The aim of this study was to develop a physical activity advisory system supporting the correct implementation of sport exercises using inertial sensors and machine learning algorithms. Specifically, three mobile sensors (tags), six stationary anchors and a system-controlling server (gateway) were employed for 15 scenarios of the series of subsequent activities, namely squats, pull-ups and dips. The proposed solution consists of two modules: an activity recognition module (ARM) and a repetition-counting module (RCM). The former is responsible for extracting the series of subsequent activities (so-called scenario), and the latter determines the number of repetitions of a given activity in a single series. Data used in this study contained 488 three defined sport activity occurrences. Data processing was conducted to enhance performance, including an overlapping and non-overlapping window, raw and normalized data, a convolutional neural network (CNN) with an additional post-processing block (PPB) and repetition counting. The developed system achieved satisfactory accuracy: CNN + PPB: non-overlapping window and raw data, 0.88; non-overlapping window and normalized data, 0.78; overlapping window and raw data, 0.92; overlapping window and normalized data, 0.87. For repetition counting, the achieved accuracies were 0.93 and 0.97 within an error of ±1 and ±2 repetitions, respectively. The archived results indicate that the proposed system could be a helpful tool to support the correct implementation of sport exercises and could be successfully implemented in further work in the form of web application detecting the user’s sport activity.

This paper presents a new approach to the structural integration of piezoceramics into thin-walled steel components for condition-monitoring applications. The procedure for integrating the sensors into metal components is described, and their functionality is experimentally examined with a 2 mm-thick steel sheet. The signal quality of the produced sensors is investigated in a frequency range from 100 Hz to 50,000 Hz and is compared with the results of piezo patches and strain gauges under the same conditions. The results show that due to a higher signal-to-noise ratio and a better coherence, the structurally integrated piezoceramics and the piezo patches are more qualified sensors for vibration measurement in the examined frequency range than the strain gauges. The measurements also indicate that the patches provide higher amplitudes for the frequency range up to 20 kHz. Beyond that, up to 40 kHz, the integrated sensors supplied higher amplitudes. The better signal quality in different frequency ranges as well as the different manufacturing and application methods can be interpreted as an advantage or disadvantage depending on the boundary conditions of the condition-monitoring system. In summary, structural integrated piezoceramics extend the options of monitoring technology.

In contrast to other cutting processes, adiabatic blanking typically features high blanking velocities (>3 m/s), which can lead to the formation of adiabatic shear bands in the blanking surface. The produced surfaces have excellent properties, such as high hardness, low roll-over, and low roughness. However, details about the qualitative and quantitative influence of significant process parameters on the quality of the blanked surface are still lacking. In the presented study, a variable tool is used for a systematic investigation of different process parameters and their influences on the blanked surface of a hardened 22MnB5 steel. Different relative clearances (1.67% to 16.67%), velocities (7 to 12.5 m/s), and impact energies (250 J to 1000 J) were studied in detail. It is demonstrated that a relative clearance of ≤6.67% and an impact velocity of ≥7 m/s lead to adiabatic shear band formation, regardless of the impact energy. Further, an initiated shear band results in the formation of an S-shaped surface. Unexpectedly, a low impact energy results in the highest geometric accuracy. The influence of the clearance, the velocity, and the impact energy on the evolution of adiabatic shear band formation is shown for the first time. The gained knowledge can enable a functionalization of the blanked surfaces in the future.

The paper presents research on increasing the efficiency of industrial centrifugal fans, which are the third highest energy-consuming group of devices. This problem is related to the frequent incompatibility of the fan characteristics with the flow conditions of the installation in which they are operated, which lowers efficiency and increases energy consumption. By ensuring high efficiency of these devices, it is possible to significantly reduce the operating costs of such industrial equipment. For this purpose, a unique concept of regulating the flow parameters of centrifugal fans was developed. The scientific basis of this idea is that a relatively small change in the impeller diameter of the fan significantly affects the flow rate and the pressure rise of the fan. Therefore, the idea uses variable length of the impeller blades by dividing them into a fixed and a movable part. It enables adjustment of the length of the blades, which allows extension of the range of effective and efficient operating parameters. On this basis, several technical solutions of the regulation system were developed, which were then tested using simulation and analytical methods. Two material options for the moving part of the blade have also been developed, one made of metallic materials (high-strength steel and aluminum) and the other made of composite materials. The research showed a significant influence of the mass of the movable part of the blade on the load of the control system. Therefore, ultra-light material variants were used for the impeller blades. The flow simulation tests of the new method of adjusting the fan flow parameters confirmed the effectiveness of this solution. As a result, a wider range of highly efficient centrifugal fans equipped with such a control system was obtained.

Perfectly coated surfaces are an essential quality feature in the automotive and consumer goods industries. They are the result of an optimized, controlled coating process. Because entire assemblies could be rejected if Out-of-Specification (OOS) parts are installed, this has a severe economic impact. This paper presents a novel, line-integrated multi-camera system with intelligent algorithms for anomaly detection on small KTL-coated aluminum parts. The system also aims to automatize the previously used human inspection to a sophisticated and automated vision system that efficiently detects defects and anomalies on coated parts.