This paper addresses the design of an optimally executed proportional-integral-derivative (PID) controller, tailored for the speed regulation of a direct current (DC) motor. To achieve this objective, we present a novel hybrid algorithm, combining the gazelle optimization algorithm (GOA) with the effective simplex search method known as the Nelder-Mead (NM) technique. The fusion of these algorithms yields an innovative hybridized version, striking the balance between exploration and exploitation. The proposed approach, named the gazelle simplex optimizer (GSO), showcases great promise when applied to the task of controlling the speed regulation of a DC motor using the PID controller. To identify the optimal values for PID gains, we harness the power of a novel objective function as well, which guides the GSO in determining the most favorable controller settings. Rigorous comparative simulations are then undertaken, where we pit the GSO against several other algorithms, namely the reptile search algorithm, prairie dog optimization algorithm, weighted mean of vectors optimization, and the original GOA algorithm. These simulations allow us to assess the system’s behavior through various lenses, such as statistical tests, time and frequency domain responses, robustness analysis, and changes in the objective function. The evaluations from these comprehensive tests demonstrate the superiority of the GSO-based PID controlled DC motor speed regulation system. The GSO exhibits better performance than the alternative algorithms, providing solid evidence of its effectiveness. Furthermore, the proposed GSO approach outperforms other reported PID tuning methods, affirming its prowess in achieving superior speed regulation for DC motors.

Ceramic materials are an indispensable part of our lives. Today, ceramic materials are mainly used in construction and kitchenware production. The fact that some deformations cannot be seen with the naked eye in the ceramic industry leads to a loss of time in the detection of deformations in the products. Delays that may occur in the elimination of deformations and in the planning of the production process cause the products with deformation to be excessive, which adversely affects the quality. In this study, a deep learning model based on acoustic noise data and transfer learning techniques was designed to detect cracks in ceramic plates. In order to create a data set, noise curves were obtained by applying the same magnitude impact to the ceramic experiment plates by impact pendulum. For experimental application, ceramic plates with three invisible cracks and one undamaged ceramic plate were used. The deep learning model was trained and tested for crack detection in ceramic plates by the data set obtained from the noise graphs. As a result, 99.50% accuracy was achieved with the deep learning model based on acoustic noise.

Photovoltaic (PV) panels exhibit a non-linear current-voltage characteristic with a Maximum Power Point (MPP) that varies due to environmental factors such as solar radiation and ambient temperature. In this study, an Artificial Neural Network (ANN)-based MPPT method, called the ANN-based Adaptive Reference Voltage (ARV) method, is proposed to determine the optimal operating point of the PV panel. The ANN-based ARV method is a voltage-controlled approach that can adapt to changing atmospheric conditions. The performance of the proposed method is evaluated using both a normal Proportional-Integral (PI) controller and an anti-windup PI controller. Comparative analysis is conducted with the widely used Perturb and Observe (P&O) and Incremental Conductance (INC) methods in the MATLAB/Simulink environment, considering three different atmospheric scenarios with varying radiation levels according to EN50530 standards. The proposed method demonstrates superior efficiency with overall results of 99.4%, 95.9%, and 96% in scenario 1, scenario 2, and scenario 3, respectively. Particularly, the proposed method exhibits notable superiority in rapidly changing atmospheric conditions.

Maximum Power Point Tracking (MPPT) algorithms are crucial for maximizing power extraction from photovoltaic (PV) systems. Traditional MPPT methods often exhibit suboptimal performance under partial shading conditions. Hence, advanced MPPT algorithms have been developed to enhance efficiency in such scenarios. The voltage scanning-based MPPT algorithm is notable for its superior performance under partial shading, characterized by high tracking speed and efficiency. This study introduces a novel enhancement to this method—namely, a voltage skipping algorithm designed to further improve tracking speed. Unlike conventional scanning techniques, this approach dynamically calculates skipping voltages during operation, eliminating the need for prior knowledge of PV panel characteristics. Performance evaluation was conducted using a MATLAB/Simulink model of a PV system comprising 4 series panels and a boost converter, subjected to simulations under 5 distinct partial shading scenarios. Comparative analyses with established optimization algorithms such as particle swarm optimization, cuckoo search algorithm, and grey wolf optimization highlight the proposed method's effectiveness in terms of tracking speed and maximum power output. The proposed algorithm has worked with high efficiency of 99.28 %, 99.61 %, 99.13 %, 99.16 % and 99.58 % in 5 different scenarios, respectively. By using the proposed method, a significant superiority has been achieved over other methods, with tracking speeds of 0.26s, 0.22s, 0.2s, 0.22s and 0.26s, respectively.

Today, as in every life-threatening disease, early diagnosis of brain tumors plays a life-saving role. The brain tumor is formed by the transformation of brain cells from their normal structures into abnormal cell structures. These formed abnormal cells begin to form in masses in the brain regions. Nowadays, many different techniques are employed to detect these tumor masses, and the most common of these techniques is Magnetic Resonance Imaging (MRI). In this study, it is aimed to automatically detect brain tumors with the help of ensemble deep learning architectures (ResNet50, VGG19, InceptionV3 and MobileNet) and Class Activation Maps (CAMs) indicators by employing MRI images. The proposed system was implemented in three stages. In the first stage, it was determined whether there was a tumor in the MR images (Binary Approach). In the second stage, different tumor types (Normal, Glioma Tumor, Meningioma Tumor, Pituitary Tumor) were detected from MR images (Multi-class Approach). In the last stage, CAMs of each tumor group were created as an alternative tool to facilitate the work of specialists in tumor detection. The results showed that the overall accuracy of the binary approach was calculated as 100% on the ResNet50, InceptionV3 and MobileNet architectures, and 99.71% on the VGG19 architecture. Moreover, the accuracy values of 96.45% with ResNet50, 93.40% with VGG19, 85.03% with InceptionV3 and 89.34% with MobileNet architectures were obtained in the multi-class approach.