مدرس سرور مؤيد داوود الصالح

Due to the applied load torque variations, the electric Direct Current (DC) motors' speed has many more fluctuations. The main objective of this research is to study the speed control of Brushless DC Motors (BLDCMs) using a Proportional Integral Derivative (PID) controller that regulates the motor voltage. This controller was automatically tuned using the Transit Search Algorithm (TSA). The effects of the proposed controller on BLDCM speed control were studied, analyzed, and compared with those of other PID gain calculation methods like Particle Swarm Optimization (PSO), Adaptive Tabu Search (ATS), Genetic Algorithm (GA), Rime-inspired metaheuristic (RIME) and Whale Optimization Algorithm (WOA). The performance is evaluated by contrasting speed-response characteristics such as Settling Time (ST), Rise Time (RT), and Percentage Overshoot (P.O.%). Different objective functions, such as the Integral Absolute Error (IAE), Integral Squared Error (ISE), Integral Time Absolute Error (ITAE), and Mean Squared Error (MSE), are used with TSA to determine the best PID gain parameters for controlling the BLDCM using each objective function separately. The main novelty of this work lies in the integration of fusion-based execution criteria with the TSA's effective search ability to achieve high-quality, superior, and robust PID gains for the BLDCM speed control process. The performance of the PID-TSA for controlling the speed of the BLDCM surpasses that of other controllers by optimizing its control and confirming the superiority of the proposed system under different applied load conditions. The proposed controller uses a fusion objective function (FOF) to achieve a fast response with zero P.O.%, ST equal to 0.027 s, and a RT reach to 0.01 s using single run, in addition, average with standard deviation values of (RT = 3.96414E-05 ± 2.85417E-05 s and ST = 0.002346233 ± 0.000439398 s) for 30 runs.

Hepatitis C Virus (HCV) is a disease that infects the liver with multiple stages that spread through blood, requiring blood tests and body symptoms for diagnosis. The diagnosis should decide which stage the patient reaches. This work suggests a hybrid classification method based on optimization and machine learning techniques. A Long Short-Term Memory Neural Network (LSTM) is used as a classifier to identify the stages of the disease, based on the four stages, using 28 features comprising body symptoms and blood tests. To find the optimal number of hidden cells in the hidden layers of LSTM, the Transit Search Algorithm (TSA) is used, TSA identifies the best integer value for the number of hidden cells and selects the best features combined with this number of cells that will give the highest accuracy of classification. The preprocessing step is required to enhance the quality of the dataset and resizing it. In multiclass classification, a large dataset is essential for the network to learn effectively through all classes. To achieve this, Synthetic Minority Oversampling Techniques (SMOTE) is used to generate similar data that will increase the size of the dataset. The proposed TSA-LSTM method achieves high performance, with classification accuracy exceeding 99% outperforming previous works.

Early detection of breast cancer significantly improves patient outcomes through timely and accurate diagnosis. This study proposes a hybrid image reconstruction method combining the Maximum Likelihood Expectation Maximization (MLEM) algorithm with the Distance Driven Method (DDM) for stationary digital breast tomosynthesis, aimed at producing high-resolution three-dimensional (3D) breast images. The method was initially validated using simulated projection data of a digital breast phantom modeled with two spheres of varying radii and attenuation coefficients. Fifteen projection images were generated over a 15° angular range (from +7° to –7° with 1° increments) to replicate realistic tomosynthesis acquisition. The focus plane was set 45 mm above the detector with a pixel size of 0.14 mm. Reconstruction results demonstrated enhanced image quality, with spatial resolution quantitatively evaluated using the Line Spread Function (LSF) across the smaller sphere. Compared to the Ray Driven Method (RDM), the MLEM-DDM approach provided better contrast, sharper edges, and fewer artifacts.

The Heating, Ventilation, Air Conditioning, and Refrigeration (HVAC&R) system is a complex, nonlinear behavior with a high uncertainty control system that equips the thermal comfort desired but consumes significant electrical energy and costs in different types of buildings, such as residential, commercial, and industrial. This paper introduces a new approach for online controlling of HVAC&R systems using model-based reinforcement learning (MB-RL) style to diminish energy usage and energy cost, maintain the occupants’ comfort levels by controlling the buildings’ indoor temperature, and maintain the desired carbon dioxide levels simultaneously. For this purpose, a new model based on energy and mass conservation laws is presented to model the dynamic variations of temperature and CO2 concentration levels. The HVAC&R system control trouble is defined as a specific Markov Decision Processes (MDPs) model. The reward function balances the ability to increase energy conservation while preserving the interior comfort requirements of occupants. Employing the deterministic policy algorithm (DP), the proposed methodology can manage the dimensionality curse problem due to increased state-action space. Then, it overcomes the nonlinearity and the control system uncertainty. The MB-RL algorithm, which uses a unique DP called DP-MB-RL, can select the best decisions instead of stochastic policy to reduce the calculation time. A real case, a building in Basra City, Iraq, is simulated using MATLAB software. Devoting the MB-RL and DP-MB-RL techniques to online control of an HVAC&R system, the simulation results for both methods are provided. For instance, the parameters, like electrical power, internal comfort levels, energy consumed, and energy cost at different pricing schemes, such as fixed pricing (FP), timeofuse (TOU), and real-time pricing (RTP), are assessed. The results indicated that the suggested DP-MB-RL methodology had better indoor thermal and air quality satisfaction levels, energy-saving (more than 15%), and reduced the cost of electricity by more than 15%, 13%, and 10% for FP, TOU, and RTP pricing schemes, respectively, compared to the benchmark MB-RL style controller. The DP-MB-RL controller also performed better than the Takagi-Sugeno Fuzzy (TSF) controller for the same building, saving more than 21% energy. © 2025, Tikrit University. All rights reserved.

Stroke is a sudden-onset and life-threatening medical condition, consistently ranked among the leading causes of mortality worldwide. Early detection is critical for reducing fatal outcomes, enabling timely medical intervention, and improving patient prognosis. This study presents a cost-effective, accessible, and non-invasive stroke prediction application designed to operate without the need for specialized diagnostic procedures, making it particularly valuable in resource-constrained settings. Several Machine Learning (ML) algorithms were systematically evaluated to identify the most effective predictive model. The Ensemble Learner (EL) demonstrated the highest performance, achieving a classification accuracy of 96.7%, thereby outperforming widely adopted models such as Random Forest (RF), which exhibited marginally lower accuracy. The predictive model was trained on a dataset containing general health-related features that are easily obtainable without frequent medical checkups, ensuring high applicability for large-scale use. To address the class imbalance challenge, the Synthetic Minority Oversampling Technique (SMOTE) was applied, significantly enhancing the model’s robustness and prediction reliability. Upon execution, the application issues an immediate risk alert when a high probability of stroke is detected, prompting users to seek urgent medical evaluation. This work offers a scalable and practical solution that integrates high predictive accuracy with broad accessibility, holding strong potential to reduce stroke-related morbidity and mortality through proactive early detection.

This paper presents Model-based Reinforcement Learning (MB-RL) techniques to control the indoor air temperature, and CO2 concentration level, and minimize the energy consumption of the heating, ventilating, and air conditioning (HVAC) systems, simultaneously. For this purpose, a trade-off is made between maintaining indoor comfort levels and minimizing energy consumption. The control of the HVAC system is performed using the Deterministic Policy RL (DP-RL) method. Moreover, the nonlinear autoregressive exogenous neural network (NARX-NN) is employed as an approximation function with DP-RL method to provide a hybrid DP-NARX-RL controller. By applying the DP-RL and DP-NARX-RL controllers to the HVAC system of a typical building, parameters such as the indoor comfort levels, the electrical power, and energy consumed, and the energy costs at various pricing schemes are evaluated for two case studies. In both cases, the results show the better performance of DP-NARX-RL compared to DP-RL, RL, and PID controllers.

Improving the air quality and preserving the residents’ comfort are the main tasks of HVAC (heating, ventilation, and air conditioning) systems in different buildings. A large number of control methods have been applied to HVAC systems to adjust the indoor temperature of buildings and at the same time to minimize the energy consumption and the energy cost, to reduce the peak load of the grid, and to provide ancillary services such as frequency regulation. This paper reviews different techniques proposed for HVAC systems modeling. Then, the HVAC system control methods are reviewed comprehensively and the main features of them are extracted. Furthermore, an HVAC system model is proposed and the performance of it is compared with the RLF (residential load factor) model with and without applying the Takagi-Sugeno Fuzzy (TSF) controller. The simulation results are obtained and analyzed for the proposed HVAC system and the RLF model from different aspects. The results demonstrate the efficiency and robustness of the proposed model. Moreover, the energy consumption of an HVAC system, controlled by a TSF controller, along a day is evaluated. The results show an energy saving of 10.06% of the proposed HVAC system as compared with the RLF model.

In some fields, such as the semiconductor manufacturing process, museum, pharmaceutical, and medicine manufacturing industry, the HVAC system needs a very fast response time to protect products and more energy-efficient buildings than traditional controllers. So, the proposed controller is designed to overcome such problems by using integrated fuzzy PI-PD Mamdani-type (FPIPDM) and cluster adaptive training based on Takagi-Sugeno-Kang (CABTSK) type. The spans of the fuzzy membership functions of the FPIPDM are tuned online by the Nelder-Mead simplex search (NMSS) algorithm to minimize time response, while the CABTSK model is tuned offline and online using a gradient descent (GD) algorithm to enhance the stability of the overall system and reject disturbances. Then, the integration framework is used to enable the concept of time-optimal based on the bang-bang code delegation. In this sense, a selected switch delegates the execution of proper control code to the action processor that provides computational resources to control indoor conditions. The predicted mean vote (PMV) index provides a higher comfort level than the temperature, as it considers six variables related to thermal comfort. The results of the proposed structure show that it improves the overall output accuracy and significantly reduces the response time. Furthermore, it increases the robustness of the indoor conditions and it is quite applicable to the MIMO HVAC systems processes with strong coupling actions between temperature and humidity, large time delay, noise, disturbances, nonlinearities, and imprecise identification model.

الوصف This paper presents two methods used for three closed-loop speed controllers of Variable-Voltage Variable-Frequency (VVVF) triple 3-phase Induction Motors (IMs) master/slave system. A dynamic dq model of a 3-phase IM in state space form and its computer simulation in the MATLAB/SIMULINK software package are described. The two different methods of speed control that are used to improve the performance of the three IMs drive systems are named conventional PI controller and PID controller. For the PID speed controller, simulation results clearly show that the response of the system is superior compared to the PI speed controller in terms of rise time, settling time, accuracy, and steady-state error. The design, analysis, and speed responses of the system obtained under both controllers have been simulated, studied, and compared using the MATLAB/Simulink environment for different operating conditions such as sudden changes in reference speed and load torque. The simulation results showed good synchronization between the master and the slave IMs with suitable tracking error

This paper suggests the use of the traditional proportional-integral-derivative (PID) controller to control the speed of multi Permanent Magnet Synchronous Motors (PMSMs). The PMSMs are commonly used in industrial applications due to their high steady state torque, high power, high efficiency, low inertia and simple control of their drives compared to the other motors drives. In the present study a mathematical model of three phase four poles PMSM is given and simulated. The closed loop speed control for this type of motors with voltage source inverter and abc to dq blocks are designed. The multi (Master/Slaves approach) method is proposed for PMSMs. Mathwork's Matlab/Simulink software package is selected to implement this model. The simulation results have illustrated that this control method can control the multi PMSMs successfully and give better performance.