This master's dissertation consists of 80 pages, 42 figures, 24 tables and 20 sources according to the list of references.
The object of research - the process of automated eddy current testing of metal products. Subject of research - systems of automated eddy current testing for products with complex geometry.
The purpose of the study is to develop a robotic system of eddy-current testing for products with complex geometry of the surface. Methods of research - theoretical studies of the process of eddy current testing and testing object; model experiments on the processing of information signals; modeling the work of individual nodes.
The master's dissertation consists of the introduction and 6 sections, the conclusion and the list of used literature. The full volume is 89 pages, including 41 illustrations, 26 tables and 25 literary sources.
The urgency of this topic is that automation of production simplifies the control process, and also can replace some processes of production. Known foreign work-manipulators have a significant drawback - a high price, and in our country work manipulators of the same type or the same type are not manufactured. Because of this, the automation of domestic production and further control of manufactured products is high value, and not every manufacturer or company can afford to use a robot-manipulator. Therefore, it is proposed to create a robot-manipulator model for the training of specialists who in the future will program such robot manipulators for work. Due to the high price of industrial robot manipulators, their availability in higher education institutions is impossible, therefore, it is proposed to print a design of this similar model using a 3D printer and using as a source of propulsion power and stepper motors.
The master's dissertation contains 82 pages, 27 figures, 27 tables, 18 sources according to the list of references.
The dissertation deals with the issues of control of heat exchangers of steam generators in nuclear power plants. The internal diameter of the heat exchanger tubes is only 16 mm, which necessitates the miniaturization of the sensor and access to the testing object only from inside of tube. The functional scheme and algorithm of work according to system requirements are proposed. The novelty of the work is combining the amplitude and phase methods of signal processing from the eddy current sensor in order to increase the probability of detecting defect signals. Also, the project proposed a sensor for control presented a harvesting drawing. Appropriate simulations have been carried out to confirm the relevance of the proposed processing method, in particular to improve the accuracy of the method using phase processing, which suggests the use of R-statistics.
This master's dissertation consists of 86 pages, 26 figures, 22 tables and 22 sources according to the list of references.
The main technical characteristics of the tractor Joon Deere 8430 are considered in the dissertation. The fuel supply system was analyzed and the cost calculation was done. The scheme of fuel consumption control is proposed. It is proposed to determine the cost by determining the difference between the volume of feed and the volume of fuel return. This scheme is optimal and does not require additional interference with the fuel system. Since the diameter of the fuel supply pipe is only 10 mm, the design of the flow meter was proposed. It is monoblock, that is, piezoelectric converters are mounted in a pipe stationary.
The dissertation has a volume of 80 pages, the main part consists of an introduction, five sections, contains 29 figures, 25 tables, 4 annexes and 13 sources of literature.
The purpose of the research is to investigate the possibility of using the neural networks for decision-making process of mechanical impedance analysis.
The object of the research is the methods of machine learning for detecting flaws by mechanical impedance analysis of composite materials. The subject of the research is the decision-making process based on the analysis of the informational parameters of the mechanical impedance defectoscope transducer.
In the first two sections of the dissertation, an analytical review of existing testing of composites, major flaws in them, and description of existing devices and systems that implement this method are carried out. Also the physical foundations of the mechanical impedance testing method is described.
The following sections reveal the process of forming an array of input data for research, the development and testing of the neural network, and graphs that show the dependencies of errors on the parameters of the neural network. To investigate the ability of the neural network to learn on the data and to further classification of the testing object’s area on the basis of the presence or absence of a defect, the creation and testing of the neural network was carried out using the Keras library based on the Python programming language, which confirmed the expediency of using this method of information processing in the mechanical impedance testing of compositional materials.
The dissertation has a volume of 80 pages, the main part consists of an introduction, five sections, contains 29 figures, 25 tables, 4 annexes and 13 sources of literature.
The purpose of the research is to investigate the possibility of using the neural networks for decision-making process ofmechanical impedance analysis.
The object of the research is the methods of machine learning for detecting flawsbymechanical impedance analysis of composite materials.
The subject of the research is the decision-making process based on the analysis of the informational parameters of the mechanical impedance defectoscope transducer.
In the first two sections of the dissertation, an analytical review of existing testing of composites, major flaws in them, and description of existing devices and systems that implement this method are carried out. Also the physical foundations of the mechanical impedance testing method is described.
The following sections reveal the process of forming an array of input data for research, the development and testing of the neural network, and graphs that show the dependencies of errors on the parameters of the neural network. To investigate the ability of the neural network to learn on the data and to further classification of the testing object’s area on the basis of the presence or absence of a defect, the creation and testing of the neural network was carried out using the Keras library based on the Python programming language, which confirmed the expediency of using this method of information processing in the mechanical impedance testing of compositional materials.
