Dans le domaine d’optimisation de forme de structures, la réduction des coûts et l’amélioration des produits sont des défis permanents à relever. Pour ce faire, le procédé de mise en forme doit être optimisé. Optimiser le procédé revient alors à résoudre un problème d’optimisation. Généralement ce problème est un problème d’optimisation multicritère très coûteux en terme de temps de calcul, où on cherche à minimiser plusieurs fonctions coût en présence d’un certain nombre de contraintes. Pour résoudre ce type de problème, on a développé un algorithme robuste, efficace et fiable. Cet algorithme, consiste à coupler un algorithme de capture de front de Pareto (NBI ou NNCM) avec un métamodèle (RBF), c’est-à-dire des approximations des résultats des simulations coûteuses. D’après l’ensemble des résultats obtenus par cette approche, il est intéressant de souligner que la capture de front de Pareto génère un ensemble des solutions non dominées. Pour savoir lesquelles choisir, le cas échéant, il est nécessaire de faire appel à des algorithmes de sélection, comme par exemple Nash et Kalai-Smorodinsky. Ces deux approches, issues de la théorie des jeux, ont été utilisées pour notre travail. L’ensemble des algorithmes sont validés sur deux cas industriels proposés par notre partenaire industriel. Le premier concerne un modèle 2D du fond de la canette (elasto-plasticité) et le second est un modèle 3D de la traverse (élasticité linéaire). Les résultats obtenus confirment l’efficacité de nos algorithmes développés. / One of the current challenges in the domain of the multiobjective shape optimization is to reduce the calculation time required by conventional methods. The high computational cost is due to the high number of simulation or function calls required by these methods. Recently, several studies have been led to overcome this problem by integratinga metamodel in the overall optimization loop. In this thesis, we perform a coupling between the Normal Boundary Intersection -NBI- algorithm and The Normalized Normal constraint Method -NNCM- algorithm with Radial Basis Function -RBF- metamodel in order to have asimple tool with a reasonable calculation time to solve multicriteria optimization problems. First, we apply our approach to academic test cases. Then, we validate our method against two industrial cases, namely, shape optimization of the bottom of a can undergoing nonlinear elasto-plastic deformation and an optimization of an automotive twist beam. Then, in order to select solutions among the Pareto efficient ones, we use the same surrogate approach to implement a method to compute Nash and Kalai-Smorodinsky equilibria.

Dans l’industrie de fabrication mécanique et notamment pour l’utilisation des centres d’usinage haute vitesse, la connaissance des propriétés dynamiques du système broche-outil-pièce en opération est d’une grande importance. L’accroissement des performances des machines-outils et des outils de coupe a œuvré au développement de ce procédé compétitif. D’innombrables travaux ont été menés pour accroître les performances et les remarquables avancées dans les matériaux, les revêtements des outils coupants et les lubrifiants ont permis d’accroître considérablement les vitesses de coupe tout en améliorant la qualité de la surface usinée. Cependant, l’utilisation rationnelle de cette technologie est encore fortement pénalisée par les lacunes dans la connaissance de la coupe, que ce soit au niveau microscopique des interactions fines entre l’outil et la matière coupée, aussi bien qu’au niveau macroscopique intégrant le comportement de la cellule élémentaire d’usinage, si bien que le comportement dynamique en coupe garde encore une grande part de questionnement et exige de l’utilisateur un bon niveau de savoir-faire et parfois d’empirisme pour exploiter au mieux les capacités des moyens de production. Le fonctionnement des machines d’usinage engendre des vibrations qui sont souvent la cause des dysfonctionnements et accélère l’usure des composantes mécaniques (roulements) et outils. Ces vibrations sont une image des efforts internes des systèmes, d’où l’intérêt d’analyser les grandeurs mécaniques vibratoires telle que la vitesse ou l’accélération vibratoire. Ces outils sont indispensables pour une maintenance moderne dont l’objectif est de réduire les coûts liés aux pannes / In machining field, chatter phenomenon takes a lot of interest because manufacturing enterprises are turning to the automation system and the development of reliable and robust monitoring system to provide increased productivity, improved part quality and reduced costs. Chatter occurrence has several negatives effects: a) Poor surface quality, b) Unacceptable inaccuracy, c) Excessive noise, d) Machine tool damage, e) Reduced material removal rate, f) Increase costs in terms of production time, g) Waste of material, h) Environmental impact in terms of materials and energy. Moreover, chatter monitoring is not an easy task for various reasons. Firstly, the non linearity of machining processes and the time-varying of systems complicate this task. Secondly, the sensitivity and the dependency of acquired signals from sensors on different factors, such as machining condition, cutting tool geometry and workpiece material. Thirdly, at high rotating speeds, the gyroscopic effects on the spindle dynamics in addition to the centrifugal force on the bearings and thermal effects become more relevant thus affecting the stability of the system. For these reasons, demands for an advanced automatic chatter detection and monitoring system for optimizing and controlling machining processes becomes a topic of enormous interest. Several researches in this field are performed. Advanced monitoring and detection methods are developed mostly relying on time, frequency and time-frequency analysis. In order to detect chatter in milling centers, three new methods are studied and developed using advanced techniques of signal processing and exploiting cyclostationarity property of signals acquired

The present work focuses on the two areas of investigation: system identification of helicopter and design of controller for the helicopter. Helicopter system identification, the first subject of investigation in this thesis, can be described as the extraction of system characteristics/dynamics from measured flight test data. Wind tunnel experimental data suffers from scale effects and model deficiencies. The increasing need for accurate models for the design of high bandwidth control system for helicopters has initiated a renewed interest in and a more active use of system identification. Besides, system identification is likely to become mandatory in the future for model validation of ground based helicopter simulators. Such simulators require accurate models in order to be accepted by pilots and regulatory authorities like Federal Aviation Regulation for realistic complementary helicopter mission training. Two approaches are widely used for system identification, namely, black box and gray box approach. In the black-box approach, the relationship between input-output data is approximated using nonparametric methods such as neural networks and in such a case, internal details of the system and model structure may not be known. In the gray box approach, parameters are estimated after defining the model structure. In this thesis, both black box and gray box approaches are investigated. In the black box approach, in this thesis, a comparative study and analysis of different Recurrent Neural Networks(RNN) for the identification of helicopter dynamics using flight data is investigated. Three different RNN architectures namely, Nonlinear Auto Regressive eXogenous input(NARX) model, neural network with internal memory known as Memory Neuron Networks(MNN)and Recurrent MultiLayer perceptron (RMLP) networks are used to identify dynamics of the helicopter at various flight conditions. Based on the results, the practical utility, advantages and limitations of the three models are critically appraised and it is found that the NARX model is most suitable for the identification of helicopter dynamics. In the gray box approach, helicopter model parameters are estimated after defining the model structure. The identification process becomes more difficult as the number of degrees-of-freedom and model parameters increase. To avoid the drawbacks of conventional methods, neural network based techniques, called the delta method is investigated in this thesis. This method does not require initial estimates of the parameters and the parameters can be directly extracted from the flight data. The Radial Basis Function Network(RBFN)is used for the purpose of estimation of parameters. It is shown that RBFN is able to satisfactorily estimate stability and control derivatives using the delta method. The second area of investigation addressed in this thesis is the control of helicopter in flight. Helicopter requires use of a control system to achieve satisfactory flight. Designing a classical controller involves developing a nonlinear model of the helicopter and extracting linearized state space matrices from the nonlinear model at various flight conditions. After examining the stability characteristics of the helicopter, the desired response is obtained using a feedback control system. The scheduling of controller gains over the entire envelope is used to obtain the desired response. In the present work, a helicopter having a soft inplane four bladed hingeless main rotor and a four-bladed tail rotor with conventional mechanical controls is considered. For this helicopter, a mathematical model and also a model based on neural network (using flight data) has been developed. As a precursor, a feed back controller, the Stability Augmentation System(SAS), is designed using linear quadratic regulator control with full state feedback and LQR with out put feedback approaches. SAS is designed to meet the handling qualities specification known as Aeronautical Design Standard ADS-33E-PRF. The control gains have been tuned with respect to forward speed and gain scheduling has been arrived at. The SAS in the longitudinal axis meets the requirement of the Level1 handling quality specifications in hover and low speed as well as for forward speed flight conditions. The SAS in the lateral axis meets the requirement of the Level2 handling quality specifications in both hover and low speed as well as for forward speed flight conditions. Such conventional design of control has served useful purposes, however, it requires considerable flight testing which is time consuming, to demonstrate and tune these control law gains. In modern helicopters, the stringent requirements and non-linear maneuvers make the controller design further complicated. Hence, new design tools have to be explored to control such helicopters. Among the many approaches in adaptive control, neural networks present a potential alternative for modeling and control of nonlinear dynamical systems due to their approximating capabilities and inherent adaptive features. Furthermore, from a practical perspective, the massive parallelism and fast adaptability of neural network implementations provide more incentive for further investigation in problems involving dynamical systems with unknown non-linearity. Therefore, adaptive control approach based on neural networks is proposed in this thesis. A neural network based Feedback Error Neural adaptive Controller(FENC) is designed for a helicopter. The proposed controller scheme is based on feedback error learning strategy in which the outer loop neural controller enhances the inner loop conventional controller by compensating for unknown non-linearity and parameter un-certainties. Nonlinear Auto Regressive eXogenous input(NARX)neural network architecture is used to approximate the control law and the controller network parameters are adapted using updated rules Lyapunov synthesis. An offline (finite time interval)and on-line adaptation strategy is used to approximate system uncertainties. The results are validated using simulation studies on helicopter undergoing an agile maneuver. The study shows that the neuro-controller meets the requirements of ADS-33 handling quality specifications. Even though the tracking error is less in FENC scheme, the control effort required to follow the command is very high. To overcome these problems, a Direct Adaptive Neural Control(DANC)scheme to track the rate command signal is presented. The neural controller is designed to track rate command signal generated using the reference model. For the simulation study, a linearized helicopter model at different straight and level flight conditions is considered. A neural network with a linear filter architecture trained using back propagation through time is used to approximate the control law. The controller network parameters are adapted using updated rules Lyapunov synthesis. The off-line trained (for finite time interval)network provides the necessary stability and tracking performance. The on-line learning is used to adapt the network under varying flight conditions. The on-line learning ability is demonstrated through parameter uncertainties. The performance of the proposed direct adaptive neural controller is compared with feedback error learning neural controller. The performance of the controller has been validated at various flight conditions. The theoretical results are validated using simulation studies based on a nonlinear six degree-of-freedom helicopter undergoing an agile maneuver. Realistic gust and sensor noise are added to the system to study the disturbance rejection properties of the neural controllers. To investigate the on-line learning ability of the proposed neural controller, different fault scenarios representing large model error and control surface loss are considered. The performances of the proposed DANC scheme is compared with the FENC scheme. The study shows that the neuro-controller meets the requirements of ADS-33 handling quality specifications.

This study proposes novel optimization methodologies for the optimization of problems that reveal non-physical step discontinuities. More specifically, it is proposed to use gradient-only techniques that do not use any zeroth order information at all for step discontinuous problems. A step discontinuous problem of note is the shape optimization problem in the presence of remeshing strategies, since changes in mesh topologies may - and normally do - introduce non-physical step discontinuities. These discontinuities may in turn manifest themselves as non-physical local minima in which optimization algorithms may become trapped. Conventional optimization approaches for step discontinuous problems include evolutionary strategies, and design of experiment (DoE) techniques. These conventional approaches typically rely on the exclusive use of zeroth order information to overcome the discontinuities, but are characterized by two important shortcomings: Firstly, the computational demands of zero order methods may be very high, since many function values are in general required. Secondly, the use of zero order information only does not necessarily guarantee that the algorithms will not terminate in highly unfit local minima. In contrast, the methodologies proposed herein use only first order information, rather than only zeroth order information. The motivation for this approach is that associated gradient information in the presence of remeshing remains accurately and uniquely computable, notwithstanding the presence of discontinuities. From a computational effort point of view, a gradient-only approach is of course comparable to conventional gradient based techniques. In addition, the step discontinuities do not manifest themselves as local minima. / Thesis (PhD)--University of Pretoria, 2010. / Mechanical and Aeronautical Engineering / unrestricted

In the 21st century, information is the new currency. With the omnipresence of devices connected to the internet, humanity can instantly avail any information. However, there are certain are cybercrime groups which steal the information. An Intrusion Detection System (IDS) monitors a network for suspicious activities and alerts its owner about an undesired intrusion. These commercial IDS’es react after detecting intrusion attempts. With the cyber attacks becoming increasingly complex, it is expensive to wait for the attacks to happen and respond later. It is crucial for network owners to employ IDS’es that preemptively differentiate a harmless data request from a malicious one. Machine Learning (ML) can solve this problem by recognizing patterns in internet traffic to predict the behaviour of network users. This project studies how effectively Radial Basis Function Neural Network (RBFN) with Deep Learning Architecture can impact intrusion detection. On the basis of the existing framework, it asks how well can an RBFN predict malicious intrusive attempts, especially when compared to contemporary detection practices.Here, an RBFN is a multi-layered neural network model that uses a radial basis function to transform input traffic data. Once transformed, it is possible to separate the various traffic data points using a single straight line in extradimensional space. The outcome of the project indicates that the proposed method is severely affected by limitations. E.g. the model needs to be fine tuned over several trials to achieve a desired accuracy. The results of the implementation show that RBFN is accurate at predicting various cyber attacks such as web attacks, infiltrations, brute force, SSH etc, and normal internet behaviour on an average 80% of the time. Other algorithms in identical testbed are more than 90% accurate. Despite the lower accuracy, RBFN model is more than 94% accurate at recording specific kinds of attacks such as Port Scans and BotNet malware. One possible solution is to restrict this model to predict only malware attacks and use different machine learning algorithm for other attacks. / I det 21: a århundradet är information den nya valutan. Med allnärvaro av enheter anslutna till internet har mänskligheten tillgång till information inom ett ögonblick. Det finns dock vissa grupper som använder metoder för att stjäla information för personlig vinst via internet. Ett intrångsdetekteringssystem (IDS) övervakar ett nätverk för misstänkta aktiviteter och varnar dess ägare om ett oönskat intrång skett. Kommersiella IDS reagerar efter detekteringen av ett intrångsförsök. Angreppen blir alltmer komplexa och det kan vara dyrt att vänta på att attackerna ska ske för att reagera senare. Det är avgörande för nätverksägare att använda IDS:er som på ett förebyggande sätt kan skilja på oskadlig dataanvändning från skadlig. Maskininlärning kan lösa detta problem. Den kan analysera all befintliga data om internettrafik, känna igen mönster och förutse användarnas beteende. Detta projekt syftar till att studera hur effektivt Radial Basis Function Neural Networks (RBFN) med Djupinlärnings arkitektur kan påverka intrångsdetektering. Från detta perspektiv ställs frågan hur väl en RBFN kan förutsäga skadliga intrångsförsök, särskilt i jämförelse med befintliga detektionsmetoder.Här är RBFN definierad som en flera-lagers neuralt nätverksmodell som använder en radiell grundfunktion för att omvandla data till linjärt separerbar. Efter en undersökning av modern litteratur och lokalisering av ett namngivet dataset användes kvantitativ forskningsmetodik med prestanda indikatorer för att utvärdera RBFN: s prestanda. En Random Forest Classifier algorithm användes också för jämförelse. Resultaten erhölls efter en serie finjusteringar av parametrar på modellerna. Resultaten visar att RBFN är korrekt när den förutsäger avvikande internetbeteende i genomsnitt 80% av tiden. Andra algoritmer i litteraturen beskrivs som mer än 90% korrekta. Den föreslagna RBFN-modellen är emellertid mycket exakt när man registrerar specifika typer av attacker som Port Scans och BotNet malware. Resultatet av projektet visar att den föreslagna metoden är allvarligt påverkad av begränsningar. T.ex. så behöver modellen finjusteras över flera försök för att uppnå önskad noggrannhet. En möjlig lösning är att begränsa denna modell till att endast förutsäga malware-attacker och använda andra maskininlärnings-algoritmer för andra attacker.

<p>Математички модели за естимацију тешко мерљивих величина називају<br />се софт сензорима. Процес формирања софт сензора није тривијалан и<br />квалитет естимације тешко мерљиве величине директно зависи од<br />начина формирања. Недостаци постојећих алгоритама за формирање<br />спречавају аутоматску конфигурацију софт сензора. У овом раду су<br />реализовани нови алгоритми који имају за сврху аутоматизацију<br />конфигурације софт сензора. Реализовани алгоритми решавају<br />проблеме проналаска оптималног сета улаза у софт сензор и кашњења<br />сваког од њих као и одабира структуре и начина обуке софт сензора<br />заснованих на вештачким неуронским мрежама са радијално базираним<br />функцијама.</p> / <p>Matematički modeli za estimaciju teško merljivih veličina nazivaju<br />se soft senzorima. Proces formiranja soft senzora nije trivijalan i<br />kvalitet estimacije teško merljive veličine direktno zavisi od<br />načina formiranja. Nedostaci postojećih algoritama za formiranje<br />sprečavaju automatsku konfiguraciju soft senzora. U ovom radu su<br />realizovani novi algoritmi koji imaju za svrhu automatizaciju<br />konfiguracije soft senzora. Realizovani algoritmi rešavaju<br />probleme pronalaska optimalnog seta ulaza u soft senzor i kašnjenja<br />svakog od njih kao i odabira strukture i načina obuke soft senzora<br />zasnovanih na veštačkim neuronskim mrežama sa radijalno baziranim<br />funkcijama.</p> / <p>Mathematical models that are used for estimation of variables that can not be<br />measured in real time are called soft sensors. Creation of soft sensor is a<br />complex process and quality of estimation depends on the way soft sensor is<br />created. Restricted applicability of existing algorithms is preventing automatic<br />configuration of soft sensors. This paper presents new algorithms that are<br />providing automatic configuration of soft sensors. Presented algorithms are<br />capable of determing optimal subset of soft sensor inputs and their time<br />delays, as well as optimal architecture and automatic training of the soft<br />sensors that are based on artificial radial basis function networks.</p>

No description available.

Face recognition is a field of biometrics that deals with identification of subjects based on features present in the images of their faces. The factors that make face recognition popular and favorite as compared to other biometric methods are easier operation and ability to identify subjects without their knowledge. With these features, face recognition has become an integral part of the present day security systems, targeting a smart and secure world. There are various factors that de ne the performance of a face recognition system. The most important among them are recognition accuracy of algorithm used and time taken for recognition. Recognition accuracy of the face recognition algorithm gets affected by changes in pose, facial expression and illumination along with occlusions in the images. There have been a number of algorithms proposed to enable recognition under these ambient changes. However, it has been hard to and a single algorithm that can efficiently recognize faces in all the above mentioned conditions. Moreover, achieving real time performance for most of the complex face recognition algorithms on embedded platforms has been a challenge. Real-time performance is highly preferred in critical applications such as identification of crime suspects in public. As available software solutions for FR have significantly large latency in recognizing individuals, they are not suitable for such critical real-time applications. This thesis focuses on real-time aspect of FR, where acceleration of the algorithms is achieved by means of parallel hardware architectures. The major contributions of this work are as follows. We target to design a face recognition system that can identify at most 30 faces in each frame of video at 15 frames per second, which amounts to 450 recognitions per second. In addition, we target to achieve good recognition accuracy along with scalability in terms of database size and input image resolutions. To design a system with these specifications, as a first step, we explore algorithms in literature and come up with a hybrid face recognition algorithm. This hybrid algorithm shows good recognition accuracy on face images with changes in illumination, pose and expressions, and also with occlusions. In addition the computations in the algorithm are modular in nature which are suitable for real-time realizations through parallel processing. The face recognition system consists of a face detection module to detect faces in the input image, which is followed by a face recognition module to identify the detected faces. There are well established algorithms and architectures for face detection in literature which can perform detection at 15 frames per second on video frames. Detected faces of different sizes need to be scaled to the size specified by the face recognition module. To meet the real-time constraints, we propose a hardware architecture for real-time bi-cubic convolution interpolation with dynamic scaling factors. To recognize the resized faces in real-time, a scalable parallel pipelined architecture is designed for the hybrid algorithm which can perform 450 recognitions per second on a database containing grayscale images of at most 450 classes on Virtex 6 FPGA. To provide flexibility and programmability, we extend this design to REDEFINE, a multi-core massively parallel reconfigurable architecture. In this design, we come up with FR specific programmable cores termed Scalable Unit for Region Evaluation (SURE) capable of performing modular computations in the hybrid face recognition algorithm. We replicate SUREs in each tile of REDEFINE to construct a face recognition module termed REDEFINE for Face Recognition using SURE Homogeneous Cores (REFRESH). There is a need to learn new unseen faces on-line in practical face recognition systems. Considering this, for real-time on-line learning of unseen face images, we design tiny processors termed VOP, Processor for Vector Operations. VOPs function as coprocessors to process elements under each tile of REDEFINE to accelerate micro vector operations appearing in the synaptic weight computations. We also explore deep neural networks which operate similar to the processing in human brain and capable of working on very large face databases. We explore the field of Random matrix theory to come up with a solution for synaptic weight initialization in deep neural networks for better classification . In addition, we perform design space exploration of hardware architecture for deep convolution networks and conclude with directions for future work.

Disertační práce se věnuje využití umělých neuronových sítí pro modelování elektromagnetických polí uvnitř automobilů. První část práce je zaměřena na analytický popis šíření elektromagnetických vlny interiérem pomocí Nortonovy povrchové vlny. Následující část práce se věnuje praktickému měření a ověření analytických modelů. Praktická měření byla zdrojem trénovacích a verifikačních dat pro neuronové sítě. Práce se zaměřuje na kmitočtová pásma 3 až 11 GHz a 55 až 65 GHz.

This master's thesis deals with the use of text classification for sorting of incoming emails. First, there is described the Knowledge Discovery in Databases and there is also analyzed in detail the text classification with selected methods. Further, this thesis describes the email communication and SMTP, POP3 and IMAP protocols. The next part contains design of the system that classifies incoming emails and there are also described realated technologie ie Apache James Server, PostgreSQL and RapidMiner. Further, there is described the implementation of all necessary components. The last part contains an experiments with email server using Enron Dataset.