|
|
Spatial materials for additive manufacturing in civil engineering
Říha, Tomáš ; Apeltauer, Tomáš (referee) ; Podroužek, Jan (advisor)
The bachelor thesis deals with additive manufacturing in the construction industry and with materials used in this field. The first part of the thesis defines the 3D printing, briefly describes the history of this progressive technology and gives an overview of the used methods and technologies. The printing methods are divided according to the physical state of the basic material used for printing. The next part of the thesis presents the possible use of additive manufacturing in the construction industry and an overview of realized projects. Finally, at the end of the theoretical part are introduced materials applicable to additive manufacturing in the construction industry and is defined the concept of spatial materials. Spatial materials are a relatively new term, which is not yet in the literature sufficiently defined. These materials can be used for an application in a space where the structure and the position of their particles can be optimized. They can be applied for the creation of 2D filling structures, which are more useful for geometrically simple and simply loaded constructions. It is preferable to use spatial materials to create 3D structures that are designed to fill numerically optimized structures. These structures are based on the principle of double curvature and on a triply-periodic minimum surface (TPMS). In the practical part of the thesis was created the design of building block filled with 3D gyroid structure, designed for prefabrication by using additive manufacturing in the factory or at the site of construction. This proposal reflects the increasing demand for easy individualization of constructions and building elements. Especially, the demand for the creation of structures and shapes which are topologically optimized with a customized appearance and sufficient strength, all at the customer's request.
|
|
|
Automated design and 3D printing of prototypes for urban engineering
Krutáková, Anna ; Vořechovská, Dita (referee) ; Podroužek, Jan (advisor)
This bachelor thesis deals with automated design and 3D prototype printing for urban engineering. In the first part, there is a general definition of 3D printing, including development and overview of basic technology and materials. It also follows the focus on certain measurement methods and the creation of 3D models. In the second part, the thesis focuses mainly on the use in the building industry and it discusses related topics such as the automatic optimization of the external elements of building elements or objects(shape), the internal topology of these building elements (fill) and the possible inspiration from organic structures. There is also distinguished between terrestrial applications focusing on the production of prefabricated building components and implementation at site. Extraterrestrial autonomous applications discuss the possibilities this technology for colonizing the Moon or Mars. This thesis presents the results of a unique assessment of the current state of the art in the field of applicability of 3D technology for additive production in the context of urban engineering and demonstrates the associated advantages and open problems on many examples. Finally, the benefits of this technology are evaluated.
|
|
|
Train Identification System at Railway Switches And Crossings Using Advanced Machine Learning Methods
Krč, Rostislav ; Vorel,, Jan (referee) ; Plášek, Otto (referee) ; Podroužek, Jan (advisor)
This doctoral thesis elaborates possibilities of automatic train type identification in railway S&C using accelerometer data. Current state-of-the-art was considered, including requirements stated by research projects such as S-Code, In2Track or Turnout 4.0. Conducted experiments considered different architectures of artificial neural networks (ANN) and statistically evaluated multiple use case scenarios. The resulting accuracy reached up to 89.2% for convolutional neural network (CNN), which was selected as a suitable baseline architecture for further experiments. High generalization capability was observed as models trained on data from one location were able to classify locomotive types in the other location. Further experiments evaluated the effect of signal filtering and denoising. Evaluation of allocated memory and processing time for pre-trained models proved feasibility for in-situ application with regard to hardware restrictions. Due to a limited amount of available accelerometer data, distribution grid power demand data were utilized for further refinement of the proposed CNN architecture. Deep multi-layer architecture with regularization techniques such as dropout or batch normalization provides state-of-the-art performance for time series classification problems. Class activation mapping (CAM) allowed an explanation of decisions made by the neural network. Presented results proved that train type identification directly in the S&C is possible. The CNN was selected as optimal architecture for this task due to high classification accuracy, automatic filtration, and pattern recognition capabilities, allowing for the incorporation of the end-to-end learning strategy. Moreover, direct on-site application of pre-trained models is feasible with respect to limitations of in-situ hardware. This thesis contributes to understanding the train type identification problem and provides a solid theoretical background for future research.
|
|
|
RedirFS - Application on Data Compression
Podroužek, Jan ; Čejka, Rudolf (referee) ; Kašpárek, Tomáš (advisor)
This thesis in its first part examines the problems of developing linux kernel modules, specifically modules implementig RedirFS filters. In the next part it considers different types of copression algorithms and the implementation specifics on the CryptoAPI framework in the linux kernel. Finally it describes the design and operation of the CompFLT module that implements a RedirFS compression filter. Benchmarks done using the CompFLT module are presented in the last section.
|
|
|
Technology for 3D printing of prototypes in construction
Čechal, Petr ; Apeltauer, Tomáš (referee) ; Podroužek, Jan (advisor)
Bachelor thesis deals with technology for 3D prototype printing in construction. The theoretical part is mainly focused on 3D technology in construction. It explains the system and the principle of functioning of 3D technologies such as d-shape, contour crafting and concrete printing. It also solves the possibilities of using 3D printing in the concept of smart city or industry 4.0. Here it contributes with its features like speed, low costs, or high form variability. Last part of the theoretical part contains the largest buildings created by these technologies, for example Levis Grand hotel in the Philippines. In the practical part there is demonstrated 3d printing according to project terraperfrom. Terraperfrom is a Spanish company, which focus on printing from natural sources. The robotic hand system is used for printing. According to this project printing head was compiled from PVC pipes and practically tested by extruding layers of cement clay mixture. Two test figures were prepared. These two tests figures were tested on formation of the rifts, density or setting time.
|
|
|
APPLICATION OF MACHINE LEARNING IN CIVIL ENGINEERING
Pálková, Martina ; Hromada, Martin (referee) ; Řehák,, David (referee) ; Podroužek, Jan (advisor)
This thesis deals with the issue of machine learning in modeling of movement of pedestrians, the possibilities of its use and its limitations. The problem is shown on two real examples from practice. Digitization of industry and related use of advanced computing methods, such as artificial intelligence, has undergone unprecedented progress in the last ten years. Nevertheless, the construction industry lags behind other industries. This topic offers a lot of scope for research, the results of which can be very well applied in practice. Machine learning has the potential to be cheap and efficiently process large data sets with high accuracy, almost in real-time. In order for this to be possible, it is necessary to solve questions such as the appropriate choice for the given problem method, its architecture and parameter optimization. Another important direction of research is pre-processing of data, its format and division into training and test sets. This the topic, despite the great progress in the field of machine learning, is still discussed without uniform conclusions. These are the directions in which this work goes.
|
|
|
Train Identification System at Railway Switches And Crossings Using Advanced Machine Learning Methods
Krč, Rostislav ; Vorel,, Jan (referee) ; Plášek, Otto (referee) ; Podroužek, Jan (advisor)
This doctoral thesis elaborates possibilities of automatic train type identification in railway S&C using accelerometer data. Current state-of-the-art was considered, including requirements stated by research projects such as S-Code, In2Track or Turnout 4.0. Conducted experiments considered different architectures of artificial neural networks (ANN) and statistically evaluated multiple use case scenarios. The resulting accuracy reached up to 89.2% for convolutional neural network (CNN), which was selected as a suitable baseline architecture for further experiments. High generalization capability was observed as models trained on data from one location were able to classify locomotive types in the other location. Further experiments evaluated the effect of signal filtering and denoising. Evaluation of allocated memory and processing time for pre-trained models proved feasibility for in-situ application with regard to hardware restrictions. Due to a limited amount of available accelerometer data, distribution grid power demand data were utilized for further refinement of the proposed CNN architecture. Deep multi-layer architecture with regularization techniques such as dropout or batch normalization provides state-of-the-art performance for time series classification problems. Class activation mapping (CAM) allowed an explanation of decisions made by the neural network. Presented results proved that train type identification directly in the S&C is possible. The CNN was selected as optimal architecture for this task due to high classification accuracy, automatic filtration, and pattern recognition capabilities, allowing for the incorporation of the end-to-end learning strategy. Moreover, direct on-site application of pre-trained models is feasible with respect to limitations of in-situ hardware. This thesis contributes to understanding the train type identification problem and provides a solid theoretical background for future research.
|
|
|
Spatial materials for additive manufacturing in civil engineering
Říha, Tomáš ; Apeltauer, Tomáš (referee) ; Podroužek, Jan (advisor)
The bachelor thesis deals with additive manufacturing in the construction industry and with materials used in this field. The first part of the thesis defines the 3D printing, briefly describes the history of this progressive technology and gives an overview of the used methods and technologies. The printing methods are divided according to the physical state of the basic material used for printing. The next part of the thesis presents the possible use of additive manufacturing in the construction industry and an overview of realized projects. Finally, at the end of the theoretical part are introduced materials applicable to additive manufacturing in the construction industry and is defined the concept of spatial materials. Spatial materials are a relatively new term, which is not yet in the literature sufficiently defined. These materials can be used for an application in a space where the structure and the position of their particles can be optimized. They can be applied for the creation of 2D filling structures, which are more useful for geometrically simple and simply loaded constructions. It is preferable to use spatial materials to create 3D structures that are designed to fill numerically optimized structures. These structures are based on the principle of double curvature and on a triply-periodic minimum surface (TPMS). In the practical part of the thesis was created the design of building block filled with 3D gyroid structure, designed for prefabrication by using additive manufacturing in the factory or at the site of construction. This proposal reflects the increasing demand for easy individualization of constructions and building elements. Especially, the demand for the creation of structures and shapes which are topologically optimized with a customized appearance and sufficient strength, all at the customer's request.
|
|
|
Technology for 3D printing of prototypes in construction
Čechal, Petr ; Apeltauer, Tomáš (referee) ; Podroužek, Jan (advisor)
Bachelor thesis deals with technology for 3D prototype printing in construction. The theoretical part is mainly focused on 3D technology in construction. It explains the system and the principle of functioning of 3D technologies such as d-shape, contour crafting and concrete printing. It also solves the possibilities of using 3D printing in the concept of smart city or industry 4.0. Here it contributes with its features like speed, low costs, or high form variability. Last part of the theoretical part contains the largest buildings created by these technologies, for example Levis Grand hotel in the Philippines. In the practical part there is demonstrated 3d printing according to project terraperfrom. Terraperfrom is a Spanish company, which focus on printing from natural sources. The robotic hand system is used for printing. According to this project printing head was compiled from PVC pipes and practically tested by extruding layers of cement clay mixture. Two test figures were prepared. These two tests figures were tested on formation of the rifts, density or setting time.
|
|
|
Automated design and 3D printing of prototypes for urban engineering
Krutáková, Anna ; Vořechovská, Dita (referee) ; Podroužek, Jan (advisor)
This bachelor thesis deals with automated design and 3D prototype printing for urban engineering. In the first part, there is a general definition of 3D printing, including development and overview of basic technology and materials. It also follows the focus on certain measurement methods and the creation of 3D models. In the second part, the thesis focuses mainly on the use in the building industry and it discusses related topics such as the automatic optimization of the external elements of building elements or objects(shape), the internal topology of these building elements (fill) and the possible inspiration from organic structures. There is also distinguished between terrestrial applications focusing on the production of prefabricated building components and implementation at site. Extraterrestrial autonomous applications discuss the possibilities this technology for colonizing the Moon or Mars. This thesis presents the results of a unique assessment of the current state of the art in the field of applicability of 3D technology for additive production in the context of urban engineering and demonstrates the associated advantages and open problems on many examples. Finally, the benefits of this technology are evaluated.
|
guest ::
