This paper proposes a novel hybrid control of induction motor, based on the combination of the direct torque control DTC and the backstepping one, optimized by Genetic Algorithm (GA). First the basic ...evolution of DTC is explained, where the torque and stator flux are controlled by non linear hysteresis controllers which cause large ripple in motor torque at steady state operation. A Backstepping control is applied to overcome these problems, however the used parameters are often chosen arbitrarily, which may affect the controller quality. To find the best parameters, an optimization technique based on genetic algorithm is used. Also, in order to obtain accurate information about stator flux, torque and load torque, open loops estimators are used for this Backstepping control. At last, experimental results are presented in order to prove the efficiency of the above mentioned control technique.
Choosing and implementing a Maximum Power Point Tracking (MPPT) algorithm in a photovoltaic (PV) system, along with choosing the power converter, constitutes the fundamental basic capabilities of a ...photovoltaic system. MPPT techniques are implemented in photovoltaic systems to achieve full utilization of PV array output power. Today there is a wide variety of MPPT algorithms, each one has its advantages and disadvantages. This paper presents theoretical, as well as experimental comparison results, in several aspects regarding four MPPT methods based on the basic two MPPT algorithms (Perturb and Observe, Incremental Conductance), implemented on a single DC/DC converter, under the same experimental conditions. The theoretical and experimental comparison is performed for characteristics of ripple around the MPP and the convergence time. The experimental results are provided and supported by theoretical analysis and show that gradient based methods have better convergence time as well as ripple values in comparison to fixed step methods.
Evolutionary computation has been widely used in computer science for decades. Even though it started as far back as the 1960s with simulated evolution, the subject is still evolving. During this ...time, new metaheuristic optimization approaches, like evolutionary algorithms, genetic algorithms, swarm intelligence, etc., were being developed and new fields of usage in artificial intelligence, machine learning, combinatorial and numerical optimization, etc., were being explored. However, even with so much work done, novel research into new techniques and new areas of usage is far from over. This book presents some new theoretical as well as practical aspects of evolutionary computation. This book will be of great value to undergraduates, graduate students, researchers in computer science, and anyone else with an interest in learning about the latest developments in evolutionary computation.
Problemi s upravljanjem mnogih procesa u industriji vezani su s nemogućnošću on-line mjerenja nekih važnih procesnih veličina. Ovaj se problem može u značajnoj mjeri riješiti estimacijom ovih ...teško-mjerljivih procesnih veličina. Estimator je pri tome odgovarajući matematički model procesa koji na temelju informacije o ostalim (lako-mjerljivim) procesnim veličinama procjenjuje trenutni iznos teško-mjerljive veličine. Budući da su procesi po prirodi promjenjivi, točnost estimacije zasnovane na modelu procesa izgra.enog na starim podacima u pravilu opada s vremenom. Kako bi se ovo izbjeglo, parametre modela procesa je potrebno kontinuirano prepodešavati kako bi model što bolje opisivao (trenutno) vladanje procesa. Ovisno o tipu matematičkog modela, za prepodešavanje njegovih parametara na raspolaganju je više metoda. Kao osnova estimatora teško-mjerljive veličine u radu se koristi PLSR model procesa, dok se njegovi parametri prepodešavaju na više načina – metodom pomičnog prozora, rekurzivnim NIPALS algoritmom, rekurzivnim kernel algoritmom te Just-in-Time Learning metodom. Svojstva navedenih metoda adaptacije PLSR modela procesa ispitana su na odabranom primjeru. Nadalje, metode adaptacije su analizirane i s obzirom na računalnu i memorijsku zahtjevnost.
I progetti di costruzione devono soddisfare requisiti in termini di tempi, costi e qualità e il Project Management è fondamentalmente concentrato su questo compromesso. In ogni progetto questi tre ...parametri sono interdipendenti: non si può modificare un elemento senza influenzare almeno uno degli altri due. Questo lavoro presenta l’uso di una tecnica di intelligenza artificiale per la pianificazione delle attività di un progetto infrastrutturale, in vista di una ottimizzazione multi obbiettivo in termini di tempi-costi-qualità. L’approccio si basa sull’utilizzo di algoritmi genetici, implementati in Matlab, per valutare set di combinazioni di opzioni per le attività di costruzione. Lo scopo è quello di fornire una tecnica efficace per esplorare adeguatamente tutte le possibili configurazioni progettuali.
U radu je opisana optimizacija skalarnih matematičkih funkcija i multikriterijska optimizacija putanje četveropolužnog mehanizma zasnovana na genetičkim algoritmima. Genetičkim se algoritmom ...optimiziraju parametri Hoekenovog četveropolužnog mehanizma koji na jednom dijelu putanje aproksimira pravocrtno gibanje. Problem optimizacije parametara četvoropolužnog mehanizma promatra se kao dvokriterijski jer je potrebno zadovoljiti položaj krajnje točke mehanizma po x-osi i po y-osi. Algoritam realiziran u JavaScript programskom jeziku optimizira parametre Hoekenovog mehanizma koji su sintetizirani u programskom alatu SAM 6.0.
HIV/AIDS surveillance data indicate that, in 2008, approximately one-fourth of all HIV infections in adults remain undiagnosed in Italy and that close to 60% of Aids diagnosed individuals discovered ...their seropositivity at the diagnosis of AIDS. Late diagnosis of HIV infection is associated with increased mortality and morbidity and increased cost to healthcare services. From a public health perspective, knowledge of HIV status is associated with a reduction in risk behaviour. Thus, a routine screening for HIV infection is important for both a better prognostic outcome, and control of HIV spreading in the population. In Italy there are not shared guidelines for the laboratory diagnosis. In this paper, we suggest two algorithms that can be adopted for the diagnosis of HIV infection in individuals undergoing HIV testing.
U radu je predstavljen istraživačko-razvojni projekt (engl. Industrial Research and Innovation - IRI) novog sustava zaštite, mjerenja i upravljanja za primjenu u elektroenergetskom sustavu (EES). ...Sustav zaštite, mjerenja i upravljanja koristi nove funkcionalnosti - kako zaštitne tako i komunikacijske, poboljšale su se i objedinile postojeće funkcionalnosti, te znatno proširilo područje primjene. Projekt je dio cjelokupnog razvoja nove platforme naprednih mikroprocesorskih ugradbenih sustava (engl. Embedded Systems) za regulaciju, zaštitu i upravljanje u EES-u. Nova platforma temelji se na distribuiranim modularnim funkcijama (hardverskim i softverskim) koje se komunikacijski povezuju u cjeloviti napredni sustav. Tehničko-ekonomska opravdanost projekta povećava se jer se na istoj platformi, kao izvedenice, kasnije mogu realizirati i drugi slični uređaji za regulaciju i upravljanje procesima u elektroenergetici.
There exist many problems regarding process control in the process industry since some of the important variables cannot be measured online. This problem can be significantly solved by estimating ...these difficult-to-measure process variables. In doing so, the estimator is in fact an appropriate mathematical model of the process which, based on information about easy-to-measure process variables, estimates the current value of the difficult- to-measure variable. Since processes are usually time-varying, the precision of the estimation based on the process model which is built on old data is decreasing over time. To avoid estimator accuracy degradation, model parameters should be continuously updated in order to track process behavior. There are a couple of methods available for updating model parameters depending on the type of process model. In this paper, PLSR process model is chosen as the basis of the difficult-to-measure process variable estimator while its parameters are updated in several ways-by the moving window method, recursive NIPALS algorithm, recursive kernel algorithm and Just-in-Time learning algorithm. Properties of these adaptive methods are explored on a simulated example. Additionally, the methods are analyzed in terms of computational load and memory requirements.