International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

The importance of artificial lighting in our daily lives is growing, and street lighting has become a major focus over time. The creation of street lighting was motivated by the need to increase visual and property security and public safety. Current developments in metropolitan environments foreshadow the ‘smart cities’ of the future. The basic concept is that CCTV cameras, traffic lights and street lighting all have ‘smart functions’. Municipalities will be able to adapt to the needs of their inhabitants, thus increasing safety, comfort and energy efficiency. Given the adaptability of smart street lighting to the built environment, artificial intelligence is an essential element of smart cities, even in the systems already in place. Extensive sensor networks will facilitate the collection of environmental data by AI. In addition, unauthorised access to information available through IoT systems poses a serious threat. A critical point is the monitoring and protection of surveillance systems that are vital to the operation of smart systems.

The utilization of robotic systems is prevalent in various industries, such as defence and automotive, and is commonly utilized in industrial settings. The movements of these systems can be controlled through software programming, allowing for the manipulation of objects and modification of trajectory as desired. However, it is important to exercise caution during these operations as improper manipulation may result in undesired outcomes. As a result, the control of robotic systems has become a crucial aspect in modern industry.
The parameters of robotic systems are subject to change based on the loads they carry. Robust control is a method that adapts the control system to accommodate these changes in parameters, thereby maintaining stability and performance. This control method allows for the desired level of control to be maintained even in the presence of changing system parameters. In contrast to traditional robust control methods, robust control utilizes variable parameters with a constant upper limit for parameter uncertainty. Control parameters are updated over time using cosine and sine functions, however, determining appropriate values for these parameters can be challenging. To address this issue, a neural network model utilizing fuzzy logic compensator is employed to continuously calculate the appropriate control parameter values. The effectiveness of this proposed control method is demonstrated through graphical representation.

A prototype of a system for segmenting images of trains and wagons has been developed. Video cameras and specialized websites are used as the source of the original images. Median filtering of images and increase of their local contrast is carried out. The contours of the objects were calculated using the Sobel and Canny methods. Image segmentation is performed by the method of contour lines. As a result of the processing on the images of trains and wagons, meaningful areas (segments) were identified, for example, windows, headlights, etc. Detection of content areas of the object is performed using fuzzy membership functions. The hardware and software implementation of the computer system is made in Python using scipy and scikit-fuzzy libraries, the Google Colab cloud platform and Raspberry Pi 3B+ microcomputer.

Generally, passenger ride comfort can be interpreted as an attenuation of sprung mass acceleration or as peak minimization of sprung mass vertical displacement, while good handling can be characterized as an attenuation of unsprung mass acceleration. This effort devoted to passive suspension design is ineffective because improvements to ride comfort are achieved at the expense of handling and vice versa. Instead, the best result can be achieved by active suspension, i.e. when an additional force can act on the system and simultaneously improve both of these conflicting requirements. Another important goal of the control design is to maintain robustness of the closed loop system. In the paper, fuzzy logic is used to simulate active suspension control of a one-half-car model. Velocity and acceleration of the front and rear wheels and undercarriage velocity above the wheels are taken as input data of the fuzzy logic controller. Active forces improving vehicle driving, ride comfort, and handling properties are considered to be the controlled actuator outputs. The controller design is proposed to minimize chassis and wheels deflection when uneven road surfaces, pavement points, etc. are acting on tires of running cars. As a result, a comparison of an active suspension fuzzy control and a spring/damper passive suspension is shown using MATLAB simulations.

Machine learning has been used in many disciplines to reveal important patterns in data. One of the research disciplines that benefits from using these methods is eco-informatics. This branch of applied computer science to solve environmental problems uses computer algorithms to discover the impact of the environmental stress factors on the organisms’ abundance. Decision tree type of machine learning methods are particularly interesting for the computer scientists as well as ecologists, because they provide very easy interpretable structure without any practical knowledge in mathematics or the inner working of the algorithm. These methods do not rely only on classical sets, but many of them are using fuzzy set theory to overcome some problems like overfitting, robustness to data change and improved prediction accuracy. In this direction, this paper aims to discover the influence of one particular environmental stress factor (Saturated Oxygen) on real measured data containing information about the diatoms’ abundance in Lake Prespa, Macedonia, using weighted pattern tree (WPT) algorithm. WPT is a decision tree method variant that combines fuzzy set theory concepts, like similarity metrics, fuzzy membership functions and aggregation operators, to achieve better prediction accuracy, improve interpretability and increase the resistance to overfitting compared to the classical decision trees. In this study, we use Algebraic operators for aggregation. One WPT model is presented in this paper to relate the saturated oxygen parameter with the diatoms’ abundance and reveal which diatoms can be used to indicate certain water quality class (WQC). The obtained results are verified with the existing knowledge found in literature.

Protein classification is among the main themes in bioinformatics, for the reason that it helps understand the protein molecules. By classifying the protein structures, the evolutionary relations between them can be discovered. The knowledge for protein structures and the functions that they might have could be used to regulate the processes in organisms, which is made by developing medications for different diseases. In the literature, plethora of methods for protein classification are offered, including manual, automatic or semiautomatic methods. The manual methods are considered as precise, but their main problem is that they are time consuming, hence by using them a large number of protein structures stay uncategorized. Therefore, the researchers intensively work on developing methods that would afford classification of protein structures in automatic way with acceptable precision. In this paper, we propose an approach for classifying protein structures. Our protein voxel-based descriptor is used to describe the features of protein structures. For classification of unclassified protein structures, we use a k nearest neighbors classifier based on fuzzy logic. For evaluation, we use knowledge for the classification of protein structures in the SCOP database. We provide some results from the evaluation of our approach. The results show that the proposed approach provide accurate classification of protein structures with reasonable speed.

In the paper, fuzzy logic is used to simulate active suspension control of a one-half-car model. Velocity and acceleration of the front and rear wheels and undercarriage velocity above the wheels are taken as input data of the fuzzy logic controller. Active forces improving vehicle driving, ride comfort and handling properties are considered to be the controller outputs. The controller design is proposed to minimize chassis and wheels deflection (sky-hook concept) when uneven road surfaces, pavement points, etc. are acting on tires of the running car. As a result, a comparison of an active suspension fuzzy control and a spring/damper passive suspension is shown using MATLAB simulations.

The paper deals with a variable multifunctional simulation tool that enables to design and assemble animated models of various technological processes controlled by externally connected fuzzy logic unit. It enables to verify the correctness of fuzzy controller settings in the future control of real technological processes in practice. This tool represents an effective, innovative, and creative concept important to understanding control approach of technological processes modeling as an insight to behavior of real industrial processes and their control which is based on fuzzy logic. On the base of this animated simulation, real technological processes control can be realized successfully according to producer demands afterwards. Models of technological processes assembled by this simulation tool can be then externally controlled by various control strategies (traditional PID controllers, ON-OFF controllers,PLC controllers, fuzzy logic controllers etc.) via a proper real controller connected to the computer. In the paper, two-conveyor-belt system for product packing is shown. The goal consists in control of synchronization of products and boxes placed on individual conveyor belts in order to pack the product into the box. The main concern here is to improve dynamic performance and control efficiency with the help of assembling an animated model of the controlled technological process and its external control by a fuzzy logic unit.

In this paper a fuzzy logic proportional derivative controller is proposed for suppressing vertical vibrations of vehicles. Initially quarter vehicle model is presented. Afterwards fuzzy proportional derivative approach is described in order to minimize vertical displacement of vehicle body. The proposed controller is applied to quarter vehicle model to demonstrate and evaluate performance of the controller. Time responses of vehicle body displacement, acceleration and suspension deflection are compared between controlled and uncontrolled cases. The proposed controller exhibits promising behavior.

In this study, microbial fuel cell’s energy conversion performance experimentally investigated from the chemical energy of the organic waste to electrical energy by means of microorganisms. Microbial fuel cell (MFC) consists of two cells which has 15x15x15 cm³ volume. One part of the cell conserves the mud (anode) the other part conserves the water (cathode). The membrane of the microbial fuel cell has 8×8 cm² area. Two different samples were used in the experiments which are active and settlement mud. The power, volt and current values of the active and settlement mud for different temperature, resistance and bubble were determined. The temperature values consist of ΔT = 8°C, ΔT = 10°C, ΔT = 12°C, ΔT = 14°C. ΔT=Tenvironment- Tmud. For every ΔT value 2 different bubble values were examined (High=21,5 g/h, low=3,5 g/h). For every bubble effect 7 different resistance values were determined (1. Resistance= 3,75 Ω; 2. Resistance =7,5 Ω; 3. Resistance =10,5; 4. Resistance = 14,5 Ω; 5. Resistance = 16 Ω; 6. Resistance = 19 Ω; 7. Resistance = 21,5 Ω) and the performance of the 8×8 cm2 membrane of the MFC is detected. As a result; with the increase of the temperature, resistance and bubble effect the voltage production increases and correspondingly the current decreases. When all the experimental results are evaluated,the highest voltage production (687 mV) occurred at ΔT = 14°C and 21,5 Ω with the high bubble effect in the settlement mud. Also, in this study, MFCs performances in terms of voltage, current, temperature, power was modeled with Rule-Based Mamdani-Type Fuzzy (RBMTF) modeling technique. Input parameters ΔT and time; output parameter power was described by RBMTF if-the rules. 1792 experimental data sets, which obtained for power according to ΔT and time, were used in the training step. The comparison between experimental data and RBMTF is done by using coefficient of multiple determination (R2). The actual values and RBMTF results indicated that RBMTF can be successfully used in MFC.