Machines. Technologies. Materials.
Vol. 17 (2023), Issue 4

Table of Contents

  • MACHINES

  • TECHNOLOGIES

    • Possibilities of using an autoencoder network in the failure state recognition

      pg(s) 141-144

      Approaches to machine and equipment maintenance based on data analytics and artificial intelligence are trending in modern manufacturing. These methods are used to predict the remaining useful life (RUL) of equipment and thus enable forward maintenance planning. However, for predictive maintenance systems, it is also necessary to detect anomalies in operation and classify the occurring errors. Classical approaches of supervised machine learning are often in this case unusable because those methods require a large amount of run-to-failure data (R2F), which is often not possible to collect due to the undesirable character of failure states in the manufacturing process. The paper presents and tests several methods of detecting device fault states using an autoencoder network, which offers a beneficial solution in the case of the unavailability of R2F data in the system.

    • Βasic principles of metal processing using LASERS

      pg(s) 145-147

      This paper analyzes the basic definition of light in physics, the mechanics of how it is transmitted through space, as well as how much energy it can convey, what are the laws that allow but at the same time limit its exploitation by modern engineering. Also, quantum mechanics basic principles are being presented along with definitions, such as stimulated emission of radiation, abstraction, stimulating energy sources, optical resonators, lasing mediums, and excitation systems.

    • Tool Wear Detection in Milling Process Using Long Short-Term Memory Networks: An Industry 4.0 Approach

      pg(s) 148-151

      Industry 4.0 and the rise of predictive maintenance have led to increased interest in developing efficient and accurate methods for detecting tool wear in manufacturing processes. In this work, we investigate the use of machine learning techniques, specifically Long Short- Term Memory (LSTM) networks, for the detection of tool wear using NASA Milling Data Set. We first preprocess the raw milling data and extract relevant features using signal processing techniques. Then, we train and evaluate the performance of the LSTM network for detecting tool wear in the milling process. Our results demonstrate the effectiveness of the LSTM network for detecting tool wear, achieving high accuracy and recall scores. Additionally, we compare our results to those obtained using traditional statistical process control methods and highlight the advantages of using machine learning techniques for tool wear detection in the context of Industry 4.0 and predictive maintenance. Our work provides a practical example of how machine learning techniques can be applied to manufacturing processes to improve efficiency and reduce downtime.

    • Elementary electron extraction from devices using galvanic corrosion

      pg(s) 152-154

      Galvanic corrosion is a well-known phenomenon, which occurs when two different metals exposed to the same conditions exhibit differential corrosion rates. The corrosion process is accelerated by the exchange electrons between the metals. In this study, we created a novel layered structure of Cu and Al for efficient electron extraction through charge transfer. Using this Cu/Al laminated structure configuration and galvanic corrosion effect, an open-circuit voltage of approximately −160 mV was generated by measuring the difference in potential between the metal and a useful indicator of the electrochemical dynamics of the system. Furthermore, we effectively transmitted electrons between the metal in the layered structure, as demonstrated by the extraction of a charge of approximately 10−5 C. These results show the potential of using a laminated structure to take advantage of galvanic corrosion as energy generation and electrochemical sensing.

    • Study of the properties of the metal surface after pre-treatment by phosphating

      pg(s) 155-157

      The contribution is focused on the analysis of the roughness of metal surfaces after applying a conversion layer using phosphating. The types of basic materials is used in the experiment hot-dip galvanized microalloyed steel HX340LAD+Z. During the application of the conversion layer, changes in surface roughness were studied with respect to the phosphating time, which was 3, 5 and 10 minutes. The paper deals with the evaluation of the relationship between the individual roughnesses parameters of pre-treated surfaces using correlation analysis. Based on the measured roughness values on the surfaces, the standard of statistical significance of the correlation between the observed parameters was determined from them. The achieved results provide information for other technological operations such as the creation of adhesive joints, where the correct anchoring of the adhesive is important for load bearing capacity of joints.

    • Analysis of the possibilities of joining thin-walled metallic and composite materials

      pg(s) 158-163

      This paper presents an overview of technologies for joining fibre-reinforced polymer composites to thin-walled metal sheets. It covers the areas of welding, bonding with different surface texturing as well as mechanical joining. It analyses the problems arising from the different mechanical, physical properties of metals and composite materials and presents the possibilities of solving them by the application of individual and combined joining technologies.

  • MATERIALS

    • Investigation of the influence of deformation temperature on the radial shear rolling mill on the microstructure evolution of copper

      pg(s) 164-166

      One of the effective ways to control the properties of copper is to refine its structure to a nano- or ultrafine-grained level, and primarily with the help of severe plastic deformation. At the same time, radial-shear rolling is one of the promising methods for obtaining long-length rods with a gradient ultra-fine-grained structure. It is known from a number of scientific works that one of the main factors influencing the possibility of obtaining an ultrafine-grained structure in various ferrous and non-ferrous metals and alloys is the deformation temperature of these metals and alloys. The aim of the work is to study the influence of the deformation temperature at the radial-shear rolling mill on the microstructure evolution of copper. The following deformation temperatures of copper rods were selected for the planned studies: 20°C, 100°C and 200°C. The conducted studies have shown that the implementation of radial-shear rolling at ambient temperature compared with rolling at temperatures of 100°C and 200°C made it possible to achieve more intensive refinement of the initial structure. And first of all, this is due to the fact that with radial-shear rolling of copper, realized at ambient temperature, there are no dynamic return processes.

    • Investigation of an appropriate marl raw material for the production of innovative ceramic beehives

      pg(s) 167-170

      An observation of the current state of the beekeeping industry and the prevailing main problems was carried out. The prospects for increasing the efficiency and functional capabilities of the bee farms were analyzed. According to the long-term research activity, a technological regulation was contrived for producing innovative ceramic hives. The development is superior to the existing standard beehives made of other materials, in terms of complex operational indicators. The phase composition and technical characteristics of obtained samples of marl raw material (from Bulgarian deposits) were investigated, potentially applicable for the production of various
      modifications of ceramic collapsible hives.