Ograniczanie wyników
Czasopisma help
Autorzy help
Lata help
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 545

Liczba wyników na stronie
first rewind previous Strona / 28 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  algorytm genetyczny
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 28 next fast forward last
1
Content available remote Metameric representations on optimization of nano particle cancer treatment
EN
In silico evolutionary optimization of cancer treatment based on multiple nano-particle (NP) assisted drug delivery systems was investigated in this study. The use of multiple types of NPs is expected to increase the robustness of the treatment, due to imposing higher complexity on the solution tackling a problem of high complexity, namely the physiology of a tumor. Thus, the utilization of metameric representations in the evolutionary optimization method was examined, along with suitable crossover and mutation operators. An opensource physics-based simulator was utilized, namely PhysiCell, after appropriate modifications, to test the fitness of possible treatments with multiple types of NPs. The possible treatments could be comprised of up to ten types of NPs, simultaneously injected in an area close to the cancerous tumour. Initial results seem to suffer from bloat, namely the best solutions discovered are converging towards the maximum amount of different types of NPs, however, without providing a significant return in fitness when compared with solutions of fewer types of NPs. As the large diversity of NPs will most probably prove to be quite toxic in lab experiments, we opted for methods to reduce the bloat, thus, resolve to therapies with fewer types of NPs. Namely, the bloat control methods studied here were removing types of NPs from the optimization genome as part of the mutation operator and applying parsimony pressure in the replacement operator. By utilizing these techniques, the treatments discovered are composed of fewer types of NPs, while their fitness is not significantly smaller.
EN
Manual interpretation of heart sounds is insensitive and prone to subjectivity. Automated diagnosis systems incorporating artificial intelligence and advanced signal processing tools can potentially increase the sensitivity of disease detection and reduce the subjectiveness. This study proposes a novel method for the automated binary classification of heart sound signals using the Fano-factor constrained tunable quality wavelet transform (TQWT) technique. Optimal TQWT based decomposition can reveal significant information in subbands for the reconstruction of events of interest. While transforming heart sound signals using TQWT, the Fano-factor is applied as a thresholding parameter to select the subbands for the clinically relevant reconstruction of signals. TQWT parameters and threshold of the Fanofactor are tuned using a genetic algorithm (GA) to adapt to the underlying optimal detection performance. The time and frequency domain features are extracted from the reconstructed signals. Overall 15 unique features are extracted from each sub-frame resulting in a total feature set of 315 features for each epoch. The resultant features are fed to Light Gradient Boosting Machine model to perform binary classification of the heart sound recordings. The proposed framework is validated using a ten-fold cross-validation scheme and attained sensitivity of 89.30%, specificity of 91.20%, and overall score of 90.25%. Further, synthetic minority over-sampling technique (SMOTE) is applied to produce balanced data set which yielded sensitivity and specificity of 86.32% and 99.44% respectively and overall score of 92.88%. Our developed model can be used in digital stethoscopes to automatically detect abnormal heart sounds and aid the clinicians in their diagnosis.
EN
Medical robots with an instant center of rotation mechanism in a trocar are used for operating a human body or servicing artificial organs. The result of the work is the development of a multi-criteria optimization model of a discussed medical robot, considering safety factor, first eigenfrequency and buckling coefficient as a criteria. The article also analyzes two issues of mechanics, the natural frequency and linear buckling. A discrete mesh model of a novel robot design with ten degrees of freedom and ended with a scalpel was developed based on finite element method. For the given loads and supports, a multi-criteria optimization model was evolved, which was solved by using the response surface method and the multi-objective genetic algorithm. The results section shows the Pareto fronts for the criteria and geometrical dimensions of the kinematic chain. The courses of resonant vibrations and buckling strains were also characterized. The solved optimization model gives correct values for the adopted criteria. The values of resonance were defined, which makes it possible to select mechatronic drive systems in terms of the input they generate. Variability of the resonant vibrations phenomena, as well as shapes and directions of buckling, provide information about the displacements taking place in the medical robot system.
PL
W artykule przedstawiono podstawowe właściwości i badania laboratoryjne wysokoczęstotliwościowego falownika klasy EF (20 MHz, 400 W, 91,2%) z ćwierćfalową linią długą dołączoną po stronie zasilania. Falownik ten zawiera jeden tranzystor, przebieg napięcie tranzystora zbliżony jest do prostokątnego oraz występuje przełączanie miękkie tranzystora typowe dla klasy E. Zastosowany tranzystor MOSFET serii DE sterowany jest za pomocą dedykowanego, niskostratnego sterownika bramkowego własnej konstrukcji. Wyjaśniono metodę optymalizacji parametrów falownika klasy EF ze względu na sprawność, którą zrealizowano z wykorzystaniem oprogramowania ANSYS Simplorer i wbudowanego algorytmu genetycznego. Koncepcja falownika klasy EF została pozytywnie zweryfikowana laboratoryjnie. Zarejestrowano przykładowe przebiegi czasowe napięć tranzystora oraz wyznaczono wybrane parametry falownika.
EN
Some basic properties and laboratory tests of high-frequency Class EF inverter (20 MHz, 400 W, 91.2%) with quarter-wave transmission line on the supply side are presented in the article. The inverter contains one transistor, the transistor voltage waveform is close to a rectangular one and the soft-switching of the transistor is realized as typically in Class E. The applied DE-series MOSFET transistor was controlled by a dedicated, low-loss driver of its own design. The optimization method of the Class EF inverter parameters to maximize efficiency was explained. It was implemented using ANSYS Simplorer software and a built-in genetic algorithm. The concept of the Class EF inverter was positively verified in the laboratory. Examples of transistor voltage waveforms were recorded and selected inverter parameters were determined.
EN
The use of wind energy in water pumping is an economically viable and sustainable solution to rural communities without access to the electricity grid. The aim of this paper is to present a detailed modeling of the wind-powered pumping system, propose and compare some control schemes to optimize the performance of the system and enhance the quality of the generated power. The wind energy system used in this paper consists of a permanent magnet synchronous generator (PMSG) and static converters directly coupled to an asynchronous motor that drives a centrifugal pump. A typical control is applied to the proposed configuration for the purpose of controlling the generator to extract maximum wind power. Furthermore, four types of controllers (PI and conventional RST polynomials, adaptive RST-fuzzy and genetic algorithm are designed for the wind energy system and tested under various operating conditions.
PL
Wykorzystanie energii wiatru w pompowaniu wody jest opłacalnym i zrównoważonym rozwiązaniem dla społeczności wiejskich bez dostępu do sieci elektrycznej. Celem tego artykułu jest przedstawienie szczegółowego modelowania systemu pompowania napędzanego wiatrem, zaproponowanie i porównanie niektórych schematów sterowania, aby zoptymalizować wydajność systemu i poprawić jakość generowanej mocy. System energii wiatrowej zastosowany w tym artykule składa się z synchronicznego generatora z magnesami trwałymi (PMSG) i przekształtników statycznych bezpośrednio sprzężonych z silnikiem asynchronicznym, który napędza pompę odśrodkową. Typowe sterowanie jest stosowane do proponowanej konfiguracji w celu sterowania generatorem w celu wydobycia maksymalnej energii wiatru. Ponadto cztery typy sterowników (PI i konwencjonalne wielomiany RST, adaptacyjny algorytm rozmytego RST i genetyczny) są zaprojektowane dla systemu energii wiatrowej i testowane w różnych warunkach pracy).
EN
In this paper, the Non-dominated Sorting Genetic Algorithm NSGA-II, accompanied by the Newton Raphson method for power flow calculation, has been applied to an IEEE 33 bus test network to plan locations of photovoltaic power plants and Battery Energy Storage Systems. In addition to the minimization of costs, total losses and the maintain of voltage within acceptable limits (minimize voltage drops), the determination of these optimal locations will make it possible to converge towards a decentralized network with optimized, local energy and close to the consumer.
PL
Przedstawiono wykorzystanie algorytmów genetycznych wspomaganych przez metodę Newton-Raphson do obliczania przepływów mocy. Analizowano szynę zgodną z IEEE 33 w planowanej sieci ze źródłami fotowoltaicznymi i bateryjnym zasobnikiem energii.
EN
This paper discusses optimal allocation planning of synchronous distributed generation (SDG) on mesh grid power system, using breeder genetic algorithm (BGA) method. This optimization technique was built to allocate SDG units for obtaining the smallest power losses, while all buses voltage awakens in standard value. Furthermore, the proposed method was tested on IEEE 30 bus test system, and the optimal solution was reached for three SDG unit installation on 27.73 MW + j1.502 MVAr total power, with 22.46% power losses reduction.
PL
W artykule omówiono optymalne planowanie alokacji synchronicznej generacji rozproszonej (SDG) w systemie elektroenergetycznym sieci kratowej z wykorzystaniem metody algorytmu genetycznego rozpłodnika (BGA). Ta technika optymalizacji została zbudowana w celu alokacji jednostek SDG dla uzyskania najmniejszych strat mocy, podczas gdy napięcie wszystkich magistrali zawiera się w wartości standardowej. Ponadto zaproponowana metoda została przetestowana na systemie testowym magistrali IEEE 30 i osiągnięto optymalne rozwiązanie dla instalacji trzech jednostek SDG o łącznej mocy 27,73 MW + j 1,502 MVAr, przy obniżeniu strat mocy o 22,46%.
EN
This paper proposes a novel hybrid software/hardware system to automatically create filters for image processing based on genetic algorithms and mathematical morphology. Experimental results show that the hybrid system, implemented using a combination of a NIOS-II processor and a custom hardware accelerator in an Altera FPGA device, is able to generate solutions that are equivalent to the software version in terms of quality in approximately one third of the time.
PL
W artykule zaproponowano nowe hybrydowe oprogramowanie do automatycznego tworzenia filtrów grafiki bazuj ˛acych na algorytmach genetycznych i morfologii matematycznej. Eksperymenty wykazały ˙ze proponowany system wykorzystuj ˛acy procesor NIOS-II i Altera FPGA jest w stanie generowa´c rozwi ˛azanie niemal trzy razy szybciej ni˙z dotychczas stosowane systemy.
EN
The purpose of this study is to optimize the location and capacity of PV in the feeder distribution system 20 kV of Central Sulawesi, Indonesia. The proposed method uses the optimization method of development from the genetic algorithm, namely NSGA-II. Optimization is carried out in three scenarios by considering the value of the total active PV power capacity which produces the minimum active power loss and voltage deviation. The simulation result shows that the integration of PV-DG can improve drop voltage of distribution system performance due to load growth effect.
PL
Celem tego badania jest optymalizacja lokalizacji i wydajności PV w systemie dystrybucji zasilania 20 kV w środkowym Sulawesi w Indonezji. Proponowana metoda wykorzystuje optymalizację opartą na algorytmie genetycznym, mianowicie NSGA-II. Optymalizację przeprowadza się w trzech scenariuszach, biorąc pod uwagę wartość całkowitej mocy czynnej PV, która powoduje minimalne straty mocy czynnej i odchylenie napięcia. Wynik symulacji pokazuje, że integracja PV-DG może poprawić wydajność systemu dystrybucji ze względu na efekt wzrostu obciążenia.
PL
W pracy dokonano przeglądu struktur regulatorów PID2DOF, przedstawiono wyniki symulacyjnego procesu optymalizacji nastaw tych regulatorów dla modelu napędu bezpośredniego z silnikiem PMSM z uwzględnieniem tętnień momentu. Przeprowadzono dwie serie optymalizacji nastaw analizowanych struktur za pomocą algorytmu genetycznego: pierwszą pod kątem tłumienia nierównomierności prędkości napędu bezpośredniego wywołanych tętnieniami momentu; drugą – referencyjną – pod kątem minimalizacji kwadratu uchybu z pominięciem modelu tętnień.
EN
This paper reviews structures of the PID2DOF controllers and presents results of a simulation process of optimizing the settings of these controllers for a PMSM direct drive model including torque ripple. Two series of optimization of the settings of these structures with the use of genetic algorithm were executed: first one in terms of minimization of speed unevenness caused by torque ripples, second – referential – in terms of ISE minimization.
11
EN
In this paper the results of the development of voltage and reactive power regulation algorithm based on the particle swarm method, optimizing the electric power system mode by the level of losses, are presented. To provide an integration of this algorithm into a real system of an automated dispatching control system, the algorithm is implemented using programs, which are used in the System Operator of the Unified Power System of Russia, as well as standard communication protocols and a software platform. The analysis and comparison of the optimization results obtained by the particle swarm method and standard optimization method (gradient descent method), realized in RastrWin, confirm the correctness and reliability of the obtained results and the developed algorithm. At the same time, the algorithm does not depend on the initial conditions (setpoints), set on the control objects, which allows it to be used to optimize the modes of complex power network, finding the balance in which is a time-consuming task. In the future, it is planned to develop an algorithm for optimizing the mode, taking into account the increased stability of the electric power system.
PL
W artykule przedstawiono metodę sterowania napięciem I moca bierną bazującą na algorytmach rojowych. Algorytm zaadaptowano do rzeczywistych warunków sieci dystrybucyjnej w Rosji. Sprawdzono praće algorytmu badając stabilność I niezawodność systemu. W dalszym etapie planuje się zastosowanie metody do optymalizacji sieci zasilania.
EN
Background: Under conditions of digital transformation, the effective decision-making process should involve the usage of different mathematical models and methods, one of which is the transportation problem. The transportation problem, as the problem of resource allocation, is applicable in such domains as manufacturing, information technologies, etc. To get more precise solutions, the multi-index transportation problem can be applied, which allows taking into account several variables. Methods: This paper develops an approach for applying the genetic algorithm for solving four-index transportation problems. Results: The steps of the genetic algorithm for solving four-index transportation problems are outlined. The research has proved the steps of the genetic algorithm to be the same for all four-index transportation problem types, except for the first step (initialization), which is described for every type of transportation problem separately. Based on the theoretical results, the program implementation of the genetic algorithm for solving four-index symmetric transportation problems has been developed with the open-source programming language typescript. Conclusions: The paper promotes the application of the genetic algorithm for solving multi-index transportation problems. The investigated problem requires comprehensive studies, specifically, on the influence of change different parameters of the genetic algorithm (population size, the mutation, and crossover rates, etc.) on the efficiency of the algorithm in solving four-index transportation problems.
PL
Wstęp: W warunkach komputerowej transformacji, efektywny proces podejmowania decyzji powinien obejmować wykorzystania modeli metod matematycznych. Przykładem takiej sytuacji jest problem transportowy, który jest problemem alokacji zasobów, występujący w takich obszarach jak produkcji, technologie informatyczne, itp. W celu uzyskania precyzyjniejszych rozwiązań, można zastosować wieloczynnikowy problem transportowy, który umożliwia uwzględnienie wielu zmiennych. Metody: W pracy zastosowano algorytm genetyczny dla rozwiązania czteroczynnikowych problemów transportowych. Wyniki: Wyszczególniono kroki algorytmu genetycznego dla czteroczynnikowego problem transportowego. Udowodnione, że kroki algorytmu genetycznego są takie same dla wszystkich typów czteroczynnikowych problemów transportowych, z wyjątkiem pierwszego kroku (inicjalizacji), który został opisany osobno dla każdego z typów problemu transportowego. W oparciu o wyniki teoretyczne, utworzono programowanie dla algorytmu genetycznego dla rozwiązywania czteroczynnikowych problemów transportowych przy użyciu opensourcowego języka typescript. Wnioski: W pracy zaproponowano zastosowanie algorytmu genetycznego dla rozwiązywania wieloczynnikowych problemów transportowych. Analizowany problem wymaga dalszych badań, szczególnie w zakresie wpływu zmian poszczególnych parametrów algorytmu genetycznego (wielkości populacji, mutacji, współczynnika podziału, itp.) na efektywność algorytmu w rozwiązywaniu czteroczynnikowych problemów transportowych.
EN
Permanent magnet brushless DC motors (PMBLDC) find broad applications in industries due to their huge power density, efficiency, low maintenance, low cost, quiet operation, compact form and ease of control. The motor needs suitable speed controllers to conduct the required level of interpretation. As with PI controller, PID controller, fuzzy logic, genetic algorithms, neural networks, PWM control, and sensorless control, there are several methods for managing the BLDC motor. Generally, speed control is provided by a proportional-integral (PI) controller if permanent magnet motors are involved. Although standard PI controllers are extensively used in industry owing totheir simple control structure and execution, these controller shave a few control complexities such as nonlinearity, load disruption, and parametric variations. Besides, PI controllers need more precise linear mathematical models. This statement reflects the use of Classic Controller and Genetic Algorithm Based PI, PID Controller with the BLDC motor drive. The technique is used to regulate velocity, direct the BLDC motor drive system’s improved dynamic behavior, resolve the immune load problem and handle changes in parameters. Classical control & GA-based control provides qualitative velocity reaction enhancement. This article focuses on exploring and estimating the efficiency of a continuous brushless DC motor (PMBLDC) drive, regulated as a current controller by various combinations of Classical Controllers such as PI, GA-based PI, PID Controller. The controllers are simulated using MATLAB software for the BLDC motor drive.
EN
In the present work, the optimal balancing of the planar six-bar mechanism is investigated to minimize the fluctuations of shaking force and shaking moment. An optimization problem is formulated for balancing the planar six-bar mechanism by developing an objective function. The genetic algorithm and MINITAB software were used to solve the optimization problem. The selection of weighting factors has a crucial role to obtain the optimum values of design parameters. Two sets of weighting factors were considered as per the contribution of X and Y components of the shaking force and shaking moments. Shaking force and shaking moments were minimized drastically and were compared with the original values.
EN
A lot of uncertainties and complexities exist in real life problem. Unfortunately, the world approaches such intricate realistic life problems using traditional methods which has failed to offer robust solutions. In recent times, researchers look beyond classical techniques. There is a model shift from the use of classical techniques to the use of standardized intelligent biological systems or evolutionary biology. Genetic Algorithm (GA) has been recognized as a prospective technique capable of handling uncertainties and providing optimized solutions in diverse area, especially in homes, offices, stores and industrial operations. This research is focused on the appraisal of GA and its application in real life problem. The scenario considered is the application of GA in 0-1 knapsack problem. From the solution of the GA model, it was observed that there is no combination that would give the exact weight or capacity the 35 kg bag can carry but the possible range from the solution model is 34 kg and 36 kg. Since the weight of the bag is 35 kg, the feasible or near optimal solution weight of items the bag can carry would be 34 kg at benefit of 16. Additional load beyond 34 kg could lead to warping of the bag.
EN
A scheduling problem in considered on unrelated machines with the goal of total late work minimization, in which the late work of a job means the late units executed after its due date. Due to the NP-hardness of the problem, we propose two meta-heuristic algorithms to solve it, namely, a tabu search (TS) and a genetic algorithm (GA), both of which are equipped with the techniques of initialization, iteration, as well as termination. The performances of the designed algorithms are verified through computational experiments, where we show that the GA can produce better solutions but with a higher time consumption. Moreover, we also analyze the influence of problem parameters on the performances of these metaheuristics.
EN
Given an undirected connected graph G = (V, E), a subset of vertices S is a maximum 2-packing set if the number of edges in the shortest path between any pair of vertices in S is at least 3 and S has the maximum cardinality. In this paper, we present a genetic algorithm for the maximum 2-packing set problem on arbitrary graphs, which is an NP-hard problem. To the best of our knowledge, this work is a pioneering effort to tackle this problem for arbitrary graphs. For comparison, we extended and outperformed a well-known genetic algorithm originally designed for the maximum independent set problem. We also compared our genetic algorithm with a polynomial-time one for the maximum 2-packing set problem on cactus graphs. Empirical results show that our genetic algorithm is capable of finding 2-packing sets with a cardinality relatively close (or equal) to that of the maximum 2-packing sets. Moreover, the cardinality of the 2-packing sets found by our genetic algorithm increases linearly with the number of vertices and with a larger population and a larger number of generations. Furthermore, we provide a theoretical proof demonstrating that our genetic algorithm increases the fitness for each candidate solution when certain conditions are met.
EN
The most common type of liver cancer is hepatocellular carcinoma (HCC), which begins in hepatocytes. The HCC, like most types of cancer, does not show symptoms in the early stages and hence it is difficult to detect at this stage. The symptoms begin to appear in the advanced stages of the disease due to the unlimited growth of cancer cells. So, early detection can help to get timely treatment and reduce the mortality rate. In this paper, we proposes a novel machine learning model using seven classifiers such as K-nearest neighbor (KNN), random forest, Naïve Bayes, and other four classifiers combined to form stacking learning (ensemble) method with genetic optimization helping to select the features for each classifier to obtain highest HCC detection accuracy. In addition to preparing the data and make it suitable for further processing, we performed the normalization techniques. We have used KNN algorithm to fill in the missing values. We trained and evaluated our developed algorithm using 165 HCC patients collected from Coimbra's Hospital and University Centre (CHUC) using stratified cross-validation techniques. There are total of 49 clinically significant features in this dataset, which are divided into two groups such as quantitative and qualitative groups. Our proposed algorithm has achieved the highest accuracy and F1-score of 0.9030 and 0.8857, respectively. The developed model is ready to be tested with huge database and can be employed in cancer screening laboratories to aid the clinicians to make an accurate diagnosis.
EN
Currently, air pollution and energy consumption are the main issues in the transportation area in large urban cities. In these cities, most people choose their transportation mode according to corresponding utility including traveller's and trip’s characteristics. Also, there is no effective solution in terms of population growth, urban space, and transportation demands, so it is essential to optimize systematically travel demands in the real network of roads in urban areas, especially in congested areas. Travel Demand Management (TDM) is one of the well-known ways to solve these problems. TDM defined as a strategy that aims to maximize the efficiency of the urban transport system by granting certain privileges for public transportation modes, Enforcement on the private car traffic prohibition in specific places or times, increase in the cost of using certain facilities like parking in congested areas. Network pricing is one of the most effective methods of managing transportation demands for reducing traffic and controlling air pollution especially in the crowded parts of downtown. A little paper may exist that optimize urban transportations in busy parts of cities with combined Markov decision making processes with reward and evolutionary-based algorithms and simultaneously considering customers’ and trip’s characteristics. Therefore, we present a new network traffic management for urban cities that optimizes a multi-objective function that related to the expected value of the Markov decision system’s reward using the Genetic Algorithm. The planned Shiraz city is taken as a benchmark for evaluating the performance of the proposed approach. At first, an analysis is also performed on the impact of the toll levels on the variation of the user and operator cost components, respectively. After choosing suitable values for the network parameters, simulation of the Markov decision process and GA is dynamically performed, then the optimal decision for the Markov decision process in terms of total reward is obtained. The results illustrate that the proposed cordon pricing has significant improvement in performance for all seasons including spring, autumn, and winter.
PL
W artykule przedstawiono nowe narzędzie optymalizacyjne wspierające zarządzanie łańcuchem dostaw w aspekcie wielokryterialnym. To narzędzie zostało wdrożone w systemie EPLOS (Europejski Portal Usług Logistycznych). System EPLOS to zintegrowany system informatyczny wspierający proces tworzenia sieci dostaw i dystrybucji w łańcuchach dostaw. Ten system składa się z wielu modułów, np. moduł optymalizacji odpowiedzialny za przetwarzanie danych, generowanie wyników, moduł danych wejściowych, moduł kalibracji parametrów algorytmu optymalizacyjnego. Głównym celem badań było opracowanie systemu do określania parametrów łańcucha dostaw, które wpływają na jego efektywność w procesie zarządzania przepływem towarów między poszczególnymi ogniwami łańcucha. Parametry te zostały uwzględnione w modelu matematycznym jako zmienne decyzyjne w celu ustalenia ich w procesie optymalizacji. W modelu matematycznym zdefiniowano dane wejściowe adekwatne do analizowanego problemu, przedstawiono główne ograniczenia związane z wyznaczaniem efektywnego sposobu zarządzania łańcuchem dostaw oraz opisano funkcje kryterium. Problem zarządzania przepływem towarów w łańcuchu dostaw został przedstawiony w ujęciu wielokryterialnym. Ocenę efektywności zarządzania łańcuchem dostaw przeprowadzono na podstawie globalnej funkcji kryterium składającej się z częściowych funkcji kryteriów opisanych w modelu matematycznym. Główne funkcje kryteriów na podstawie których wyznaczane jest końcowe rozwiązane to współczynnik wykorzystania wewnętrznych środków transportu, współczynnik wykorzystania zewnętrznych środków transportu, koszty pracy środków transportu wewnętrznego i personelu, całkowity koszt realizacji zadań transportowych, współczynnik wykorzystania czasu zaangażowania pojazdów, całkowity czas poświęcony na wykonanie zadań, czy liczba pojazdów. Punktem wyjścia do badania było założenie, że o skuteczności zarządzania łańcuchem decydują dwa problemy decyzyjne ważne dla menedżerów w procesie zarządzania łańcuchem dostaw, tj. problem przydziału pojazdów do zadań i problem lokalizacji obiektów logistycznych w łańcuchu dostaw. Aby rozwiązać badany problem, zaproponowano innowacyjne podejście w postaci opracowania algorytmu genetycznego, który został dostosowane do przedstawionego modelu matematycznego. W pracy szczegółowo opisano poszczególne kroki konstruowania algorytmu. Zaproponowana struktura przetwarzana przez algorytm jest strukturą macierzową, dzięki której wyznaczane są optymalne parametry łańcucha dostaw. Procesy krzyżowania i mutacji zostały opracowane adekwatnie do przyjętej struktury macierzowej. W procesie kalibracji algorytmu wyznaczono takie wartości parametrów algorytmu tj. prawdopodobieństwo krzyżowania czy mutacji, które generują optymalne rozwiązanie. Poprawność algorytmu genetycznego oraz efektywność zaproponowanego narzędzia wspomagającego proces zarządzania łańcuchem dostaw została potwierdzona w procesie jego weryfikacji.
EN
The article presents a new optimization tool supporting supply chain management in the multi-criteria aspect. This tool was implemented in the EPLOS system (European Logistics Services Portal system). The EPLOS system is an integrated IT system supporting the process of creating a supply and distribution network in supply chains. This system consists of many modules e.g. optimization module which are responsible for data processing, generating results. The main objective of the research was to develop a system to determine the parameters of the supply chain, which affect its efficiency in the process of managing the goods flow between individual links in the chain. These parameters were taken into account in the mathematical model as decision variables in order to determine them in the optimization process. The assessment of supply chain management effectiveness was carried out on the basis of the global function of the criterion consisting of partial functions of the criteria described in the mathematical model. The starting point for the study was the assumption that the effectiveness of chain management is determined by two important decision-making problems that are important for managers in the supply chain management process, i.e. the problem of assigning vehicles to tasks and the problem of locating logistics facilities in the supply chain. In order to solve the problem, an innovative approach to the genetic algorithm was proposed, which was adapted to the developed mathematical model. The correctness of the genetic algorithm has been confirmed in the process of its verification.
first rewind previous Strona / 28 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.