Tastimur, Canan; Kaya, Volkan

Bearing components are critical elements of rotating machinery, and their failures can lead to sudden shutdowns, reduced efficiency, and increased maintenance costs. To address the limitations of conventional fault diagnosis methods, this study proposes a multimodal deep learning framework that integrates raw time-domain vibration signals with stationary wavelet transform (SWT)-based time-frequency representations using a novel bidirectional cross-attention mechanism. This architecture enables effective and mutual interaction between heterogeneous features, significantly enhancing discriminative representation learning and fault classification performance in complex operating environments. The proposed model was evaluated on the public SUBVF1.0 dataset under three fault conditions, achieving training and validation accuracies of 99.17% and 95.63%, respectively. The model also demonstrated strong performance in terms of precision, recall, F1-score, and ROC analysis. An ablation study further confirms the contribution of each model component. These results indicate that the proposed approach is accurate, robust, and suitable for practical industrial fault diagnosis applications.

Ting, Naim Suleyman; Ipek, Asli Seyda

Recent progress in DC microgrids necessitates high gain DC-DC converters for effective energy conversion. In this regard, this paper introduces a new high gain single-switch quadratic boost converter (HGS2QBC). This converter, comprising a switch, two inductors, four capacitors, and five diodes, incorporates a voltage multiplier cell (VMC) that provides an 8-times voltage gain at a 0.5 duty cycle. The salient features of the proposed converter are its high voltage gain, having only one switch, low voltage stress across semiconductor devices, and non-pulsating input source current. In addition to its high voltage gain, one of the most significant added-value features of the proposed converter is the presence of a single switch in its structure and the fact that the voltage stress on this switch is half of the output voltage. Furthermore, a 100 W, 200 V, and 20 kHz laboratory prototype is constructed to assess practical viability, and the related experimental results are provided. Experimental analysis confirms the converter's effectiveness in managing voltage and current waveforms across its components, reducing stress on the semiconductor elements and minimizing voltage levels across the diodes. Such design optimizations not only provide superior performance but also offer cost advantages that make the converter economically viable.

Can, Erol; Kürşat Demirci, Oğuz

Battery charging and regulation for the electrical system of electric cars or fuel cars are of great importance for the efficient operation and comfort of the vehicles. In this study, a DC-DC boost converter system that can charge two batteries isolated from each other with the same dynamo for a car is presented. With this system, it is possible to charge two different batteries at their nominal voltages at the same time by increasing the voltage of the system at the low voltage inputs that will occur. First, the circuit model and mathematical expansions that give the operating logic of the circuit are given. Then, the designed circuit model is operated between the modulation indexes of 0.2-0.5 and two different batteries are fed at their nominal voltages in isolation from each other. After the simulation studies, the current and voltage values of the circuit elements and the charging parameters of the battery are measured and the system application is carried out. According to the obtained results, although the charging circuit receives low voltage from the alternator, the two batteries can be charged to the requested level with the proposed system.

Orman, Kamil

In this study, a memristor-based sliding mode controller (Mem-SMC) was designed for speed control of BLDC motor and the performance of the controller was tested in simulation. The sliding mode controller, known for its robustness against disturbances and parameter variations, was designed with a memristor known as a missing circuit element. Simulation results show that the proposed controller is successful in the speed reference tracking and is also able to respond quickly to sudden changes in the reference.

Ciflikli, Cebrail; Ilgin, FatihYavuz

The eigenvalue based spectrum sensing is a low-cost spectrum sensing method that detects the presence of the licensed user signal in desired frequency. Traditional single-threshold eigenvalue sensing methods, which are widely used in the literature, can exhibit inadequate performance under low SNR and noise uncertainty. Therefore, in this study an eigenvalue-based spectrum sensing method is proposed using a double threshold with the studentized extreme eigenvalue distribution function. The results that threshold values obtained for the proposed method were simulated in Rayleigh fading channels. The results were compared with traditional methods and they were observed to be more accurate.

Can, Erol

In energy conversion studies, some situations have been aimed at up to now. According to this, while the direct voltage is converted from some renewable energy sources to the alternating voltage, the shape of the voltage must be close to the sinus. Therefore, the works are being done on inverters with multi-levels. As the level of the inverters increases, the number of switches and control signals on them increases and it becomes harder to find the possible errors. Finding faults of a device with a large number of transistors with control signals is important, very difficult, and time-consuming task. This paper addresses the issue of determining fault conditions for a multi-level inverter with a very complex switching scheme. The results are analyzed and evaluated after the values obtained in the simulation are validated by the experimental study. For different switch fault conditions at the applications, the harmonic distortion of the alternating voltage is measured and made into tables. After that, different fault conditions of the 21-level inverter structure are explained when fault curves are created from the distortion value of the fault signals.

Çiflikli, Cebrail; Ilgin, Fatih Yavuz

The eigenvalue based detection is a low-cost spectrum sensing method that detects the presence of primary user signal at a desired frequency. In this study, the largest eigenvalue distribution used in eigenvalue based detection methods is expressed using a new centering and scaling coefficients adjustment. Thus, the detection probability (Pd) and false detection probability (Pfa) equations for the maximum-minimum eigenvalue (MME), maximum eigenvalue to trace (MET) and maximum eigenvalue-geometric mean (ME-GM) have been obtained again. Weibull fading channels are the best model for wireless communication. For this reason, the studies were simulated in Weibull fading channels and analysed in detail with receiver operating characteristic curves (ROC). The results were compared with traditional methods and found to be more accurate.

Can, Erol

In this study, the quality of the transformed energy form is analysed after comparing the single-phase induction motor operated by the SPWM inverter to the 15-level LPWM inverter. Firstly, multilevel inverter and pulse width modulation are designed. The multi-level inverter has sixteen IGBT switches because inverter circuit is constructed with high multilevel inverter topology. Linear pulse width modulation (LPWM) is designed for operation of sixteen switches in the inverter circuit. Secondly, equations of the induction motor are calculated according to d-q axis with creating 15-level alternating voltage. After described equations, 15-level inverter running single phase induction motor is formed at the Matlab Simulink. The obtained results are analyzed according to motor performance and harmonic distortion of the created alternating energy after the proposed model is simulated. Finally, Simulation results of the proposed system are compared with simulation results of SPWM inverter controlling the single-phase induction motor.

Can, Erol; Sayan, H. Hüseyin

Step sinus pulse width modulation (SSPWM) multilevel inverter is designed in order to control loads with reducing nonlinear effects as harmonics. Multilevel inverter has six switches for every phase and the switches are connected to control inputs and outputs of load. This method focuses on the identification of twelve IGBT and six MOSFET switches as nonlinear device, which consists of only the active and passive switches in three phase multilevel inverter. Inverter switches operate with pulse width modulation after signals of six step sinus compare with 2- small triangle signals for every phase. While operating characteristics of the switches are determined, a mathematical model of inverter controlling loads can be formed. After that, two PWM techniques are used to investigate the non-linear effects on this circuit model which contains mixed switches in its structure. So, the inverter load of ohmic (R) and inductive (L) are performed at the simulation so that performance of SSPWM multilevel inverter could be showed on loads. So, SSPWM and SPWM controlling inverter is tested on frequencies and modulation indexes. Then, performances of SPWM inverter and SSPWM multilevel inverter running loads are compared with output results.

Can, Erol; Sayan, H. Hüseyin

In this study, a three-phase asynchronous motor driven by a broad-based system is described. So, mathematical model of converter, sinus pulse width modulation for the three phase inverter, and mathematical model of three-phase asynchronous motor have to be utilized in order to establish the system. After creating such a system, Fuzzy Logic and PID controllers are focused in order to get satisfactory results which are short settling time of rotor speed, low harmonic and short settling time of high phase current. Created mathematical models are run at the MATLAB Simulink. Direct voltage is applied to converter input. This voltage is represented by a renewable energy source that could be obtained from solar energy source. The direct voltage is lower than the peak of the alternating voltage. The alternating voltage is obtained from output of the inverter to drive the induction motor. Firstly, resistive (R) and inductive (L) loads are driven. Secondly, three-phase asynchronous motor (ASM) is driven with the low direct voltage. After that, simulation results are given in order to demonstrate performance and effectiveness of the proposed system.