus den Bereichen der Klassifikation, der Funktionsapproximation und des Lernens von Aktionen in einer interaktiven Lernumgebung unter Beweis gestellt.

A New Prediction Model for Slope Stability Analysis

The instability of river bank can result in considerable human and land losses. The Po river is the most important in Italy, characterized by main banks of significant and constantly increasing height. This study presents multilayer perceptron of artificial neural network (ANN) to construct prediction models for the stability analysis of river banks along the Po River, under various river and groundwater boundary conditions. For this aim, a number of networks of threshold logic unit are tested using different combinations of the input parameters. Factor of safety (FS), as an index of slope stability, is formulated in terms of several influencing geometrical and geotechnical parameters. In order to obtain a comprehensive geotechnical database, several cone penetration tests from the study site have been interpreted. The proposed models are developed upon stability analyses using finite element code over different representative sections of river embankments. For the validity verification, the ANN models are employed to predict the FS values of a part of the database beyond the calibration data domain. The results indicate that the proposed ANN models are effective tools for evaluating the slope stability. The ANN models notably outperform the derived multiple linear regression models.

Global and regional sea level variations in the recent past and future: insight from observations and modeling

This work is focused on the analysis of sea–level change (last century), based mainly on instrumental observations. During this period, individual components of sea–level change are investigated, both at global and regional scales. Some of the geophysical processes responsible for current sea-level change such as glacial isostatic adjustments and current melting terrestrial ice sources, have been modeled and compared with observations. A new value of global mean sea level change based of tide gauges observations has been independently assessed in 1.5 mm/year, using corrections for glacial isostatic adjustment obtained with different models as a criterion for the tide gauge selection. The long wavelength spatial variability of the main components of sea–level change has been investigated by means of traditional and new spectral methods. Complex non–linear trends and abrupt sea–level variations shown by tide gauges records have been addressed applying different approaches to regional case studies. The Ensemble Empirical Mode Decomposition technique has been used to analyse tide gauges records from the Adriatic Sea to ascertain the existence of cyclic sea-level variations. An Early Warning approach have been adopted to detect tipping points in sea–level records of North East Pacific and their relationship with oceanic modes. Global sea–level projections to year 2100 have been obtained by a semi-empirical approach based on the artificial neural network method. In addition, a model-based approach has been applied to the case of the Mediterranean Sea, obtaining sea-level projection to year 2050.

Extracting FSA descriptions of robot behaviours from the dynamics of automatically designed controller networks

Automatic design has become a common approach to evolve complex networks, such as artificial neural networks (ANNs) and random boolean networks (RBNs), and many evolutionary setups have been discussed to increase the efficiency of this process. However networks evolved in this way have few limitations that should not be overlooked. One of these limitations is the black-box problem that refers to the impossibility to analyze internal behaviour of complex networks in an efficient and meaningful way. The aim of this study is to develop a methodology that make it possible to extract finite-state automata (FSAs) descriptions of robot behaviours from the dynamics of automatically designed complex controller networks. These FSAs unlike complex networks from which they're extracted are both readable and editable thus making the resulting designs much more valuable.