Wyniki wyszukiwania - BazTech

1

Evolution of δ phase precipitates in Inconel 625 superalloy additively manufactured by laser powder bed fusion and its modeling with fuzzy logic

Staroń Sylwia, Macioł Piotr, Dubiel Beata, Gola Kewin, Falkus Jan

Archives of Civil and Mechanical Engineering

|

2023

|

Vol. 23, no. 2

art. no. e86, 2023

EN

Experimental and modeling studies of the evolution of plate-like δ phase precipitates in Inconel 625 superalloy additively manufactured by the laser powder bed fusion process are performed. The maximum Feret diameter and the number of particles per unit area are used as parameters describing the size and distribution of the δ phase precipitates. On the basis of microstructural analysis and quantitative image analysis, the effect of time and temperature on the development of δ phase precipitates is determined. The distinct differences in the intensity of precipitation, growth, and coarsening of the δ phase precipitates during annealing at temperatures of 700 and 800 °C up to 2000 h are shown. The experimental results are compared with computational data obtained by thermodynamic modeling. Using the experimentally determined parameters of the δ phase precipitates in different variants of annealing, a fuzzy logic-based phase distribution model is designed. Since the quantity of available data was too small to train a model with the machine learning approach, expert knowledge is used to design the rules, while numerical data are used for its validation. Designed rules, as well as reasoning methodology are described. The proposed model is validated by comparing it with the experimental results. It can be used to predict the size and number density of the δ phase precipitates in the additively manufactured Inconel 625, subjected to long-term annealing at temperatures of 700-800 °C. Due to limited experimental data, the quality of assurance is not perfect, but warrants preliminary research.

2

Free running ship model tests of interaction between a moored ship and a passing ship

Raszeja Magdalena, Hejmlich Andrzej, Nowicki Jacek, Jaworski Tomasz

Zeszyty Naukowe Akademii Morskiej w Szczecinie

|

2022

|

nr 72 (144)

50--56

EN

For many reasons, ship model interaction tests are performed in experimental towing tanks. This paper presents research on the hydrodynamic forces acting on a ship tied up at the solid berth, which is produced by other ships passing by using free-running ship models with much larger dimensions than those used in towing tanks. A passing ship model was controlled by a human operator – an experienced master. This enabled a study of the influence of the interaction impact on the course of the maneuver. The research was carried out at the Ship Handling Research and Training Centre in Iława. The ship model was moored alongside and equipped with multi-directional force sensors linking the ship model with a solid berth. Forces were measured as a function of the passing ship speed, side distance between both ships, ship sizes, and depth-to-draft ratio (H/T). Forces were measured in two planes: the longitudinal (surge) and the transversal (sway). A numerical database was processed and ordered according to the variables. The fuzzy model was created within a “Matlab” computing environment using a Sugeno-type self-learning neuron network model. The proposed Sugeno model was evaluated with other methods presented by Flory (2002), Seelig (2001), and PASS-MOOR by Wang (1975). The ultimate goal of this study was to simplify the method of predictive calculations for adjusting speed and distance when passing by the moored ship, which ensures compliance with safe port mooring requirements.

3

Fuzzy comprehensive model of manufacturing industry transfer risk based on economic big data analysis

Sun Tong, Liu Chunzhi

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2022

|

Vol. 70, nr 2

art. no. e139959

EN

Aiming at the problems of low accuracy, low efficiency and low stability of traditional methods and recent developments in advanced technology incite the industries to be in sync with modern technology. With respect to various available techniques, this paper designs a fuzzy comprehensive evaluation model of the manufacturing industry for transferring risk based on economic big-data analytics. The big-data analysis method is utilized to obtain the data source of fuzzy evaluation of the manufacturing industry to transfer risk using data as the basis of risk evaluation. Based on the risk factors, the proposed model establishes the risk index system of the manufacturing industry and uses the expert evaluation method to design the scoring method of the evaluation index system. To ensure the accuracy of the evaluation results, the manufacturing industry’s fuzzy comprehensive model is established using the entropy weight method, and the expert evaluation results are modified accordingly. The experimental results show that the highest efficiency of the proposed method is 96%, the highest accuracy of the evaluation result is 75%. The evaluation result’s stability is higher than the other existing methods, which fully verifies the effectiveness and can provide a reliable theoretical basis for enterprise risk evaluation research.

4

Modelling of iron ore processing in technological units based on the hybrid approach

Morkun Vladimir, Tron Vitaliy, Zymohliad Vadym

Acta Mechanica et Automatica

|

2022

|

Vol. 16, no. 1

82--90

EN

The process line of concentrating iron ore materials is considered as a sequence of connected concentration units, some of which partially return ore materials to the previous unit. The output product of the final concentration unit in the process line is the end product of the whole line. Characteristics of ore, such as distribution of ore particles by size and distribution of iron content by size classes, are considered. Processing of iron ore materials by process units (a cycle, a scheme) is characterised by a separation characteristic – namely the function of extracting elementary fractions depending on physical properties of ore particles. The results of fraction analysis of ore samples in different points of the process line provide an experimental definition of separation characteristics and numerical values of the Rosin–Rammler equation factors. To identify dependencies that cannot be analytically described, the hybrid approach accompanied by the Takagi–Sugeno fuzzy models, in accompaniment with triangular membership functions determining fuzzy sets in preconditions, are used. To identify fuzzy sets in rule preconditions, triangular membership functions are used. Introduction of a-priori data on iron ore concentration as constraints for model parameters is a promising trend of further research, since it enables increased accuracy of identification despite limited availability of experimental data.

5

Machine learning based approach to a crane load estimation

Smoczek Jarosław, Hyla Paweł, Kusznir Tom

Journal of KONBiN

|

2021

|

Vol. 51, iss. 4

1--10

EN

In the presence of increasing demands for safety and efficiency of material handling systems, the development of advanced supervisory control, monitoring, data acquisition and diagnostic systems is involved, especially for large industrial cranes. The important part of such systems is the continuous monitoring of a crane load. The crane load monitoring system proposed in the paper is based on a fuzzy model that estimates a payload mass transferred by a crane based on measuring the crane girder deflection and trolley position. The model was identified using the fuzzy subtractive clustering and least mean square with the data collected during experiments carried out on the laboratory scaled overhead crane.

PL

Coraz większe wymagania odnośnie bezpieczeństwa i wydajności procesu transportu technologicznego kierują uwagę na rozwój coraz bardziej zaawansowanych systemów nadrzędnego sterowania, monitorowania, akwizycji danych i diagnostyki dźwignic. Ważnym elementem takiego systemu jest pomiar i monitorowanie obciążenia dźwignicy. Zaproponowany w pracy system monitorowania obciążenia suwnicy pomostowej został oparty na rozmytym modelu estymującym masę ładunku transportowanego przez suwnicę na podstawie odkształcenia dźwigara mostu suwnicy oraz pozycji wciągarki. Przedstawiono dwustopniową procedurę identyfikacji modelu z zastosowaniem metod grupowania rozmytego oraz najmniejszych kwadratów, którą przeprowadzono dla danych uzyskanych z eksperymentów wykonanych na stanowisku laboratoryjnym.

6

Development of Subcontractor Selection Models Using Fuzzy and AHP Methods in the Apparel Industry Supply Chain

Lahdhiri Mourad, Babay Amel, Jmali Mohamed

Autex Research Journal

|

2021

|

Vol. 21, no. 4

413--427

EN

The subcontractor selection decision is inherently a multicriterion problem. It is a decision of strategic importance for companies. The nature of this decision is usually complex and unstructured. Management science techniques might be helpful tools for solving these kinds of decision-making problems. In this research, the fuzzy logic method and the analytic hierarchy process were applied for the selection of suitable subcontractors in an apparel supply chain. In general, many factors, such as quality level, price offer, and delivery delay, were considered to determine the most suitable and reliable subcontractors that fit the company's strategy. This survey is carried out using the database of an apparel company manufacturing denim products.

7

Fuzzy modeling and parametric analysis of non-traditional machining processes

Chakraborty Shankar, Das Partha Protim

Management and Production Engineering Review

|

2019

|

Vol. 10, No. 3

111--123

EN

The application of artiﬁcial intelligence (AI) in modeling of various machining processes has been the topic of immense interest among the researchers since several years. In this direction, the principle of fuzzy logic, a paradigm of AI technique, is eﬀectively being utilized to predict various performance measures (responses) and control the parametric settings of those machining processes. This paper presents the application of fuzzy logic to model two non-traditional machining (NTM) processes, i.e. electrical discharge machining (EDM) and electrochemical machining (ECM) processes, while identifying the relationships present between the process parameters and the measured responses. Moreover, the interaction plots which are developed based on the past experimental observations depict the eﬀects of changing values of diﬀerent process parameters on the measured responses. The predicted response values derived from the developed models are observed to be in close agreement with those as investigated during the past experimental runs. The interaction plots also play signiﬁcant roles in identifying the optimal parametric combinations so as to achieve the desired responses for the considered NTM processes.

8

The prospects for the use of intelligent systems in the processes of gravitational enrichment

Suleimenov Batyrbek, Kulakova Yelena

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2019

|

T. 9, nr 2

46--49

EN

Intelligent control systems are actively developing and can significantly reduce financial costs and improve the environmental performance of ore-dressing processes. Usage of intelligent control systems for gravitational enrichment allows to minimize costs and negative influence of ore tails on the environment, exclude losses of concentrate and energy resources in the ore-dressing process. The paper discusses the problems and prospects for the application of intelligent control systems of gravity concentration equipment. A structure of the control system and an intelligent model for determining the frequency of pulsation jigging machine based on fuzzy logic are proposed. The model is based on data obtained from experts, it is researched. The obtained results allow to judge about the prospects for the implementation of intelligent systems in the management of ore enrichment.

PL

Zastosowanie inteligentnych systemów zarządzania wzbogacaniem grawitacyjnym zminimalizuje koszty i negatywny wpływ odpadów przeróbczych na środowisko, wyeliminuje straty koncentratu i zasobów energetycznych w procesie zagęszczania rudy. W artykule omówiono problemy i perspektywy zastosowania inteligentnych systemów sterowania urządzeń do wzbogacania metodą grawitacyjną. Zaproponowano strukturę systemu sterowania i model inteligentny do określania częstotliwości maszyny sedymentacyjnej na bazie logiki rozmytej. Model opiera się na danych otrzymanych od ekspertów. Uzyskane wyniki pozwalają nam ocenić perspektywy wdrożenia inteligentnych systemów w procesach kontroli przerobu rudy.

9

Self-adaptive grey wolf optimization based adaptive fuzzy aided sliding mode control for robotic manipulator

Kalshetti Sunil C., Dixit S. K.

Control and Cybernetics

|

2018

|

Vol. 47, no. 4

383--409

EN

As the robotic manipulators are highly nonlinear, it is a challenging task to design, in particular, the PUMA 560 robotic arm with acceptable performance. This paper intends to show the design and development of an adaptive sliding mode controller (SMC) for a robotic manipulator. Since it is not realistic to match the SMC operations with the system model at every time instant, this paper adopts fuzzy inference to replace the system model. This approach successfully achieves the objectives of the experiment, carried out in two stages. In the first stage, it acquires the precise characteristics of the system model for the diverse samples and adequately represents the robotic manipulator. Subsequently, we derive the acquired characteristics in the form of fuzzy rules. In the second stage, we represent the derived fuzzy rules on the basis on adaptive fuzzy membership functions. Further, the approach introduces the self-adaptiveness into a recent algorithm called Grey Wolf Optimization (GWO) in order to establish the adaptive fuzzy membership functions. We then compare the effectiveness of the proposed method with the identified experimental model and the known methods, like SMC, Fuzzy SMC (FSMC), and GWO-SMC. Finally, the comparison with the known methods establishes the effectiveness of the proposed SAGWO-FSMC technique.

10

Application of the k nearest neighbors method to fuzzy data processing

Pluciński M., Pietrzykowski M.

Przegląd Elektrotechniczny

|

2017

|

R. 93, nr 1

77--81

EN

The paper presents that with the application of fuzzy numbers arithmetic, the k nearest neighbors method can be adapted to various types of data. Both, the learning data and the input data may be in the form of the crisp number, interval or fuzzy number. Experiments proved that the method works correctly and gives credible results. There is also shown that the kNN method can be used for the determination of the fuzzy model output.

PL

W artykule pokazano, że z wykorzystaniem arytmetyki rozmytej, metoda k najbliższych sąsiadów może być zastosowana do danych różnego typu. Zarówno dane uczące, jak i dane wejściowe modelu mogą być liczbami, interwałami lub liczbami rozmytymi. Eksperymenty wykazały, że metoda działa prwidłowo i daje wiarygodne wyniki. Zaprezentowano również możliwość użycia metody k najbliższych sąsiadów do wyznaczania wyjścia modelu rozmytego.

11

Model oceny dodatkowego obciążenia poznawczego u kierowcy na podstawie badań z wykorzystaniem symulatora jazdy

Kruszewski M., Razin P., Niezgoda M., Nader M.

Prace Naukowe Politechniki Warszawskiej. Transport

|

2017

|

z. 118

155--166

PL

Rozproszenie uwagi kierowcy jest od lat jednym z podstawowych problemów motoryzacji, jednak coraz częściej rozważane jest w kontekście zwracania uwagi na systemy lub usługi dostępne w pojeździe. Obsługa telefonu komórkowego lub systemu nawigacji w trakcie jazdy może silnie negatywnie wpływać na jakość prowadzenia pojazdu, co jest podstawowym zadaniem kierowcy. W pracy zaprezentowano model oceny stanu rozproszenia kierowcy, rozumianego jako angażowanie się w zadania nie związane z prowadzeniem pojazdu, na podstawie wyłącznie danych o ruchu pojazdu. Model opracowano na podstawie wyników badań symulacyjnych, w których 72 kierowców (w tym 36 kobiet) w wieku 19-29 lat, którzy posiadali ważne prawo jazdy i mieli zróżnicowany poziom doświadczenia w prowadzeniu samochodu, wykonywali w trakcie prowadzenia samochodu dodatkowe zadania angażujące różne zmysły i zasoby poznawcze. Przejazd został opracowany zgodnie z założeniami standaryzowanego zadania: jazdy w trójpojazdowym plutonie.

EN

Drivers inattention and distraction problems are one of the most urgent issues for further development of motorization and standing on the way to improve road safety. Both issues are increasingly considered in the scope of in-vehicle services and systems exploitation. Use of cell-phone or navigation system during driving may have strongly detrimental effect on primary driver’s task – driving. In the following paper, authors present the model of evaluation of driver distraction state. Distraction is considered in terms of drivers secondary task involvement. The model uses only car-related data of drivers control over vehicle. To develop the model there were used results of driving simulator-based experiment where drivers performed different secondary tasks during driving. The group of 72 drivers (36 female) in age of between 19 and 29 years old with valid driver’s license and different level of experience performed during standardized driving task and additional (secondary) task. Primary driving task was conducted according to three-vehicles platoon task.

12

Model systemu ekspertowego rozmyto-probabilistycznego oceny zdatności obiektu technicznego w zarządzaniu linią produkcyjną

Topolska K.

Autobusy : technika, eksploatacja, systemy transportowe

|

2016

|

R. 17, nr 6

1796--1801

PL

Ocena zarządzania obiektami technicznymi wymaga bardzo często specjalistycznego podejścia. Bardzo złożone nieliniowe przestrzenie cech wymagają szukanie rozwiązań stosując różnych łączonych teorii. Autorka przedstawia w artykule teorie łączącą model rozmyty z modelem probabilistycznym. Zasadność takiego modelu jest uzasadniona w przypadkach kiedy cechy obiekty da się opisać modelem Bayesa lecz ze względu na dużą złożoność i nieprecyzyjność danych konieczne staje się zastosowanie metod opisujących takie dane.

13

Application of the reinforcement learning for selecting fuzzy rules representing the behavior policy of units in RTS-type games

Kutyło M, Pluciński M., Laskowska M

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 2

142-146

EN

The aim of the presented research was to prove the feasibility of the fuzzy modeling employing in combination with the reinforcement learning, in the process of designing an artificial intelligence that effectively controls the behavior of agents in the RTS-type computer game. It was achieved by implementing a testing environment for “StarCraft”, a widely popular RTS game. The testing environment was focused on a single test-scenario, which was used to explore the behavior of the fuzzy logic-based AI. The fuzzy model’s parameters were adjustable, and a Q-learning algorithm was applied to perform such adjustments in each learning cycle.

PL

W artykule przedstawiono badania możliwości połączenia modelowania rozmytego z uczeniem ze wzmocnieniem w procesie projektowania inteligentnego algorytmu, który będzie efektywnie kontrolował zachowanie agentów w grze typu RTS. Aby osiągnąć założony cel, zaimplementowano testowe środowisko w popularnej grze RTS „StarCraft”. W środowisku tym realizowano jeden założony scenariusz gry, w którym badano zachowanie opracowanego algorytmu rozmytego. Parametry modelu rozmytego były modyfikowane za pomocą metody Q-learning.

14

Inteligentny model wskaźnika zagrożenia pożarowego w kopalni węgla

Mrozek B., Felka D.

Pomiary Automatyka Robotyka

|

2012

|

R. 16, nr 2

540-545

PL

Istotny wpływ na wykrywanie zagrożenia pożarowego przenośników taśmowych w kopalniach węgla mają wartości takich parametrów, jak: stężenie tlenku węgla (CO) i cyjanowodoru (HCN) oraz wartości sygnałów z czujników dymu. Wielkości te są uwzględniane podczas wyznaczania wartości wskaźnika zagrożenia pożarowego. Zbudowano rozmyty model wskaźnika zagrożenia pożarowego w oparciu o laboratoryjne dane pomiarowe wymienionych wielkości. Model rozmyty wygenerowano z danych numerycznych przy zastosowaniu czterech algorytmów rozmytej klasteryzacji, które zaimplementowano w kodzie środowiska MATLAB. Uzyskane wyniki pokazano w tabelach i na wykresach. Do budowy i wizualizacji projektowanego modelu rozmytego wykorzystano funkcje oraz interfejsy Fuzzy Logic Toolbox.

EN

Significant influence on detecting the fire hazard of belt conveyor in the coal mine have values such parameters as concentration of carbon monoxide (CO), concentration of hydrogen cyanide (HCN) and signals from smoke detectors. Those values are used to set the fire risk index. Fuzzy model of the fire risk index was built based on laboratory data measurements. Fuzzy model was generated from the above numerical data using four algorithms of fuzzy clustering, implemented in the MATLAB code. The results are shown in tables and graphs. MATLAB and Fuzzy Logic Toolbox library (functions and interfaces) were used to design and visualize the proposed fuzzy model.

15

Orthonormal basis function fuzzy systems for biological wastewater treatment processes modeling

Chaibakhsh A., Chaibakhsh N., Abbasi M., Norouzi A.

Journal of Artificial Intelligence and Soft Computing Research

|

2012

|

Vol. 2, No. 4

343--356

EN

In this paper, fuzzy models with orthonormal basis functions (OBF) framework are employed for modeling the nonlinear dynamics of biological treatment processes. These models are consisting of a linear part describing the system dynamics (Laguerre filters) followed by a non-linear static part (fuzzy system). The training procedure contains of two main steps: 1) obtaining the optimum time-scale and the order of truncated Laguerre network as the linear part and 2) defining membership functions, corresponding rules and adjusting the consequent parameters of fuzzy system as the nonlinear part. A comparison between the responses of the developed model and the original plant was performed in order to validate the accuracy of the developed model.

16

Software for Occupational Health and Safety Risk Analysis Based on a Fuzzy Model

Stefanovic M., Tadic D., Djapan M., Macuzic I.

International Journal of Occupational Safety and Ergonomics

|

2012

|

Vol. 18, No. 2

127--136

EN

Risk and safety management are very important issues in healthcare systems. Those are complex systems with many entities, hazards and uncertainties. In such an environment, it is very hard to introduce a system for evaluating and simulating significant hazards. In this paper, we analyzed different types of hazards in healthcare systems and we introduced a new fuzzy model for evaluating and ranking hazards. Finally, we presented a developed software solution, based on the suggested fuzzy model for evaluating and monitoring risk.

17

Fuzzy model for structuring project teams

Bach-Dąbrowska I

Applied Computer Science

|

2012

|

Vol. 8, no 1

3--24

EN

The aim of this paper is to present the new approach to process of project team structuring. This approach contains proposition of reference model for selection process, formulated in terms of fuzzy logic theory. The model allows formalising in mathematical way linguistic, rough assessment of human behaviour, competency, and psychological profile according to vacant posts, project and team requirements.

18

Toward smart decision support system for mortgage market

Orłowski A., Szczerbicki E.

Systems Science

|

2010

|

Vol. 36, no 1

35-40

EN

This paper presents the structure of initial fuzzy model representing the Polish Internet Mortgage Market. It starts with an introduction describing the market complexities and challenges, and description of previously created rule based model. Then the steps of the process of proposed model fuzzification are presented. Next, there is presented Graphic User Interface developed for the model created. The final part of the paper consists of conclusions and directions for future research.

19

Zastosowanie identyfikacji opartej na wnioskowaniu rozmytym do identyfikacji modeli dynamicznych na przykładzie modelu protezy POLVAD

Janiszowski K.

Pomiary Automatyka Robotyka

|

2010

|

R. 14, nr 11

90-95

PL

W pracy został przedstawiony sposób modelowania dynamicznych właściwości procesu z wykorzystaniem parametrycznych modeli rozmytych. Podejście to zostało zaprezentowane na przykładzie badania dynamiki sztucznej protezy serca POLVAD, przeprowadzonego na podstawie licznych eksperymentów testowych. We wstępie opisano badany proces i podkreślono pewne właściwości o charakterze nieciągłego działania, których występowanie ogólnie ogranicza zastosowanie opisu transmitancyjnego. Wyprowadzono podstawowe zależności do prowadzenia obliczeń parametrycznych modeli dynamicznych drogą oszacowań statystycznych dla modeli liniowych parametrycznych oraz modeli rozmytych. Przedstawiono wyniki badań optymalnego modelu liniowego i modelu rozmytego oraz przeprowadzono obszerną dyskusję uzyskanych modeli. Uzyskany opis dynamiki badanego procesu odtwarza wszystkie istotne zachowania badanego procesu w sposób całkowicie wystarczający do prowadzenia badań analizujących różne algorytmy sterowania lub regulacji, jak również umożliwia wprowadzenie np. optymalizacji pracy zaworów sterujących.

EN

The aim of paper was to describe an effective approach to modelling of dynamics an artificial heath chamber - ventricular assisting device (POLVAD). The precise model of this component is very important in proper design of supply and control system, that have to be safe and have long autonomic operation time. In the introduction a short presentation of parametric and fuzzy models was made, together with some aspects of good conditioning of numerical calculations. Next results of fuzzy identification of POLVAD were presented and discussed. Obtained model is very precise and can be used in fast prototyping mode at design of proper control.

20

INTEGR - A Method for Integrating Expert Knowledge and Knowledge Derived from a Data Set

Rejer I.

Pomiary Automatyka Kontrola

|

2010

|

R. 56, nr 10

1197-1200

EN

The aim of the paper is to present a new approach for integrating expert knowledge with knowledge derived from a data set, called INTEGR. INTEGR approach is based on the method of training an expert fuzzy model with a set of data points but eliminates main drawbacks of this method. The paper presents both - the theoretical description of INTEGR algorithm and its practical application.

PL

Zarówno modele rozmyte budowane na podstawie zbioru danych pomiarowych jak i modele rozmyte budowane przy wykorzystaniu wiedzy eksperckiej mają specyficzne dla siebie wady i zalety. Model ekspercki jest modelem przybliżonym, ale obowiązującym w całej dziedzinie analizowanej zależności, natomiast model zbudowany na podstawie zbioru danych pomiarowych jest modelem dokładnym, ale wiarygodnym tylko w pewnym, ściśle określonym fragmencie dziedziny. Wynika z tego, że aby zwiększyć precyzję rozmytych modeli eksperckich należy do nich dołączyć wiedzę zawartą w danych pomiarowych i analogicznie, żeby poszerzyć zakres stosowalności modeli rozmytych opracowanych na podstawie zbioru danych pomiarowych należy dołączyć do nich wiedzę ekspercką. Celem niniejszego artykułu jest przedstawienie nowej metody integracji wiedzy eksperckiej z wiedzą wydobytą z danych pomiarowych (metody INTEGR). Opisywana metoda jest oparta na uczeniu eksperckiego modelu rozmytego przy pomocy zbioru danych pomiarowych, ale eliminuje podstawowe wady tego podejścia. W artykule zaprezentowano zarówno teoretyczny opis metody, jak i jej praktyczne wykorzystanie na przykładzie modelu rozmytego przeznaczonego do wyceny samochodów używanych.