ITEGAM-JETIA

Convolutional Neural Networks and Deep Learning for the detection of pneumonia in X-RAY images

2024-10-15T10:03:51-03:00

Artificial intelligence has been used in a variety of industries during the course of its growth, especially over the past decade as a result of the enormous rise in data accessibility. Its main objective is to assist people in making judgements that are more reliable, quick, and accurate. The usage of machine learning and artificial intelligence in the medical profession is growing. This is especially true for medical fields that employ a variety of biological picture kinds and where diagnostic procedures rely on collecting and analysing a substantial amount of digital data. Machine learning-based evaluation of medical photos enhances reporting uniformity and accuracy. In order to help decision-makers make the most accurate diagnosis, this study promotes the use of machine learning algorithms to evaluate chest X-ray images. With the aid of the CNN (Convolutional Neural Network) algorithm, the process will "learn" based on previously collected X-ray data from both healthy and sick patients (the training set). This research provides an approach to photo interpretation based on deep learning. This technique will reduce radiologists' burden because of its accuracy of more than 91% and nearly immediate findings, especially for those who must analyse an extensive amount of patient pictures.

Precision in Motion: enhancing autonomous driving with advanced Lane Recognition using High Resolution Network

2024-10-15T10:05:03-03:00

Autonomous cars are revolutionizing transportation by navigating roadways without human intervention using digital technology and artificial intelligence. However, reliable lane recognition is a big barrier in this endeavor. Lane identification is a complex topic that presents significant challenges to computer vision and machine learning systems. Accurate lane line detection can be challenging due to real-world driving conditions, resulting in negatively impacts steering angle prediction. In response to this difficulty, our research proposes a novel strategy to improving lane detection and steering control accuracy. To recognize lanes with better precision, we use computer vision techniques, namely semantic segmentation. Semantic segmentation allows the vehicle's internal artificial intelligence system to classify each pixel in an image as belonging to a given object class, such as road lanes. The precise lane detection required for secure and dependable navigation is addressed by this suggested methodology, which addresses a crucial part of autonomous driving technology. In this paper we have improved the accuracy and robustness of autonomous vehicles, preparing them to face the difficulties of real-world road conditions, by using HR-Net architecture.

An Online Incremental Adaptation Mechanism to Subdue the Effect of Drift in Streaming Data

2024-10-04T19:09:40-03:00

Concept drift detection and adaptation is one of the crucial components of a resilient machine learning pipeline in production. The Adaboost is an ensemble approach that incorporates incremental learning, that is widely used for concept drift adaptation in streaming data. It is generally combined with other methods such as ARF classifiers and Bagging Classifiers. This study presents a collection of online incremental learning algorithms for streaming data to adjust machine learning categorization when there is concept drift. Better results are obtained on the Australian power dataset, demonstrating the efficacy of our approach in comparison to the current benchmark.

Exploring the Mechanical Properties and Water Absorption Behavior of Keratin Fiber-Reinforced Epoxy Composites: Insights into Sustainable Manufacturing

2024-10-21T09:35:09-03:00

This study investigates the mechanical properties and the water absorption behavior of Keratin fiber-reinforced epoxy composites. The Keratin fibers were used as reinforcement with epoxy. Samples were prepared using the Hand lay-up method, having different amounts of reinforcement. The samples were characterized for their mechanical behavior as per ASTM standards. The tensile strength peaks found at 30wt% declined thereafter due to weakened interfacial bonding. Enhanced tensile moduli observed with fiber loading peaked at 30wt%. Flexural strength and modulus raised to 30wt%. Izod impact strength increased consistently with higher percentages, reaching a maximum of 40wt%. Density values closely matched with theoretical values, with epoxy composites demonstrating lower densities. The positive aspect is found that even after 40 days, only 4.04% of water was absorbed by the composite containing 40wt% fiber which shows the hydrophobic nature of the composite. Certainly, the thickness swelling behavior is notably adequate, owing to the low water absorption characteristics exhibited by fiber composite. This research highlights the significance of Keratin fibers composite in the field of automobile, shed manufacturing, and Marine products manufacturing industry.

A Blockchain-Based Digital educational certificate verification system

2024-10-31T11:19:29-03:00

The reliance on paper-based educational certificates and the lack of a robust and tamper-proof system for verifying academic credentials in the Nigerian education system make them vulnerable to forgery and alterations. The situation poses challenges in guaranteeing the legitimacy of such qualifications, and a need arises for a secure system to verify academic credentials. The proposed solution is a blockchain-based digital certificate verification system (BCVS) that utilizes the Celo blockchain as the underlying blockchain platform to store each digital certificate hash and meta-data, which is unique, secure, and permanently recorded on the blockchain. The system also includes a QR code feature to verify the certificate's authenticity instantly. Ten users evaluated the system, and the average scores are as follows: the user interface had 78%, the application database security scored 66%, the blockchain data security achieved 82%, the revocation mechanism achieved a score of 67%, and the maintainability achieved a score of 46%. While the system is designed to cater to university requirements and can revoke certificates if needed, it represents an advancement in certificate verification, thereby simplifying the process and improving the overall experience for everyone involved, with the potential to be scaled and customized for other universities, institutions, and use cases.

Load flow, short circuit and motor starting studies in Electrical Power Substations.

2024-11-01T17:45:50-03:00

Power system studies are essential for the proper planning and design of electrical power substations. This paper presents the load flow, short circuit, and motor starting studies for 33/6.6/0.44 kV electrical power substation. In this paper, the load flow study calculates the active power, reactive power, and bus voltage at various locations of the substation under various operating conditions and configurations. The short circuit study evaluates the transient performance of the substation under various fault conditions such as phase-to-ground fault and three-phase-to-ground fault cases. The motor starting studies analyze the transient performance of the substation while switching the induction motors. The modeling of 33/6.6/0.44 kV electrical power substation and simulation case studies are performed in PSCAD/EMTDC software. The simulation results show the steady state and transient performance of the substation under such scenarios.

The Evaluation of the Blended Learning Implemented at Al-Ahgaff University, Yemen: A Students’ Perspective

2024-10-04T19:09:36-03:00

Abstract—Numerous universities worldwide have implemented the blended learning as students prefer other complementary approaches of content delivery. Recently, blended learning has become the most popular educational approach that universities apply due to the involvement of information communication technology (ICT). This study aims to evaluate the bended learning implemented at Al-Ahgaff University, Yemen from the students’ perspective. A survey questionnaire was used to collect data from 28 students who involved in the blended learning, while thematic analysis technique was employed for data analysis. The students’ perspective has measured in terms of getting benefits from the blending learning, their motivation towards the blending learning, their acceptance for the environment of the blending learning, and the advantages and disadvantages of the blending learning. The evaluation results reveal that blended learning method is a modern approach for learning that assists in activating the discussion between lecturer and students, and in improving their abilities and skills in research. Nevertheless, the majority of students confirm that the blended learning environment is not suitable due to external reasons. The electricity and Internet disconnection have a negatively impact on implementing the blended learning.

Impact of Grain Boundaries on The Electrical Characteristics and Breakdown Behavior of Polycrystalline Silicon Pin Diodes: A Simulation Study

2024-11-01T17:46:42-03:00

In this paper, we present a comprehensive two-dimensional simulation program designed to model the intricate electrical characteristics of reverse-biased lateral polysilicon PIN diodes. Our methodology involves the numerical resolution of a system of partial differential equations, specifically Poisson's equation and the continuity equations for both electrons and holes, incorporating the significant effects of impact ionization. By employing this simulation approach, we are able to accurately derive the current-voltage (I-V) characteristics of the reverse-biased structure, including detailed analyses of breakdown phenomena.

The geometrical model employed in our study assumes that the polysilicon layer is composed of a sequence of crystallites with well-defined mean grain sizes. These crystallites are separated by lateral grain boundaries that run parallel to the metallurgical junction, influencing the overall electrical behavior of the diode. Our simulation results provide critical insights into the impact of these grain boundaries on the diode's performance, highlighting the role of trapping centers and their effect on the electric field distribution and carrier dynamics within the device.

Furthermore, this study discusses the implications of our findings for the design and optimization of polysilicon-based electronic components, suggesting potential improvements in device fabrication and performance. The comprehensive analysis presented in this paper not only enhances the understanding of polysilicon PIN diodes but also contributes to the broader field of semiconductor device engineering.

Precision crop prediction using IoT-enabled soil sensors and Machine Learning

2024-10-23T15:59:43-03:00

This paper introduces a cutting-edge approach for crop prediction that harnesses IoT-enabled soil sensors and machine learning models, specifically targeting cardamom, black pepper, and coffee in Idukki District, Kerala, India. The study aims to bridge the gap between soil nutrient analysis and precision agriculture by integrating a JXCT 7-in-1 soil sensor with Arduino UNO. This sensor provides accurate real-time measurements of soil moisture, temperature, pH, electrical conductivity, nitrogen, phosphorus, and potassium levels, which are critical for assessing soil health and suitability. The dataset used comprises 300 soil samples for cardamom, 320 for black pepper, and 300 for coffee, providing a robust foundation for analysis. Data from these sensors were processed using XGBoost and AdaBoost algorithms. Among the models, XGBoost achieved the highest accuracy of 91.2% and an AUC of 0.93, while AdaBoost also demonstrated strong performance with an AUC of 0.91. The results confirm the effectiveness of the system in providing precise crop suitability predictions and supporting farmers in making informed decisions based on comprehensive soil data. This approach not only improves crop yields and promotes sustainable farming practices but also shows potential for broader application in different regions and crops. Future research could expand the dataset and incorporate additional IoT devices to enhance the system’s accuracy and agricultural impact.

Advanced Dual-Loop Control Architecture for Superior PMSM Performance Utilizing Finite-Control-Set Model Predictive Control and Exponential Reaching Law Sliding Mode Control

2024-11-01T17:58:54-03:00

This article contributes to the field by providing a comprehensive dual-loop control solution that addresses the limitations of individual control techniques and offers a robust and efficient framework for advanced PMSM control. In the current loop, FCS-MPC is employed to predict the future behavior of the motor currents and select the optimal control action from a finite set of possible inputs. This method ensures minimal current ripple, improved tran sient response, and efficient handling of the non-linearities and constraints inherent in PMSM operation. The predictive nature of FCS-MPC allows for real-time optimization, enhancing the overall efficiency of the current regulation. For the speed loop, the ERL-SMC is designed to provide robust control against parameter variations and external dis turbances. The exponential reaching law ensures a faster and smoother reaching phase, reducing chattering and improving the steady-state performance. By incorporating an ERL, the sliding mode controller can swiftly bring the system states to the sliding surface and maintain them, thus achieving high accuracy in speed tracking and robust performance under various operating conditions. The combination of FCS-MPC and ERL-SMC harnesses the predictive capabilities and op timization of the former with the robustness and disturbance rejection of the latter. This hybrid control strategy is evaluated through extensive simulations in MATLAB/Simulink. The simulation results demonstrate significant improvements in dynamic response, tracking accuracy, reduced overshoot, and enhanced disturbance rejection. Additionally, the proposed approach shows superior performance in handling sudden load changes and parameter uncertainties, confirming its po tential for high-performance PMSM drive applications.

Enhancing Mechanical and Corrosion Properties of Brass Composites with Carbonized Coconut Shell Ash

2024-10-04T19:09:38-03:00

This study investigates the mechanical properties and corrosion behavior of brass (Cu-Zn alloy) reinforced with carbonized coconut shell ash (CSA) composites. The coconut shells were obtained, sun-dried, crushed, carbonized at 500 °C and sieved. The resulting CSA was then incorporated into molten brass scrap, which was first preheated to 950°C. For reproducibility purposes, several samples were prepared with varying CSA weight fraction (0wt%, 5wt%, 10wt%, and 15wt%). The samples were characterized by using metallurgical microscopes to assess their microstructure and homogeneity. The mechanical properties, including: ultimate tensile strength (UTS), hardness, impact energy, and compressive strength, were evaluated. The corrosion analysis was carried out by attaching the respective samples to a holder in the electrolytic streams of the acid and chloride solution in the constructed sand slurry pot using potentio-dynamic polarization. X-ray fluorescence was used to determine the elemental composition of the brass scraps. The results indicated that increased CSA content improved UTS, hardness, and compressive strength. However, a reduction in impact energy was observed. The sample with 15wt% weight fraction of CSA, exhibited the highest UTS (326.32 N/mm²), hardness (281.67 HRB), and compressive strength (198.3 MPa). Nevertheless, sample A with 0wt% weight fraction of CSA, showed the highest impact energy (35.59 J). Corrosion rates varied, with sample A showing the moderate rate of corrosion resistance, sample B is prone to high rate of corrosion, sample C has the poorest corrosion resistance, while sample D exhibited the best overall corrosion resistance. This study demonstrates that CSA reinforcement enhances the mechanical properties of brass composites, making them suitable for various engineering applications.

A comprehensive review on application of ai algorithms for GRID connected Solar Photovoltaic Systems

2024-11-01T17:58:58-03:00

The preponderance significant renewable energy is solar energy and corporations and governments are investing more in it every year. The most significant issues with PV systems are resolved with Artificial Intelligence (AI). Due to increased processing power, tools, and data collection, artificial intelligence (AI) is becoming more and more prevalent in diverse photovoltaic (PV) system applications. It has been discovered that the methodologies now in use for designing, forecasting, control and maintenance aspects for the solar Photovoltaic business provide findings that are somewhat erroneous. Additionally, applying AI to complete these activities has increased in accuracy and precision and is currently a very intriguing issue. Similar to this, proportional-integral-derivative controllers have unparalleled acceptance and reputation in control systems. PID tuning is still an important area of study, due to its simple structures, robustness to model errors, and easy operations, PID controllers are widely employed in engineering practices. In this context, this paper aims to review the accord among artificial intelligence (AI) applications for photovoltaic (PV) systems and Tunning of PID controllers. This Review paper analyses the appropriate application of AI for designing, maintenance and control of Grid-connected solar Photovoltaic systems as well as advanced control strategies and control algorithms for Tuning PID controller.

Impact of Nitrogen Incorporation on Band Gap Bowing in Zinc-Blende GaAs₁₋ₓNₓ: A First-Principles Study

2024-10-04T19:09:37-03:00

This study, utilizing full-potential linear muffin-tin orbital (FPLMTO) calculations within density functional theory (DFT), delved into the structural properties of zinc-blende GaAs_1-xN_x alloys. By varying the nitrogen concentration (x= (0.125, 0.083, and 0.063), we observed deviations from Vegard's law for lattice parameters and nonlinear behavior of the bulk modulus. The band gap bowing was primarily attributed to volume deformation effects, as elucidated by the Ferhat approach. Our findings demonstrate that the electronic and structural properties of GaAs_1-xN_x are strongly influenced by the nitrogen concentration. These variations present exciting opportunities for bandgap engineering and the design of wide-bandgap optoelectronic devices.

A comparison between a conventional and augmented rail gun launcher's performance.

2024-10-04T19:09:37-03:00

An electromagnetic launcher is a device that uses the interaction between the magnetic fields produced by electrical currents to accelerate a projectile. Such an accelerator constitutes an alternative to the launchers propelled by chemical reactions and offers the advantage of being able to obtain very high speeds. The aim of this paper is to compare the performances of the Conventional Rail Gun (CRG) and the Augmented Rail Gun (ARG). This last is presented in the form of a launcher (CRG) reinforced by a second pair of rails, The prototype proposed is of small gauge (60 cm in length and 15 mm in diameter). The launcher's power supply is comprised of condensers' benches, which supply current to two distinct circuits: the inner circuit connects to the projectile, while the outer circuit generates an additional magnetic field. The maximum current of the inner circuit is worth 200 kA, and that of the external circuit is equal to 300 kA. The launcher makes it possible to accelerate projectiles with one or several bridges of current; the projectile mass lies between 2.0 g and 20 g.

Solving the Unit Commitment Problem of 10-Generators Set by PSO with Different Spinning-Reserve Values Obtained From Hour-Hour Load Demand Increasing

2024-11-01T18:02:09-03:00

Regarding energy efficiency, the unit contract problem (UCP) is significant. It need to be seen as the assurance of occasions and energy commodities in which the generator offers the most value in addition to having a large amount of energy storage. In this study, we offer a novel approach to solve the UCP issue for a 10-generator test system with variable prices depending on hourly variations in power demand, utilizing particle swarm optimization (PSO). The objective is to keep energy levels sufficient to fulfill demand while reducing the total cost of producing power. Initially, a collection of objects that may hold the key to solving UCP are generated via the suggested PSO technique. Their dedications to the project and the power they create have an impact on everyone's health because of the mobility restriction. Using a combination of their own and other objects' histories, objects may discover the best solution for UCP via the iterative adjustments in speed and location made by the PSO algorithm. This strategy might boost generator economy and efficiency while also resolving the UCP issue. A number of scenarios with various storage factors should be taken into account in order to assess the PSO method's efficacy. The results demonstrate that the cost-confidence ratio is regarded as equal and that the algorithm may converge to the ideal or nearly optimal solution. The efficiency of alternative optimization techniques and the suggested PSO approach are compared using comparative analysis. The findings demonstrate that PSO is more cost-effective than earlier research in identifying the effects of rising storage prices on power consumption between 50 and 100 MW.

Assessment of Cement Content in Cured Concrete by Chemical Study of Materials Science and Sustainable Manufacturing Technology

2024-10-31T15:41:22-03:00

An effort was made in this investigation to determine the cement content in cured concrete. A test procedure used to determine calcium oxide which further leads to the assessment of cement in concrete that has been hardened was applied to the laboratory test. The content of cement of three different concrete samples that have been hardened of known proportions was precisely determined by applying the simplified California Test 403 procedure. The California Test 403 method originally used in order to determine the calcium oxide concentration in hardened concrete has been simplified by modifying several steps. The test results are verified by parameter determination of the composition in concrete by X-ray diffraction (XRD) using the JCP (Joint Committee of powder diffraction standards file) database. Good agreement between the results obtained by the titration and analytical methods of the instrument and the actual results is observed.

Hydraulic Perspective for Flow over Parabolic Weir and under Parabolic Gate

2024-11-01T17:33:16-03:00

The weir-gate structure is a very important discharge structure. Thus, understanding the hydraulic features of this structure is necessary. The water flow over the weir and under the gate was investigated experimentally. Both the weir and gate have a parabolic shape; therefore, this paper aims to understand the appropriateness of using a non-regular shape in the hydraulic features of the discharge structure. The following variables and parameters are adopted in this study: actual discharge, water depth above the weir crest, vertical distance between the weir and gate, cross-sectional area of flow that crosses the weir and gate, downstream water depth, discharge coefficient, Froude number, and Reynolds number. It is found that all these hydraulic variables and parameters depend mainly on the water flow velocity, water flow depth, and flow area that cross the weir and gate, respectively. As well, the variation in the results trend will be attributed to overlapping between weir flow velocity and gate flow velocity. The use of a weir and gate with a parabolic shape produces a slight alteration in some hydraulic features, and this can be considered one benefit of using a non-regular shape for the discharge structure. The conflict between water flow velocity and water flow depth will be reflected directly in the Froude number and Reynolds number.

The Determinants of Performance of Newspapers Industry: A Mediating Effect of Competitive Advantage

2024-10-31T16:01:20-03:00

The study examined the factors that influence the performance of Tanzania's newspaper industry. The research was guided by resource-based theory. The study employed the positivist research paradigm and an explanatory cross-sectional survey research design. A simple random sampling technique was used to produce a sample size of 300 respondents. Data were gathered using a questionnaire and a documentary review. Inferential statistics analysis was performed on the collected data using Partial Squares Structural Equation Modeling with SmartPLS 4, and descriptive statistics analysis was performed on data collected about respondents' profiles using IBM SPSS Statistics Version 26. The findings show that competitive advantage, firm resources, and reverse logistics performance all have a positive impact on the performance of the newspaper industry. The study concludes that competitive advantage, firm resources, and reverse logistics performance all influence the performance of the newspaper industry. The study recommends that newspaper companies in Tanzania and other developing countries use their competitive advantages, resources, and reverse logistics to improve the performance of the newspaper industry.

Influence of the Lubricant Temperature of Splashed Lubricated Worm Gearbox on Churning Power Losses

2024-10-31T16:04:33-03:00

The primary goal of lubricating a worm gearbox is to encourage sliding between teeth, which lowers the coefficient of friction and regulates the temperature rise brought on by rolling and sliding friction. Due to both non-load-dependent and load-dependent power losses, the worm gearbox has a relatively poor efficiency. Nonetheless, to meet the needs, there is now a greater need for more efficient worm gearboxes. Lowering churning power losses, can be accomplished. Bearing friction losses and gear friction losses make up the load-dependent losses. The non-load dependent losses are the bearing churning losses, gear windage losses, gear churning losses and oil seal losses. Numerous factors, including speed, direction of rotation, oil amount, and immersion depth, affect the non-load dependent losses.Only the impact of lubricant temperature and its relationship to non-load-dependent losses will be the focus of this study. A thorough experimental investigation was conducted utilizing the direct torque measuring method. A brand-new test rig was created, assembled, and placed into service to gauge input torque in the absence of load. We kept an eye on the fluctuating impacts of lubricant temperature on churning power loss.

Interference Reduction Scheme for Femtocell Ultra-Dense-Network: Concept and Research Challenges

2024-11-01T17:45:37-03:00

_{In recent times, the demand for mobile broadband communications has increase exponentially due to the creation of new multimedia applications. To cater for this trend, dense deployment of cellular networks with aggressive frequency reuse patterns has been proposed. In this regard, densification of femtocells is a promising concept to meet growing mobile service requirements and for sustainability of users’ Quality of Service (QoS). However, an ultra-dense network (UDN) faces serious interference problems. One of this is the Inter-Cell Interference (ICI) caused by the simultaneous usage of the same spectrum in different cells. The problem becomes more complex when femtocells are located on cell edge area of macrocell. ICI reduces system throughput and network capacity, and has a negative impact on cell-edge users. Therefore, reducing the effects of interferences is an important issue in UDN. Hence, a critical issue arises: are conventional reduction scheme still effective to tackle the interference in UDN? To shed light on the problem, this paper provides a comprehensive survey of the methods for reducing interference in femtocell UDN. This survey aimed to provide a concise introductory reference for early researchers in the development of interference reduction scheme in femtocell. These methods are classified based on the nature of operation, investigated as to their strength and weaknesses, and then examined via several research studies which make use of each approach. Furthermore, technical challenges in each research study were identified. Finally some remarks for enhancing the research study were provided and potential direction for future research were highlighted.}

UPQC-S, A Frontline Deployable Power Line Solution for Holistic Power Quality Enhancement

2024-11-01T17:45:42-03:00

The degradation of the electric power quality due to the escalated use of non-linear loads of commercial and domestic consumers of electric power connected via a distribution line, as well as those of industrial consumers of electric power connected via sub-transmission line, has necessitated to the invention of a variety of custom power devices. It seems more effective to insulate the power line from the effects of the non-linear loads and concurrently ensure a reliable, good quality power supply to all consumer loads, especially critical loads. The Unified Power Quality Conditioners (UPQC) is one such dedicated power quality improving device. Among the multitude of UPQC variants, in this paper the functioning of UPQC-S has been thoroughly investigated for diverse nonlinear loads operating under normal as well as abnormal loading conditions. UPQC-S has been designed and simulated for various nonlinear loading conditions under normal as well as abnormal network conditions. [side abnormalities.] The aforementioned simulation has been performed in MATLAB/SIMULINK.

Dynamic and Hydraulic Performance of a Peripheral Pump Impeller Made of Pineapple Fiber Reinforced Biocomposite Material

2024-10-31T16:03:25-03:00

Pumps are machines used at industrial and domestic level for the transport of incompressible fluids, the impeller being one of its main components that directly affects its performance; usually this element is manufactured in metallic materials, but there are not enough studies on its manufacture with new materials such as biocomposites reinforced with natural fibers. For this reason, this paper presents the results of the dynamic characterization and hydraulic performance of a peripheral pump impeller made of a biocomposite material reinforced with natural pineapple fibers. The biocomposite was prepared by the hand lay-up technique using a polyester resin with pineapple fibers in random distribution. A morphological and mechanical characterization of the fabricated material was carried out to evaluate the adhesion of the fiber with the matrix and to obtain the maximum tensile stress. Experimental modal analysis according to ISO 7626-2 and ISO 7626-5 standards was used to study the dynamic behavior. The hydraulic evaluation of the impeller was carried out by obtaining the pump characteristic curves using an academic-commercial test bench. The results were compared with those of a conventional metallic impeller, and lower natural frequencies were obtained in the pineapple biocomposite material. In terms of hydraulic performance, the head, power and efficiency were lower for the pineapple biocomposite impeller

Enhancing Performance of Permanent Magnet Synchronous Motor Drives Through Hybrid Feedback Linearization and Sliding Mode Control

2024-10-31T16:09:23-03:00

This paper proposes a novel hybrid control strategy that integrates Feedback Linearization Control (FBLC) with Sliding Mode Control (SMC) to significantly enhance the performance of Permanent Magnet Synchronous Motor (PMSM) drives. The proposed control strategy leverages the strengths of both FBLC and SMC to address the inherent challenges associated with PMSM control in demanding industrial applications. The FBLC component of the hybrid controller effectively linearizes the nonlinear dynamics of PMSMs. By transforming the nonlinear system into an equivalent linear system, FBLC facilitates precise trajectory tracking and improves transient response, thereby ensuring high control accuracy. This linearization process simplifies the control design and enables the implementation of advanced linear control techniques. On the other hand, the SMC component ensures robustness and reliability of the PMSM drive system. SMC is known for its inherent robustness against parameter variations, uncertainties, and external disturbances. By incorporating SMC into the hybrid controller, the system maintains stable and reliable operation even in the presence of these adverse conditions. The SMC component enhances disturbance rejection capabilities, providing a robust control solution that significantly improves the overall system performance. The integration of FBLC and SMC into a unified control architecture results in a synergistic improvement in PMSM drive performance. The hybrid FBLC-SMC controller combines the precise tracking capabilities of FBLC with the robustness of SMC, leading to superior tracking accuracy, effective disturbance rejection, and enhanced overall robustness compared to traditional control methods. Extensive simulation studies are conducted to validate the effectiveness of the proposed hybrid control strategy. The simulation results demonstrate the ability of the FBLC-SMC controller to achieve excellent performance metrics, including improved tracking accuracy, faster transient response, and robust disturbance rejection. The hybrid control strategy is shown to be a promising solution for industrial applications requiring high performance and reliability in PMSM control.

The Machine Learning for Predicting Gas Turbine Performance in Naval Vessels

2024-11-01T17:59:06-03:00

Gas turbines are essential components in modern naval vessels, providing both propulsion and power for onboard systems. However, their performance can degrade over time due to factors like fouling, erosion, and thermal fatigue, leading to increased fuel consumption and reduced operational efficiency. This paper explores the application of machine learning (ML) techniques for predicting gas turbine performance, focusing on models such as linear regression, support vector machines (SVM), random forests, and gradient boosting machines (GBM). A comprehensive literature review was conducted to assess the strengths and weaknesses of these techniques. The machine learning models were developed, fine-tuned, and evaluated using metrics such as accuracy, root mean squared error (RMSE), and R2. The results demonstrate that ensemble methods, particularly Random Forests and GBM, outperform traditional models in predicting turbine performance, offering robust, accurate, and interpretable solutions for proactive maintenance and operational optimization in naval vessels.

CONTROL-WAVE: Gesture Control Glove

2024-11-01T18:02:13-03:00

This Research work aims to address the challenges faced by teaching professionals in the Education as well as industry sector by developing an innovative wearable device known as Gesture control Glove named as control-wave equipped with advanced gesture recognition technology. Through a comprehensive understanding of the issues encountered by all the Teaching professionals, particularly regarding the navigation of digital content during lectures, the proposed research work seeks to create a comfortable, intuitive, and efficient tool that enhances their teaching experience.

The proposed solution includes wearable hand glove using flex sensors which performs operation on customizable gestures like Mouse click mode and Presentation mode. This glove allows teaching professionals to tailor the device to their individual teaching preferences and styles. Mouse click mode focuses on left and right mouse click to open or close the apps, files, and folder whereas presentation mode facilitating seamless transitions and interactions with slide content. Control-Wave is not just a technological advancement; it signifies a transformation towards a more intuitive, seamless, and user-focused way of engaging with technology. The research work aims to provide teaching professionals with a seamless and empowering tool for optimizing their workflow, promoting engagement, and improving overall teaching effectiveness with 95% of accuracy.

Acoustical Noise Mitigation in Slip Angle Controlled DTC of Open-End Winding Induction Motor Drive Using AISPWM Based Triple Randomization Scheme for EV Application

2024-11-01T18:19:20-03:00

Industrial and/or Electric Vehicle (EV) drives require low vibration, acoustical noise, as well as efficient utilisation of the DC link. Induction motors with Direct Torque Control (DTC) meet the requirements of EVs and other modern industries. Flux and/or torque oscillations, on the other hand, produce high pitch acoustical noise during steady state, which has an impact on people's health and safety. Hence comprehending and reducing these oscillations are essential for quieter response of EVs. Therefore, EVs and/or workplaces noise reduction has gained significant importance. Space Vector Pulse Width Modulation (SVPWM) enhances the efficiency of DC link utilisation, as required by EVs. However, SVPWM is ineffective at noise reduction. Even if numerous Random PWM (RPWM) approaches minimize f noise, the issue of noise reduction persists due to the lower level of randomization. This study offers an acoustical noise reduction strategy for EV applications, namely Alternate Inverter Switching (AIS) based Hybrid Triple Randomised PWMs (HTRPWM) for DTC of an Open-End Winding Induction Motor Drive with Slip Angle Control. The Harmonic Spread Factor (HSF) is a measure of acoustical noise; the lower the HSF, the less acoustical noise. Thus, the proposed HTRPWMs strive to reduce the HSF and are compared to existing approaches.

Analysis of Fuel Cell Powered EV Charging Station

2024-11-01T18:25:28-03:00

The paper offers a comparative performance analysis of fuel cell-powered EV charging systems utilizing ZETA, SEPIC, and modified SEPIC DC-DC converter topologies. Despite the cleaner energy source that fuel cells represent, their high cost has limited their penetration in EV charging. Selecting a suitable DC-DC converter topology is crucial for achieving fast charging and improved efficiency. The paper presents a performance analysis of the ZETA, SEPIC, and modified SEPIC converter topologies, both with open-loop and closed-loop control, for EV charging applications. A MATLAB/Simulink model was developed to examine the performance of these topologies in terms of battery state of charge (SoC), battery voltage, and charging current. The study reveals that the battery charged from an SoC of 50% to 50.03% using the modified SEPIC converter, while the ZETA and SEPIC converters charged to 50.024% under closed-loop control. Under open-loop control, the modified SEPIC charged to 50.025%, followed by ZETA at 50.024% and SEPIC at 50.02%, with a similar simulation time of ten seconds using a fuel cell as the primary energy source. The results demonstrate that the DC-DC modified SEPIC converter outperforms both ZETA and SEPIC converters.

The Impact of Nano Additives in Corn Oil Biodiesel used in Combustion Engines on the Environment: An Experimental Approach

2024-11-01T18:46:34-03:00

Biodiesel was made in this experiment by transesterifying corn oil. The engine's performance and emissions from fossil fuels were evaluated by adjusting the fuel mixture proportions. This investigation examined various parameters, including hydrocarbon emissions, CO, NOx emissions, brake power, mechanical efficiency, brake thermal efficiency, and indicated thermal efficiency. It had a 5.2-kilowatt diesel engine. Making biodiesel is possible by disposing of corn oil. Biodiesel is a product of blending 20% corn oil with diesel. The methyl ester of corn oil satisfied the criteria set by ASTM for fuel. Through the application of different loads to a single-cylinder four-stroke diesel engine, the experimental findings were derived. Although indicated thermal efficiency declined, the B20 blend with 100 ppm titanium oxide nanoparticles led to improvements in brake power, mean effective pressure, mechanical efficiency, and brake thermal efficiency. While the addition of TiO2 nanoparticles to B20 decreased HC and CO emissions, it increased NOx emissions. The BD20+100ppm TiO2 sample provided the most favourable outcomes, all things considered.

The Predicting Academic Performance in University Students Using Machine Learning

2024-11-01T18:55:56-03:00

In the present research, the prediction of the academic performance of university students of an undergraduate educational program is carried out by applying Machine Learning (ML) with the purpose of determining the students with academic difficulties and excellence in school performance. It is an applied research in a population of 327 students, to which a representative sample of 74 students is determined, using a proportional stratified probability sampling, in which the stratum is the semester the student is studying out of the nine that make up the study plan. The work is an applied study with a pre-experimental design of a single group, because after applying ML the results are observed and the measurements is carried out. The main conclusions obtained allow establishing a methodology for the application of ML methods in the prediction of academic performance. The best performing algorithms used are Support Vector Machine (SVM) and Neural Network (NN).

Applying Proportional–Integral–Derivative Controllers on Wired Network TCP’s Queue to Solve Its Incompatibility with the Wireless Ad-Hoc Network

2024-11-01T18:51:28-03:00

This paper offers a solution to the problem of incompatibility of the TCP designed for networks with fixed routers and the Ad-hoc network, which sometimes its mobile hosts act as routers causing a routing failure. In order to overcome this obstacle, this work presents three Ad-hoc TCP novels. The first novel is adding a controller to Ad-hoc TCP queues; this controller works as a memory in the TCP’s queue by saving the change rate of the previous error signals, then using it as a measure to change future error signal conduct. The second one is a comparison among the three Ad-hoc TCPs, which use different controllers, TCP PI/PD/PID. Finally, the models show promising results since all three Ad-hoc TCPs’ results surpass the traditional TCP’s result. Besides, the comparison process specified the best Ad-hoc TCP among the three, and that is the TCP/PID with Rise Time=3.472 ms, Overshoot=5.851%, Undershoot= -0.8264%, and Setting Time = 0.15 sec.

Process images-based controller fuzzy-PI to control efficiency in electric drives

2024-11-18T16:04:26-03:00

This paper deal about a fuzzy PI tuning from process image-based control system (IBC) for electric drives of hydro-mixture transport, which method use a [r g b] matrix as control vector from process images taken through a inferential sensor of density, to evaluation efficiency in electric drives for hydro-transport of laterite pulp with centrifugal pumps.