Wyniki wyszukiwania - BazTech

1

Analiza potencjału ataków wykorzystujących syntetycznie wygenerowane głosy na systemy biometrycznej weryfikacji mówców oraz wykrywania materiałów deepfake

Bartuzi-Trokielewicz Ewelina

Cybersecurity and Law

|

2024

|

Vol. 12 (2)

25--36

PL

Postęp technologiczny w dziedzinie głębokiego uczenia znacząco przyczynił się do roz-woju syntezowania głosu, umożliwił tworzenie realistycznych nagrań audio, które mogą naśladować indywidualne cechy głosów ludzkich. Chociaż ta innowacja otwiera nowe możliwości w dziedzinie technologii mowy, niesie ze sobą również poważne obawy dotyczące bezpieczeństwa, zwłaszcza w kontekście potencjalnego wykorzystania technologii deepfake do celów przestępczych. Przeprowadzone badanie koncentrowało się na ocenie wpływu syntetycznych głosów na systemy biometrycznej weryfikacji mówców w języku polskim oraz skuteczności wykrywania deepfake’ów narzędziami dostępnymi publicznie, z wykorzystaniem dwóch głównych metod generowania głosu, tj. przekształcenia tekstu na mowę oraz konwersji mowy. Jednym z głównych wniosków analizy jest potwierdzenie zdolności syntetycznych głosów do zachowania charakterystycznych cech biometrycznych i otwierania drogi przestępcom do nieautoryzowanego dostępu do zabezpieczonych systemów lub danych. To podkreśla potencjalne zagrożenia dla indywidualnych użytkowników oraz instytucji, które polegają na technologiach rozpoznawania mówcy jako metodzie uwierzytelniania i wskazuje na konieczność wdrażania modułów wykrywania ataków. Badanie ponadto pokazało, że deepfaki odnalezione w polskiej części internetu dotyczące promowania fałszywych inwestycji lub kierowane w celach dezinformacji najczęściej wykorzystują popularne i łatwo dostępne narzędzia do syntezy głosu. Badanie przyniosło również nowe spojrzenie na różnice w skuteczności metod kon-wersji tekstu na mowę i klonowania mowy. Okazuje się, że metody klonowania mowy mogą być bardziej skuteczne w przekazywaniu biometrycznych cech osobniczych niż metody konwersji tekstu na mowę, co stanowi szczególny problem z punktu widzenia bezpieczeństwa systemów weryfikacji. Wyniki eksperymentów podkreślają potrzebę dalszych badań i rozwoju w dziedzinie bezpieczeństwa biometrycznego, żeby skutecznie przeciwdziałać wykorzystywaniu syntetycznych głosów do nielegalnych działań. Wzrost świadomości o potencjalnych zagrożeniach i kontynuacja pracy nad ulepszaniem technologii weryfikacji mówców są ważne dla ochrony przed coraz bardziej wyrafinowanymi atakami wykorzystującymi technologię deepfake.

EN

Technological advancements in the field of deep learning have significantly contributed to the development of voice synthesis, enabling the creation of realistic audio recordings that can mimic the individual characteristics of human voices. While this innovation opens up new possibilities in the field of speech technology, it also raises serious security concerns, especially in the context of the potential use of deepfake technology for criminal purposes. Our study focuses on assessing the impact of synthetic voices on biometric speaker verification systems in Polish and the effectiveness of detecting deepfakes with publicly available tools, considering two main approaches to voice generation: text-to-speech conversion and speech conversion. One of the main findings of our research is the confirmation that synthetic voices are capable of retaining biometric characteristics, which could allow criminals unauthorized access to protected systems or data. The analysis showed that the greater the biometric similarity between the „victim’s” voice and the „criminal’s” synthetic voice, the more difficult it is for verification systems to distinguish between real and fake voices. This highlights the potential threats to individual users and institutions that rely on speaker recognition technologies as a method of authentication. Our study also provides a new perspective on the differences in the effectiveness of text-to-speech conversion methods versus speech cloning. It turns out that speech cloning methods may be more effective in conveying individual biometric characteristics than text-to-speech conversion methods, posing a particular problem from the security perspective of verification systems. The results of the experiments underscore the need for further research and development in the field of biometric security to effectively counteract the use of synthetic voices for illegal activities. Increasing awareness of potential threats and continuing work on improving speaker verification technologies are crucial for protecting against increasingly sophisticated attacks utilizing deepfake technology.

2

Archipelag sztucznej inteligencji. Część I

Tadeusiewicz Ryszard

Napędy i Sterowanie

|

2020

|

R. 22, nr 12

26--40

PL

Tytuł tego artykułu może budzić wątpliwości Czytelników. Sztuczna inteligencja? Wiadomo! Ale jakiś archipelag? Już wyjaśniam. Otóż sztuczna inteligencja tylko z nazwy jest dziedziną integralną, jak – nawiązując do tytułu miesięcznika – napędy albo sterowanie. W istocie sztuczna inteligencja to zbiór bardzo różnych metod, które ludzie wymyślili w tym celu, żeby maszyny lepiej zaspokajały ich potrzeby. Te metody w większości nie mają ze sobą nawzajem absolutnie nic wspólnego. Są od siebie odległe i nie ma łatwego sposobu przejścia od jednej z nich do innej. Pozwoliłem sobie porównać tę sytuację do archipelagu wysp.

3

Quantum-inspired artificil neural networks and evolutionary algorithms methods applied to modeling of the polish electric power exchange using the day-ahead market data

Tchórzewski J., Ruciński D.

Information Systems in Management

|

2018

|

Vol. 7, No. 3

201--212

EN

The paper presents selected results of research on the use of artificial intelligence methods, which are inspired by quantum computing solutions for modelling of electric power exchange systems. Methods used in the modelling of quantum data acquisition, quantization and dequantization of information as well as the methods of performing quantum computations were emphasized. Furthermore, we have analysed the results obtained for the neural model and for the evolutionary algorithm inspired by the quantum computer science. Eventually, the model was verified on the example of the neural model of the Electric Power Exchange (EPE).

4

Virtual laboratory methodology in scientific researches and education

Honysz R., Dobrzański L. A.

Journal of Achievements in Materials and Manufacturing Engineering

|

2017

|

Vol. 84, nr 2

76--84

EN

Purpose: This article is presenting the Material Science Virtual Laboratory. Developed laboratory is an open scientific, investigative, simulating and didactic medium helpful in the realisation of the scientific and didactic tasks in the field of material Science. It is implemented in the Institute of Engineering Materials and Biomaterials of Silesian University of Technology in Gliwice, Poland. Design/methodology/approach: The laboratory is a set of testers and training simulators, set in the Virtuality and created in several languages and the programming techniques, which interprets the properties, functionality and manual rules of actual equipment installed and accessible in the real science labs of scientific universities. Findings: Application of the equipment, that is practically imperishable, cheap in exploitation and ease in the use encourages students and scientific workers to independent audits and experiments in places, where the possibilities of their performance in the real investigative laboratory will be restricted because of the high material costs, difficult access to real equipment or the possible peril of his impairment. Research limitations/implications: The proposed solutions allow the utilisation of the developed virtual environment as a new medium in both, the scientific work performed remotely, as well as in education during classes. Practical implications: The usage possibilities of the virtual laboratory are practically unrestricted; it can be a foundation for any surveys, course or training plan. Originality/value: The project of the virtual laboratory corresponds with the global tendency for expand the investigative and academic centres about the possibilities of training and experiments performance with use of the virtual reality. This enriches investigation and training programmes of the new abilities reserved so far exclusively for effecting only on actual equipment.

5

The Use of Fuzzy Systems for Forecasting the Hardenability of Steel

Sitek W., Irla A.

Archives of Metallurgy and Materials

|

2016

|

Vol. 61, iss. 2A

797--802

EN

The goal of the research carried out was to develop the fuzzy systems, allowing the determination of the Jominy hardenability curve based on the chemical composition of structural steels for quenching and tempering. Fuzzy system was created to calculate hardness of the steel, based on the alloying elements concentrations, and to forecast the hardenability curves. This was done based on information from the PN-EN 10083-3: 2008. Examples of hardenability curves calculated for exemplar steels were presented. Results of the research confirmed that fuzzy systems are a useful tool in evaluation the effect of alloying elements on the properties of materials compared to conventional methods. It has been demonstrated the practical usefulness of the developed models which allows forecasting the steels’ Jominy hardenability curve.

6

The use of artificial neural networks for the prediction of sulphur content in hot metal produced in blast furnace

Dobrzański L. A., Trzaska J., Gawron M., Berliński M.

Journal of Achievements in Materials and Manufacturing Engineering

|

2015

|

Vol. 70, nr 2

86--92

EN

Purpose: The paper presents the possibilities of using artificial intelligence for the prediction of sulphur content in hot metal produced in blast furnace. Design/methodology/approach: Three blast furnaces in ArcelorMittal, Unit in Dąbrowa Górnicza, provided the data for the model construction. The data reflect a number of variables, which describe the blast furnace process. Findings: Materials research performed with the use of data mining and neural networks is consistent with the results obtained during the real research in a real laboratory. The obtained results show that the construction of such neural networks is practical. There is a strong correlation between predicted value and real value. Practical implications: The presented model can be used in the industrial practice as an additional tool for blast furnace and steel plant operators. Originality/value: Prediction of sulphur content in hot metal at the stage of adjusting hot metal process parameters.

7

The application of neural networks to analysis of the effects of chemical composition on hardenability of steel

Sitek W., Jabłoński A.

Journal of Achievements in Materials and Manufacturing Engineering

|

2015

|

Vol. 72, nr 1

32--38

EN

Purpose: The goal of the research carried out was evaluation of alloying elements effect on the development of artificial neural network models, allowing the determination of the Jominy hardenability curve based on the chemical composition of constructional and machine steels. Design/methodology/approach: MLP neural network was used to learn rule for modelling the steels properties. Then the neural network used for computer simulation synergistic effect of alloying elements on the hardenability of steel. Research limitations/implications: Results of the research confirmed that neural networks are a useful tool in evaluation the effect of alloying elements on the properties of materials compared to conventional methods. Additionally it confirms idea, that based on data from standards and catalogues is possible to develop the assumed model. Practical implications: It has been demonstrated complete the practical usefulness of the developed models in the selection of materials designed machine parts, which allows the direct relationship during the melting process real time control of the desired hardness of the steel hardenability curve. Originality/value: Based on the results of catalogues and standards with the used of neural networks developed and fully validated experimental model of the relationship between hardenability and chemical composition of the constructional and machine steels.

8

Model samoorganizującego się, złożonego systemu komunikacyjnego

Stankiewicz K.

Modelowanie Inżynierskie

|

2014

|

T. 20, nr 51

94--99

PL

W przemyśle można spotkać się ze złożonymi strukturami komunikacyjnymi zarówno w przypadku transmisji wizyjnej, głosowej, jak i danych pochodzących z układów monitoringu lub sterowania maszyn. W publikacji zaprezentowano koncepcję metody umożliwiającej samoorganizowanie się złożonych struktur transmisji danych w jednolite ciągi komunikacyjne tworzące wirtualne, niezawodne medium transmisyjne. Systemy bazujące na podobnych technikach odznaczają się dużą odpornością na awarie oraz dynamiczną, samoistną zmianą struktury sprzętowej lub programowej, adaptującej się do zmiennych warunków pracy.

EN

The industry can meet the complex communication structures for the visual, voice and data, from monitoring or control systems, transmission. The paper presents the concept of self-organization methods allow complex data structures into a single virtual traffic routes forming which are reliable transmission medium. Systems based on similar techniques have a high fault tolerance and dynamic, spontaneous changes in the hardware or software, which allows adaptation to changing conditions.

9

The evaluation of the TPM synchronization on the basis of their outputs

Dolecki M., Kozera R., Lenik K.

Journal of Achievements in Materials and Manufacturing Engineering

|

2013

|

Vol. 57, nr 2

91--98

EN

Purpose: Tree Parity Machines are specific artificial neural networks used to construct relatively secure key exchange protocol [12,15,24]. The level of networks’ compatibility is measured by weight vectors mutual overlap. However, to calculate such mutual overlap, one needs to be familiar with both weights’ vectors, which is impossible in practical key exchange. This paper discusses other schemes to evaluate compatibility of weights’ vectors. The first one uses Euclidean distance of both weights’ vectors. The second one is based on frequencies of common TPM’s outputs and as such does not rely on the weights’ vectors. Both approaches to handle secure key exchange protocol facilitate more extended analysis of many technical processes in which a vital role plays an incorporation of a non-standard high-quality method securing any sensitive data. Design/methodology/approach: Computer simulations of TPM synchronization are conducted using authors’ program and the obtained results are statistically analyzed herein. Findings: We found experimentally that mutual overlap of the weights’ vectors is highly correlated with Euclidean distance. Additionally, frequencies of common outputs in given numbers of learning cycles stay in high correlation with this mutual overlap and Euclidean distance. The latter can subsequently be used to draw pertinent conclusions about TPM’s weights compatibility. Practical implications: Proposed methods, especially frequencies analysis, can be applied to key exchange protocol to improve its security. Determining the vectors compatibility level before synchronization completion allows qualifying this synchronization to one of the possible time classes. Originality/value: New ideas presented in this work involve application of Euclidean distance and common output frequencies to calculate the networks compatibility given by weights mutual overlap.

10

Influence analysis of admixtures on mechanical properties of non-alloy structural steels

Honysz R., Dobrzański L.A.

Journal of Achievements in Materials and Manufacturing Engineering

|

2013

|

Vol. 61, nr 2

336--342

EN

Purpose: The paper introduces analysis results of selected alloying elements influence on mechanical properties of alloy structural steels for quenching and tempering. Design/methodology/approach: Investigations were performed in virtual environment with use of materials science virtual laboratory. Virtual investigations results were verified in real investigative laboratory. Findings: Materials researches performed with use of material science virtual laboratory in range of determining the mechanical properties are consistent with the results obtained during the real research in real laboratory. Practical implications: Development of virtual tools, which are simulating the investigative equipment and simulating the research methodology, can serve as a basis for combining aspects of laboratory research, simulation, measurement, and education. Application of these tools will allow the transfer of research and teaching procedures from real laboratory to virtual environment. This will increase the number of experiments conducted in virtual environment and thus, it will increase the efficiency of such researches. Originality/value: Modelling of structural steels mechanical properties is valuable for steel designers and manufacturers, because it is associated with financial benefits, when expensive and time-consuming researches are reduced to necessary minimum.

11

Metody sztucznej inteligencji w projektowaniu harmonogramu przewozów dla dynamicznych potrzeb transportowych

Król A.

Autobusy : technika, eksploatacja, systemy transportowe

|

2013

|

R. 14, nr 3

1369-1384

PL

Problem skonstruowania optymalnego planu przewozów pomiędzy wieloma węzłami źródłowymi i wieloma węzłami docelowymi przy ograniczonej liczbie środków transportowych jest bardzo złożony obliczeniowo. Z reguły, w zależności od zakresu zadań są to problemy NP - zupełne. Opracowanie przybliżonej metody pozwalającej na znalezienie prawie optymalnego rozwiązania w krótkim czasie może mieć więc duże praktyczne znaczenie. W pracy zaproponowano zastosowanie metod sztucznej inteligencji do projektowania przebiegu linii autobusowych oraz planowania rozkładu jazdy autobusów. Porównano wyniki uzyskane przy użyciu algorytmu genetycznego i symulowanego wyżarzania. Opracowany model zakłada znajomość struktury sieci transportowej dostępnej dla komunikacji publicznej oraz ustaloną z góry liczbę środków transportu (autobusów). Dynamiczne potrzeby transportowe zadane są w postaci ciągu złożonego ze zgłoszeń zamiaru podróży pomiędzy parą przystanków przez różne grupy pasażerów w kolejnych chwilach czasowych. Minimalizowany jest sumaryczny czas podróży pasażerów uwzględniający oczekiwanie na przystankach.

EN

The problem of constructing an optimal schedule for the multiple source nodes and destination nodes with a limited number of vehicles is computationally complex. In many cases, depending on the range of the tasks the problems as a rule are NP - hard. So, the development of a heuristic method to find the optimal solution in a short time can be of great practical importance. This paper proposes the use of the methods of artificial intelligence to design the course of bus routes and the timetables. The results obtained with the use of the genetic algorithm and the simulated annealing were compared. The model assumes the knowledge of the structure of the transport network and a predetermined number of means of transport (buses). Dynamic transportation needs are introduced as a series of requests of travel between pairs of bus stops for different groups of passengers in successive moments of time. The total travel time of all passengers including waiting time at bus stops is here the minimized value.

12

A system for behavioral therapy support for autistic children

Adamus E., Kołodziejczyk J.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 10b

276-279

EN

The Applied Behavioral Analysis (ABA) is one of the very successful therapies on autistic children. There are no software systems supporting such a complex therapy either in Polish or international ABA rehabilitation centers. This article presents an idea of an integrated system to help managing the vast amount of data collected during behavioral therapy. There are four main modules in the system: a database containing therapy data, system for data analysis based on machine learning techniques, an expert system to support therapist and a semantic based search.

PL

Stosowana analiza behawioralna jest jedną ze skuteczniejszych terapii dla dzieci z autyzmem. Zarówno w Polskich jak i światowych centrach rehabilitacyjnych nie stosuje się systemów oprogramowania, które wspierałby tą skomplikowaną terapię. Niniejszy artykuł prezentuje ideę zintegrowanego systemu wspomagającego zarządzenie ogromną ilością danych gromadzonych podczas terapii. W systemie zaplanowano cztery moduły: bazę danych zawierającą dane z terapii, system analizy danych wykorzystujący techniki z maszynowego uczenia się, system ekspertowy dla terapeutów oraz oparty na semantyce.

13

Hybrid modelling methods in materials science - selected examples

Sitek W., Trzaska J.

Journal of Achievements in Materials and Manufacturing Engineering

|

2012

|

Vol. 54, nr 1

93--102

EN

Purpose: The paper presents selected examples of application of computational tools, including artificial intelligence methods to solve examples of tasks in the area of materials science. (i) Selection method of steel grade with required hardenability; (ii) Modelling of CCT diagrams for engineering and constructional steels; (iii) Application of neural networks for selection of steel with the assumed hardness after cooling from the austenitising temperature; (iv) Designing of high-speed steels chemical composition Design/methodology/approach: In the paper been applied a hybrid approach that combined application of various mathematical tools including artificial neural networks, linear regression and genetic algorithms to solve selected tasks from the area of materials science. Findings: Computer modelling and simulation make improvement of engineering materials properties possible, as well as prediction of their properties, even before the materials are fabricated, with the significant reduction of expenditures and time necessary for their investigation and application. Methods used in hybrid systems are complementary and disadvantages of one method are compensated by the advantages of another method. Practical implications: Solutions presented in the work, based on using the adequate material models may feature an interesting alternative in designing of the new materials with the required properties. The practical aspect has to be noted, resulting form the developed models, which may successfully replace the above mentioned technological investigations, consisting in one time selection of the chemical composition and heat treatment parameters and experimental verification of the newly developed materials to check of its properties meet the requirements. Originality/value: The presented approach to new materials design assumes the maximum possible limitation of carrying out the indispensable experiments, to take advantage of the existing experimental knowledge resources in the form of databases and most effective computer science tools, including neural networks and evolutionary algorithms.

14

Application of artificial intelligence methods in PVD and CVD coatings properties modelling

Dobrzański L.A., Staszuk M., Honysz R.

Archives of Materials Science and Engineering

|

2012

|

Vol. 58, nr 2

152--157

EN

Purpose: The aim of this paper is the presentation of developed computational model build with use of artificial neural networks. This model describes the influence of PVD and CVD coatings properties on the cutting edge durability from sialon tool ceramics covered with these layers. Design/methodology/approach: Obtained model has the ability to compute the durability of the PVD and CVD coatings coated on sialon tool ceramics blades determined in technological cutting trials of grey cast iron, basing on PVD and CVD coatings microhardness, thickness, grain size and their adhesion to the substrate. Findings: Results of researches, performed with use of computational model, revealed, that the greatest influence on the durability of coated sialon tool ceramics blades have the adhesion to the substrate. Smaller influence on blades durability has the size of grains. Minor influence on the cutting tool from other properties was obtained. Practical implications: Achieved results indicates, that the best coating’s adhesion to the substrate for coating material selection and design of PVD and VD coatings deposition process should have priority in implementation. Originality/value: Obtainment and utilisation of computational model builded with use of artificial intelligence methods

15

Projektowanie rozbudowy sieci transportowych za pomocą algorytmu ewolucyjnego

Król A.

Roczniki Geomatyki

|

2011

|

T. 9, z. 4

85-92

PL

W artykule przedstawiono metodę poszukiwania wytycznych do rozbudowy lub modernizacji sieci transportowej, tak aby zbliżyć ją do struktury optymalnej dla analizowanego obszaru, przy zadanych potrzebach transportowych. Zastosowanie wyspowego algorytmu genetycznego umożliwia jednoczesne znajdowanie kilku najlepszych rozwiązań, które mogą być następnie ponownie rozpatrywane pod kątem innych kryteriów, których nie można było ująć w proponowanym modelu. Łatwość modelowania struktury sieci transportowej i dość krótki czas obliczeń pozwalają na rozpatrywania szerokiego spektrum konkurencyjnych propozycji rozbudowy sieci. Aktualna postać sieci transportowej i zakres dopuszczalnych ingerencji w jej strukturę są danymi wejściowymi, zatem możliwe jest przeanalizowanie wielu opcji rozbudowy: od drobnych, koniecznych korekt, aż do gruntownej przebudowy w celu zbliżenia się do prawdziwie optymalnej struktury. W każdym rozpatrywanym wariancie uzyskiwane są informacje o korzyściach (zmniejszeniu kosztów użytkowania) i kosztach (nakładach na rozbudowę).

EN

The current transportation network structure is usually the result of historical and often long random adaptation processes and it is almost surely not optimal for the present needs. As always in the past, when modernization or extension was required, the current state was the base for changes. Cases, where the design of whole transportation network is possible, are very rare. Possible existence of several transportation network variants meeting new needs constitutes an additional difficulty. In this situation, development of a method allowing comparison of different variants of transportation network extension is an interesting and urgent task. In the absence of analytical description and due to the complexity of the problem. exploration of the whole range of solutions is impossible and it seems the most appropriate to use artificial intelligence methods, particularly evolutionary algorithms.

16

Systemy wykrywania Intruzów wykorzystujące metody sztucznej Inteligencji

Kukiełka R., Kotulski Z.

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2011

|

nr 4

114-121

PL

W ostatnich latach sztuczna inteligencja znajduje zastosowanie w wielu dziedzinach. Jedną z nich są również systemy wykrywania intruzów IDS (Intrusion Detection System). Dzięki zdolności generalizacji metody sztucznej inteligencji umożliwiają klasyfikację ataków nie tylko według nauczonych wzorców, ale również wszelkich ataków podobnych do nich oraz niektórych nowych typów. IDS stosujące takie metody mogą się również w sposób dynamiczny dostosowywać do zmieniającej się sytuacji w sieci (np. uczyć się nowych zachowań użytkowników lub nowych ataków). Ich zaletą jest to, że nie wymagają budowy skomplikowanych zbiorów reguł i sygnatur odrębnych dla każdej instancji ataków, ponieważ dane niezbędne do wykrycia ataku są uzyskiwane automatycznie w procesie nauki. Artykuł zawiera podstawowe pojęcia związane z systemami wykrywania włamań oraz przegląd wyników dotyczących zastosowania w IDS metod sztucznej inteligencji, takich jak: drzewa decyzyjne, algorytmy genetyczne, systemy immunologiczne, sieci Bayesa oraz sieci neuronowe.

EN

Last years one of the most extensively studied field of research is artificial intelligence. It is used in many practical applications, one of them is Intrusion Detection Systems (IDS). Thanks to their generalization feature artificial intelligence methods allow to classify not only the learned attacks patterns but also their modified versions and some new attacks. They could dynamically adapt to changing situation in the network (eg., learn new users' behaviors or new attacks). Ań advantage of application of the artificial intelligence methods in IDS is that they do not require generation of the rule or the signature for each new instance of an attack because they automatically update the IDS knowledge in the learning phase. The first part of this paper includes basic information about intrusion detection system. In the next sections we present application in IDS such artificial intelligence methods like: decision trees, genetic algorithms, immunology systems, Bayes networks, and neural networks.

17

Optimisation of high-speed steels chemical composition using the artificial intelligence methods

Sitek W.

Journal of Machine Engineering

|

2011

|

Vol. 11, No. 1-2

120--133

EN

The main goal of the research carried out was developing the design methodology for the new high-speed steels with the required properties, including hardness and fracture toughness, as the main properties guaranteeing the high durability and quality of tools made from them. It was decided that hardness and fracture toughness KIc are the criteria used during the high-speed steels design. In case of hardness, the statistical and neural netw chemical composition and its heat treatment parameters, i.e., austenitizing- and tempering temperatures. In the second case - high-speed steels fracture toughness, the neural network model was developed, makin it possible to compute the KIc factor based on the steel chemical composition and its heat treatment parameters. The developed material models were used for designing the chemical compositions if the new high-speed steel, demonstrating the desired properties, i.e., hardness and fracture toughness. Methodology was developed to this end, employing the evolutionary algorithms, multicriteria optimisation of the high-speed steels chemical composition.

18

Harmonogramowanie zabiegów montażowych korpusu przewodu wentylacyjnego

Honczarenko J., Berliński A.

Technologia i Automatyzacja Montażu

|

2010

|

nr 1

6-9

EN

Paper presents review of theoretical methods for added assembly schedule and systems design. There was example analytical modeling and schedule optimization operations, based on new clinching technology, for went trunk ventilating canal made of steel profile presented. Production is realized on special assembly, technological station. There were scheduling assembly operations problem in model of traveling salesman problem formulated. Implementation model was in excel spreadsheet elaborated and with program Risk Solver Platform V 9.0 solved.

19

On burr height estimation based on axial drilling force

Sokołowski A.

Journal of Achievements in Materials and Manufacturing Engineering

|

2010

|

Vol. 43, nr 2

734--742

EN

Purpose: The main goal of the research is to build a model of relationship between burr height created during drilling operation and signal representing axial drilling force. Such a model can be applied in diagnostic system for on-line estimation of bur height. Design/methodology/approach: The first applied approach is based on a step by step procedure in which several statistical models were built. The second one is based on specific features of artificial intelligence methods. The artificial neural networks serve as a tool for data selection and integration while the fuzzy logic systems are applied for data integration, only. Findings: The developed algorithm for processing axial drilling force allowed constraining the noise inherent to the drilling process and emphasising the information that could be useful for building considered model. The impact of the properly conducted data selection has been emphasised. Also, importance of providing information represented with axial drilling force has revealed. Research limitations/implications: The developed models need to be checked or improved for practical implementation. Such improvement can be done by introducing other signal features or other cutting parameters as model inputs. Also, analysis of other signals that can be measured during drilling is assumed as a future work. Practical implications: The conducted research reconfirmed possibility of on-line diagnostics of bur height during drilling. Several parameters necessary for such diagnostics have been estimated. This suggests continuing the research in order to design a system that could be applied in industrial conditions. Originality/value: The proposed approach is not a typical since analytical models, FEM models or models basing only on cutting process parameters have been considered, mainly. Such models are limited to two dimensional machining, usually. Besides, application of artificial intelligence methods for data selection and integration points at novelty of the research conducted.

20

Artificial intelligence and virtual environment application for materials design methodology

Dobrzański L.A., Honysz R.

Archives of Computational Materials Science and Surface Engineering

|

2010

|

Vol. 2, nr 4

201-212

EN

Purpose: The purpose of this study is to develop a methodology for material design, enabling the selection of the chemical elements concentration, heat and plastic treatment conditions and geometrical dimensions to ensure the required mechanical properties of structural steels specified by the designer of machinery and equipment as the basis for the design of material components manufactured from these steels, by using a computational model developed with use of artificial intelligence methods and virtual environment. The model is designed to provide impact examinations of these factors on the mechanical properties of steel only in the computing environment. Design/methodology/approach: A virtual research environment built with use of computational model describing relationships between chemical composition, heat and plastic treatment conditions, product geometric dimensions and mechanical properties of the examined group of steels was developed and practical applied. This model enables the design of new structural steel by setting the values of mechanical properties based on material production descriptors and allows the selection of production descriptors on the basis of the mechanical properties without the need for additional tests or experimental studies in reality. Findings: Virtual computing environment allows full usage of the developed intelligent model of non-alloy and alloy structural steel properties and provides an easy, intuitive and user-friendly way to designate manufacturing descriptors and mechanical properties for products. Research limitations/implications:The proposed solutions allow the usage of developed virtual environment as a new medium in both, the scientific work performed remotely, as well as in education during classes. Practical implications: The new material design methodology has practical application in the development of materials and modelling of steel descriptors in aim to improve the mechanical properties and specific applications in the production of steel. Presented examples of computer aid in structural steel production showing a potential application possibility of this methodology to support the production of any group of engineering materials. Originality/value: The prediction possibility of the material mechanical properties is valuable for manufacturers and constructors. It ensures the customers quality requirements and brings also measurable financial advantages.